From 146fa3ea1d98b5e1dc97718481d89294a4f10033 Mon Sep 17 00:00:00 2001 From: Mohamed Hamidi Date: Wed, 28 Oct 2026 21:33:32 +0100 Subject: [PATCH 1/4] chore(pricing): refresh models.dev snapshot with model card facts --- src/opentab/data/models.json | 44167 ++++++++++++++++++++++++++------- 1 file changed, 35776 insertions(+), 8391 deletions(-) diff --git a/src/opentab/data/models.json b/src/opentab/data/models.json index 62e9de7..4e2ce7c 100644 --- a/src/opentab/data/models.json +++ b/src/opentab/data/models.json @@ -1,5 +1,5 @@ { - "fetched_at": "2026-10-23T14:27:43Z", + "fetched_at": "2026-10-28T16:24:47Z", "providers": { "302ai": { "models": { @@ -10,7 +10,9 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 128000, + "released": "2025-06-16" }, "MiniMax-M2": { "cost": [ @@ -19,7 +21,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 128000, + "open": true, + "released": "2025-10-27" }, "MiniMax-M2.1": { "cost": [ @@ -28,7 +33,10 @@ 0.0, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-12-23" }, "MiniMax-M2.5": { "cost": [ @@ -37,7 +45,10 @@ 0.0, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-02-12" }, "MiniMax-M2.7": { "cost": [ @@ -46,7 +57,10 @@ 0.0, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-03-18" }, "MiniMax-M3": { "cost": [ @@ -56,6 +70,9 @@ 0.9 ], "limit": 1048576, + "max_output": 512000, + "open": true, + "released": "2026-06-01", "tiers": [ { "cost": [ @@ -78,7 +95,10 @@ 1.0, 12.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-09" }, "claude-fable-5-1": { "cost": [ @@ -87,7 +107,10 @@ 0.25, 12.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-01" }, "claude-haiku-4-5": { "cost": [ @@ -96,7 +119,10 @@ 0.0, 0.0 ], - "limit": 200000 + "knowledge": "2025-02-28", + "limit": 200000, + "max_output": 64000, + "released": "2025-10-15" }, "claude-haiku-4-5-20251001": { "cost": [ @@ -105,7 +131,10 @@ 0.0, 0.0 ], - "limit": 200000 + "knowledge": "2025-02-28", + "limit": 200000, + "max_output": 64000, + "released": "2025-10-15" }, "claude-haiku-5-5": { "cost": [ @@ -114,7 +143,10 @@ 0.01, 0.125 ], + "knowledge": "2026-06", "limit": 1000000, + "max_output": 128000, + "released": "2026-10-07", "tiers": [ { "cost": [ @@ -137,7 +169,10 @@ 1.5, 18.75 ], - "limit": 200000 + "knowledge": "2025-03-31", + "limit": 200000, + "max_output": 32000, + "released": "2025-08-05" }, "claude-opus-4-1-20250805-thinking": { "cost": [ @@ -146,7 +181,10 @@ 0.0, 0.0 ], - "limit": 200000 + "knowledge": "2025-03-31", + "limit": 200000, + "max_output": 32000, + "released": "2025-08-05" }, "claude-opus-4-5-20251101": { "cost": [ @@ -155,7 +193,10 @@ 0.0, 0.0 ], - "limit": 200000 + "knowledge": "2025-03-31", + "limit": 200000, + "max_output": 64000, + "released": "2025-11-24" }, "claude-opus-4-7": { "cost": [ @@ -164,7 +205,10 @@ 0.5, 6.25 ], + "knowledge": "2026-01-31", "limit": 1000000, + "max_output": 128000, + "released": "2026-04-16", "tiers": [ { "cost": [ @@ -187,7 +231,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-16" }, "claude-opus-4-8": { "cost": [ @@ -196,7 +243,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-28" }, "claude-opus-5": { "cost": [ @@ -205,7 +255,10 @@ 0.5, 5.0 ], - "limit": 1000000 + "knowledge": "2026-05", + "limit": 1000000, + "max_output": 128000, + "released": "2026-07-24" }, "claude-opus-5-5": { "cost": [ @@ -214,7 +267,10 @@ 0.2, 5.0 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-22" }, "claude-opus-5-thinking": { "cost": [ @@ -223,7 +279,10 @@ 0.5, 5.0 ], - "limit": 1000000 + "knowledge": "2026-05", + "limit": 1000000, + "max_output": 128000, + "released": "2026-07-24" }, "claude-sonnet-4-5-20250929": { "cost": [ @@ -232,7 +291,10 @@ 0.3, 3.75 ], + "knowledge": "2025-07-31", "limit": 200000, + "max_output": 64000, + "released": "2025-09-29", "tiers": [ { "cost": [ @@ -255,7 +317,10 @@ 0.3, 3.75 ], + "knowledge": "2025-03", "limit": 200000, + "max_output": 64000, + "released": "2025-09-29", "tiers": [ { "cost": [ @@ -278,7 +343,10 @@ 0.3, 3.75 ], + "knowledge": "2025-08-31", "limit": 1000000, + "max_output": 64000, + "released": "2026-02-17", "tiers": [ { "cost": [ @@ -301,7 +369,10 @@ 0.3, 3.75 ], + "knowledge": "2025-08-31", "limit": 1000000, + "max_output": 64000, + "released": "2026-02-17", "tiers": [ { "cost": [ @@ -324,7 +395,10 @@ 0.2, 2.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-30" }, "claude-sonnet-5-5": { "cost": [ @@ -333,7 +407,10 @@ 0.2, 2.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-28" }, "deepseek-flash": { "cost": [ @@ -342,7 +419,11 @@ 0.003, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-09-10" }, "deepseek-v3.2": { "cost": [ @@ -351,7 +432,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-12", + "limit": 128000, + "max_output": 8192, + "open": true, + "released": "2025-12-01" }, "deepseek-v3.2-thinking": { "cost": [ @@ -360,7 +445,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-12", + "limit": 128000, + "max_output": 128000, + "open": true, + "released": "2025-12-01" }, "doubao-seed-1-6-thinking-250715": { "cost": [ @@ -369,7 +458,9 @@ 0.0, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 16000, + "released": "2025-07-15" }, "doubao-seed-1-6-vision-250815": { "cost": [ @@ -378,7 +469,9 @@ 0.0, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 32000, + "released": "2025-08-15" }, "doubao-seed-1-8-251215": { "cost": [ @@ -388,6 +481,8 @@ 0.0 ], "limit": 224000, + "max_output": 64000, + "released": "2025-12-28", "tiers": [ { "cost": [ @@ -422,7 +517,10 @@ 0.0, 0.0 ], - "limit": 2000000 + "knowledge": "2024-11", + "limit": 2000000, + "max_output": 8192, + "released": "2024-12-11" }, "gemini-2.5-flash": { "cost": [ @@ -431,7 +529,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-01", + "limit": 1000000, + "max_output": 65536, + "released": "2025-06-17" }, "gemini-2.5-flash-image": { "cost": [ @@ -440,7 +541,11 @@ 0.0, 0.0 ], - "limit": 32768 + "knowledge": "2025-01", + "limit": 32768, + "max_output": 32768, + "released": "2025-08-26", + "type": "image" }, "gemini-2.5-flash-lite-preview-09-2025": { "cost": [ @@ -449,7 +554,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-01", + "limit": 1000000, + "max_output": 65536, + "released": "2025-09-26" }, "gemini-2.5-flash-nothink": { "cost": [ @@ -458,7 +566,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-01", + "limit": 1000000, + "max_output": 65536, + "released": "2025-06-17" }, "gemini-2.5-flash-preview-09-2025": { "cost": [ @@ -467,7 +578,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-01", + "limit": 1000000, + "max_output": 65536, + "released": "2025-09-26" }, "gemini-2.5-pro": { "cost": [ @@ -476,7 +590,10 @@ 0.0, 0.0 ], + "knowledge": "2025-01", "limit": 1000000, + "max_output": 65536, + "released": "2025-06-17", "tiers": [ { "cost": [ @@ -499,7 +616,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-06", + "limit": 1000000, + "max_output": 65536, + "released": "2025-12-17" }, "gemini-3-pro-image-preview": { "cost": [ @@ -508,7 +628,11 @@ 0.0, 0.0 ], - "limit": 32768 + "knowledge": "2025-06", + "limit": 32768, + "max_output": 64000, + "released": "2025-11-20", + "type": "image" }, "gemini-3-pro-preview": { "cost": [ @@ -517,7 +641,10 @@ 0.0, 0.0 ], + "knowledge": "2025-06", "limit": 1000000, + "max_output": 64000, + "released": "2025-11-18", "tiers": [ { "cost": [ @@ -540,7 +667,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2025-01", + "limit": 131072, + "max_output": 32768, + "released": "2026-02-26", + "type": "image" }, "gemini-3.1-flash-lite": { "cost": [ @@ -549,7 +680,10 @@ 0.03, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-05-07" }, "gemini-3.1-flash-lite-preview": { "cost": [ @@ -558,7 +692,10 @@ 0.0, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-03-03" }, "gemini-3.1-pro-preview": { "cost": [ @@ -567,7 +704,10 @@ 0.0, 0.0 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2026-02-19", "tiers": [ { "cost": [ @@ -590,7 +730,10 @@ 0.0, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-05-19" }, "gemini-3.5-flash-lite": { "cost": [ @@ -599,7 +742,10 @@ 0.03, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-07-21" }, "gemini-3.5-flash-thinking": { "cost": [ @@ -608,7 +754,10 @@ 0.0, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-05-19" }, "gemini-3.6-flash": { "cost": [ @@ -617,7 +766,10 @@ 0.15, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-07-21" }, "gemini-3.7-flash": { "cost": [ @@ -626,7 +778,10 @@ 0.075, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-08-13" }, "gemini-3.8-flash": { "cost": [ @@ -635,7 +790,9 @@ 0.075, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65536, + "released": "2026-09-02" }, "gemini-4-argon": { "cost": [ @@ -644,7 +801,10 @@ 0.2, 0.375 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-10-13" }, "glm-4.5": { "cost": [ @@ -653,7 +813,11 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 131072, + "max_output": 98304, + "open": true, + "released": "2025-07-28", "tiers": [ { "cost": [ @@ -676,7 +840,11 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 64000, + "max_output": 16384, + "open": true, + "released": "2025-08-11", "tiers": [ { "cost": [ @@ -699,7 +867,11 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-09-30", "tiers": [ { "cost": [ @@ -722,7 +894,11 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 128000, + "max_output": 32768, + "open": true, + "released": "2025-12-08", "tiers": [ { "cost": [ @@ -745,7 +921,11 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-12-22", "tiers": [ { "cost": [ @@ -769,6 +949,9 @@ 0.0 ], "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-02-12", "tiers": [ { "cost": [ @@ -792,6 +975,8 @@ 0.0 ], "limit": 200000, + "max_output": 131072, + "released": "2026-03-16", "tiers": [ { "cost": [ @@ -814,7 +999,10 @@ 0.26, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 131072, + "open": true, + "released": "2026-04-07" }, "glm-5.2": { "cost": [ @@ -823,7 +1011,10 @@ 0.26, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "glm-5.3": { "cost": [ @@ -832,7 +1023,10 @@ 0.26, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "glm-5.3-flash": { "cost": [ @@ -841,7 +1035,10 @@ 0.015, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-26" }, "glm-5v-turbo": { "cost": [ @@ -851,6 +1048,8 @@ 0.0 ], "limit": 200000, + "max_output": 131072, + "released": "2026-04-01", "tiers": [ { "cost": [ @@ -873,7 +1072,10 @@ 0.0, 0.0 ], - "limit": 1047576 + "knowledge": "2024-04", + "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14" }, "gpt-4.1-mini": { "cost": [ @@ -882,7 +1084,10 @@ 0.0, 0.0 ], - "limit": 1047576 + "knowledge": "2024-04", + "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14" }, "gpt-4.1-nano": { "cost": [ @@ -891,7 +1096,10 @@ 0.0, 0.0 ], - "limit": 1047576 + "knowledge": "2024-04", + "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14" }, "gpt-4o": { "cost": [ @@ -900,7 +1108,10 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-05-13" }, "gpt-5": { "cost": [ @@ -909,7 +1120,10 @@ 0.0, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "gpt-5-mini": { "cost": [ @@ -918,7 +1132,10 @@ 0.025, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "gpt-5-pro": { "cost": [ @@ -927,7 +1144,10 @@ 0.005, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 272000, + "released": "2025-10-06" }, "gpt-5-thinking": { "cost": [ @@ -936,7 +1156,10 @@ 0.0, 0.0 ], - "limit": 400000 + "knowledge": "2024-10", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "gpt-5.1": { "cost": [ @@ -945,7 +1168,10 @@ 0.0, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "gpt-5.1-chat-latest": { "cost": [ @@ -954,7 +1180,10 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-09-30", + "limit": 128000, + "max_output": 16384, + "released": "2025-11-13" }, "gpt-5.2": { "cost": [ @@ -963,7 +1192,10 @@ 0.0, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "gpt-5.2-chat-latest": { "cost": [ @@ -972,7 +1204,10 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2025-08-31", + "limit": 128000, + "max_output": 16384, + "released": "2025-12-11" }, "gpt-5.3-chat-latest": { "cost": [ @@ -981,7 +1216,10 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2025-08-31", + "limit": 128000, + "max_output": 16384, + "released": "2026-03-03" }, "gpt-5.4": { "cost": [ @@ -990,7 +1228,10 @@ 0.25, 0.0 ], + "knowledge": "2025-08-31", "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05", "tiers": [ { "cost": [ @@ -1013,7 +1254,10 @@ 0.075, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "gpt-5.4-nano": { "cost": [ @@ -1022,7 +1266,10 @@ 0.02, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "gpt-5.5": { "cost": [ @@ -1031,7 +1278,10 @@ 0.5, 0.0 ], + "knowledge": "2025-12-01", "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23", "tiers": [ { "cost": [ @@ -1054,7 +1304,10 @@ 0.02, 0.0 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "gpt-5.6-luna-pro": { "cost": [ @@ -1063,7 +1316,10 @@ 0.02, 0.0 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "gpt-5.6-sol": { "cost": [ @@ -1072,7 +1328,10 @@ 0.5, 0.0 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "gpt-5.6-sol-pro": { "cost": [ @@ -1081,7 +1340,10 @@ 0.5, 0.0 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "gpt-5.6-terra": { "cost": [ @@ -1090,7 +1352,10 @@ 0.2, 0.0 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "gpt-5.6-terra-pro": { "cost": [ @@ -1099,7 +1364,10 @@ 0.2, 0.0 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "gpt-6-astra": { "cost": [ @@ -1108,7 +1376,10 @@ 1.0, 0.0 ], - "limit": 1050000 + "knowledge": "2026-04-30", + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-04" }, "gpt-6-luna": { "cost": [ @@ -1117,7 +1388,10 @@ 0.01, 0.125 ], + "knowledge": "2026-05-18", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -1140,7 +1414,10 @@ 0.2, 2.5 ], + "knowledge": "2026-04-20", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -1163,7 +1440,10 @@ 0.1, 2.5 ], + "knowledge": "2026-04-30", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-29", "tiers": [ { "cost": [ @@ -1186,7 +1466,10 @@ 0.0, 0.0 ], - "limit": 2000000 + "knowledge": "2025-06", + "limit": 2000000, + "max_output": 30000, + "released": "2025-11-19" }, "grok-4-fast-non-reasoning": { "cost": [ @@ -1195,7 +1478,10 @@ 0.0, 0.0 ], - "limit": 2000000 + "knowledge": "2025-06", + "limit": 2000000, + "max_output": 30000, + "released": "2025-12-18" }, "grok-4-fast-reasoning": { "cost": [ @@ -1204,7 +1490,10 @@ 0.0, 0.0 ], - "limit": 2000000 + "knowledge": "2025-06", + "limit": 2000000, + "max_output": 30000, + "released": "2025-12-18" }, "grok-4.1": { "cost": [ @@ -1213,7 +1502,10 @@ 0.0, 0.0 ], - "limit": 200000 + "knowledge": "2025-06", + "limit": 200000, + "max_output": 64000, + "released": "2025-11-18" }, "grok-4.20-beta-0309-reasoning": { "cost": [ @@ -1222,7 +1514,9 @@ 0.0, 0.0 ], - "limit": 2000000 + "limit": 2000000, + "max_output": 30000, + "released": "2026-03-09" }, "grok-4.3": { "cost": [ @@ -1231,7 +1525,9 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 30000, + "released": "2026-04-17" }, "grok-4.5": { "cost": [ @@ -1240,7 +1536,9 @@ 0.5, 0.0 ], - "limit": 500000 + "limit": 500000, + "max_output": 500000, + "released": "2026-07-08" }, "grok-4.6": { "cost": [ @@ -1249,7 +1547,10 @@ 0.5, 0.0 ], - "limit": 500000 + "knowledge": "2026-02-01", + "limit": 500000, + "max_output": 500000, + "released": "2026-08-12" }, "grok-4.7": { "cost": [ @@ -1258,7 +1559,10 @@ 0.5, 0.5 ], - "limit": 500000 + "knowledge": "2026-05", + "limit": 500000, + "max_output": 500000, + "released": "2026-09-21" }, "kimi-k2-0905-preview": { "cost": [ @@ -1267,7 +1571,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-06", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2025-09-05" }, "kimi-k2-thinking": { "cost": [ @@ -1276,7 +1584,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-06", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2025-11-06" }, "kimi-k2.5": { "cost": [ @@ -1285,7 +1597,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-01-27" }, "kimi-k2.6": { "cost": [ @@ -1294,7 +1610,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-20" }, "kimi-k2.7-code": { "cost": [ @@ -1303,7 +1623,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-06-12" }, "kimi-k3": { "cost": [ @@ -1312,7 +1636,21 @@ 0.3, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-16" + }, + "kimi-k3.1-pro": { + "cost": [ + 2.4, + 12.0, + 0.24, + 0.0 + ], + "limit": 1048576, + "max_output": 131072, + "released": "2026-10-23" }, "ministral-14b-2512": { "cost": [ @@ -1321,7 +1659,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-12", + "limit": 128000, + "max_output": 128000, + "open": true, + "released": "2025-12-02" }, "mistral-large-2512": { "cost": [ @@ -1330,7 +1672,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-12", + "limit": 128000, + "max_output": 262144, + "open": true, + "released": "2025-12-02" }, "o3": { "cost": [ @@ -1339,7 +1685,10 @@ 0.0, 0.0 ], - "limit": 200000 + "knowledge": "2024-05", + "limit": 200000, + "max_output": 100000, + "released": "2025-04-16" }, "qwen3-235b-a22b": { "cost": [ @@ -1348,7 +1697,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2025-04", + "limit": 128000, + "max_output": 16384, + "open": true, + "released": "2025-04-28" }, "qwen3-235b-a22b-instruct-2507": { "cost": [ @@ -1357,7 +1710,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2025-04", + "limit": 128000, + "max_output": 65536, + "open": true, + "released": "2025-07-21" }, "qwen3-30b-a3b": { "cost": [ @@ -1366,7 +1723,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2025-04", + "limit": 128000, + "max_output": 8192, + "open": true, + "released": "2025-04-28" }, "qwen3-coder-480b-a35b-instruct": { "cost": [ @@ -1375,7 +1736,11 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2025-07-22", "tiers": [ { "cost": [ @@ -1410,7 +1775,10 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 258048, + "max_output": 65536, + "released": "2025-09-23", "tiers": [ { "cost": [ @@ -1446,6 +1814,9 @@ 0.0 ], "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-23", "tiers": [ { "cost": [ @@ -1468,7 +1839,10 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 1000000, + "max_output": 65536, + "released": "2026-02-16", "tiers": [ { "cost": [ @@ -1503,7 +1877,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-04-17" }, "qwen3.6-flash": { "cost": [ @@ -1513,6 +1890,8 @@ 0.214 ], "limit": 1000000, + "max_output": 65536, + "released": "2026-04-27", "tiers": [ { "cost": [ @@ -1535,7 +1914,10 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 1000000, + "max_output": 65536, + "released": "2026-04-02", "tiers": [ { "cost": [ @@ -1558,7 +1940,9 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-05-21" }, "qwen3.7-max-2026-06-08": { "cost": [ @@ -1567,7 +1951,9 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-05-21" }, "qwen3.7-plus": { "cost": [ @@ -1576,7 +1962,10 @@ 0.023, 0.286 ], + "knowledge": "2025-04", "limit": 1000000, + "max_output": 64000, + "released": "2026-06-02", "tiers": [ { "cost": [ @@ -1599,7 +1988,9 @@ 0.016, 0.2 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-08-26" }, "qwen3.8-max": { "cost": [ @@ -1608,7 +1999,9 @@ 0.168, 2.58 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-08-03" } }, "name": "302.AI" @@ -1622,7 +2015,10 @@ 0.0, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-03-18" }, "MiniMaxAI/MiniMax-M3": { "cost": [ @@ -1631,7 +2027,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-01" }, "Qwen/QwQ-32B": { "cost": [ @@ -1640,7 +2039,11 @@ 0.0, 0.0 ], + "knowledge": "2024-04", "limit": 32768, + "max_output": 32768, + "open": true, + "released": "2025-03-05", "status": "deprecated" }, "Qwen/Qwen2.5-72B-Instruct": { @@ -1651,6 +2054,9 @@ 0.0 ], "limit": 128000, + "max_output": 8192, + "open": true, + "released": "2024-09-19", "status": "deprecated" }, "Qwen/Qwen3-235B-A22B-Instruct-2507": { @@ -1661,6 +2067,9 @@ 0.0 ], "limit": 262144, + "max_output": 8192, + "open": true, + "released": "2025-07-21", "status": "deprecated" }, "Qwen/Qwen3-32B": { @@ -1670,7 +2079,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2025-04", + "limit": 131072, + "max_output": 8192, + "open": true, + "released": "2025-04-28" }, "Qwen/Qwen3-Coder-480B-A35B-Instruct": { "cost": [ @@ -1679,7 +2092,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-04", + "limit": 262144, + "max_output": 16384, + "open": true, + "released": "2025-07-22" }, "Qwen/Qwen3.6-27B": { "cost": [ @@ -1688,7 +2105,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 8192, + "open": true, + "released": "2026-04-22" }, "claude-3-7-sonnet-20250219": { "cost": [ @@ -1697,7 +2117,10 @@ 0.0, 0.0 ], + "knowledge": "2024-10-31", "limit": 200000, + "max_output": 64000, + "released": "2025-02-19", "status": "deprecated" }, "claude-fable-5": { @@ -1707,7 +2130,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-09" }, "claude-haiku-4-5-20251001": { "cost": [ @@ -1716,7 +2142,10 @@ 0.0, 0.0 ], - "limit": 200000 + "knowledge": "2025-02-28", + "limit": 200000, + "max_output": 64000, + "released": "2025-10-15" }, "claude-opus-4-1-20250805": { "cost": [ @@ -1725,7 +2154,10 @@ 0.0, 0.0 ], + "knowledge": "2025-03-31", "limit": 200000, + "max_output": 32000, + "released": "2025-08-05", "status": "deprecated" }, "claude-opus-4-20250514": { @@ -1735,7 +2167,10 @@ 0.0, 0.0 ], + "knowledge": "2025-03-31", "limit": 200000, + "max_output": 32000, + "released": "2025-05-22", "status": "deprecated" }, "claude-opus-4-5-20251101": { @@ -1745,7 +2180,10 @@ 0.0, 0.0 ], - "limit": 200000 + "knowledge": "2025-05", + "limit": 200000, + "max_output": 64000, + "released": "2025-11-24" }, "claude-opus-4-6": { "cost": [ @@ -1754,7 +2192,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-05" }, "claude-opus-4-7": { "cost": [ @@ -1763,7 +2204,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-16" }, "claude-opus-4-8": { "cost": [ @@ -1772,7 +2216,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2026-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-28" }, "claude-opus-5": { "cost": [ @@ -1781,7 +2228,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2026-05", + "limit": 1000000, + "max_output": 128000, + "released": "2026-07-24" }, "claude-sonnet-4-20250514": { "cost": [ @@ -1790,7 +2240,10 @@ 0.0, 0.0 ], + "knowledge": "2025-03-31", "limit": 200000, + "max_output": 64000, + "released": "2025-05-22", "status": "deprecated" }, "claude-sonnet-4-5-20250929": { @@ -1800,7 +2253,10 @@ 0.0, 0.0 ], - "limit": 200000 + "knowledge": "2025-07-31", + "limit": 200000, + "max_output": 64000, + "released": "2025-09-29" }, "claude-sonnet-4-6": { "cost": [ @@ -1809,7 +2265,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-08-31", + "limit": 1000000, + "max_output": 64000, + "released": "2026-02-17" }, "claude-sonnet-5": { "cost": [ @@ -1818,7 +2277,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 64000, + "released": "2026-06-30" }, "deepseek-ai/DeepSeek-R1": { "cost": [ @@ -1827,7 +2289,11 @@ 0.0, 0.0 ], + "knowledge": "2024-07", "limit": 128000, + "max_output": 8192, + "open": true, + "released": "2025-01-20", "status": "deprecated" }, "deepseek-ai/DeepSeek-V3.1-Terminus": { @@ -1838,6 +2304,9 @@ 0.0 ], "limit": 128000, + "max_output": 8192, + "open": true, + "released": "2025-06-01", "status": "deprecated" }, "deepseek-ai/DeepSeek-V3.2": { @@ -1847,7 +2316,11 @@ 0.0, 0.0 ], + "knowledge": "2024-07", "limit": 128000, + "max_output": 8192, + "open": true, + "released": "2025-12-01", "status": "deprecated" }, "deepseek-ai/DeepSeek-V4-Flash": { @@ -1857,7 +2330,11 @@ 0.03, 0.0 ], + "knowledge": "2025-05", "limit": 1000000, + "max_output": 32768, + "open": true, + "released": "2026-04-24", "status": "deprecated" }, "deepseek-ai/DeepSeek-V4-Pro": { @@ -1867,7 +2344,11 @@ 0.15, 0.0 ], + "knowledge": "2025-05", "limit": 1000000, + "max_output": 32768, + "open": true, + "released": "2026-04-24", "status": "deprecated" }, "deepseek/deepseek-v3.1": { @@ -1878,6 +2359,9 @@ 0.0 ], "limit": 128000, + "max_output": 8192, + "open": true, + "released": "2025-08-21", "status": "deprecated" }, "gemini-2.5-flash": { @@ -1887,7 +2371,10 @@ 0.03, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2025-06-17" }, "gemini-2.5-flash-image": { "cost": [ @@ -1896,7 +2383,11 @@ 0.0, 0.0 ], - "limit": 32768 + "knowledge": "2024-06", + "limit": 32768, + "max_output": 32768, + "released": "2025-08-26", + "type": "image" }, "gemini-2.5-pro": { "cost": [ @@ -1905,7 +2396,10 @@ 0.125, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2025-06-17" }, "gemini-3-flash-preview": { "cost": [ @@ -1914,7 +2408,10 @@ 0.05, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2025-12-17" }, "gemini-3-pro-image": { "cost": [ @@ -1923,7 +2420,11 @@ 0.2, 0.0 ], - "limit": 65536 + "knowledge": "2025-01", + "limit": 65536, + "max_output": 32768, + "released": "2026-05-28", + "type": "image" }, "gemini-3-pro-image-preview": { "cost": [ @@ -1932,8 +2433,12 @@ 0.2, 0.0 ], + "knowledge": "2025-01", "limit": 65536, - "status": "deprecated" + "max_output": 32768, + "released": "2025-11-20", + "status": "deprecated", + "type": "image" }, "gemini-3.1-flash-image": { "cost": [ @@ -1942,8 +2447,12 @@ 0.0, 0.0 ], + "knowledge": "2025-01", "limit": 1048576, - "status": "deprecated" + "max_output": 32768, + "released": "2026-05-28", + "status": "deprecated", + "type": "image" }, "gemini-3.1-flash-image-preview": { "cost": [ @@ -1952,8 +2461,12 @@ 0.0, 0.0 ], + "knowledge": "2025-01", "limit": 1048576, - "status": "deprecated" + "max_output": 32768, + "released": "2026-02-26", + "status": "deprecated", + "type": "image" }, "gemini-3.1-flash-lite": { "cost": [ @@ -1962,7 +2475,10 @@ 0.025, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-05-07" }, "gemini-3.1-flash-lite-preview": { "cost": [ @@ -1971,7 +2487,10 @@ 0.025, 1.0 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2026-03-03", "status": "deprecated" }, "gemini-3.1-pro-preview": { @@ -1981,7 +2500,10 @@ 0.2, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-02-19" }, "gemini-3.5-flash": { "cost": [ @@ -1990,7 +2512,10 @@ 0.15, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-05-19" }, "gemini-3.5-flash-lite": { "cost": [ @@ -1999,7 +2524,10 @@ 0.03, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-07-21" }, "gemini-3.6-flash": { "cost": [ @@ -2008,7 +2536,10 @@ 0.075, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-07-21" }, "gemini-3.7-flash": { "cost": [ @@ -2017,7 +2548,10 @@ 0.075, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-08-13" }, "google/gemma-4-31b-it": { "cost": [ @@ -2026,7 +2560,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 131072, + "open": true, + "released": "2026-04-02" }, "gpt-4.1": { "cost": [ @@ -2035,7 +2573,10 @@ 0.5, 0.0 ], - "limit": 1047576 + "knowledge": "2024-04", + "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14" }, "gpt-4.1-mini": { "cost": [ @@ -2044,7 +2585,10 @@ 0.1, 0.0 ], - "limit": 1047576 + "knowledge": "2024-04", + "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14" }, "gpt-4.1-nano": { "cost": [ @@ -2053,7 +2597,10 @@ 0.025, 0.0 ], - "limit": 1047576 + "knowledge": "2024-04", + "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14" }, "gpt-4o": { "cost": [ @@ -2062,7 +2609,10 @@ 1.25, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-05-13" }, "gpt-4o-2024-11-20": { "cost": [ @@ -2071,7 +2621,10 @@ 0.0, 0.0 ], + "knowledge": "2024-10", "limit": 128000, + "max_output": 16384, + "released": "2024-11-20", "status": "deprecated" }, "gpt-4o-mini": { @@ -2081,7 +2634,10 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-07-18" }, "gpt-5": { "cost": [ @@ -2090,7 +2646,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "gpt-5-codex": { "cost": [ @@ -2099,7 +2658,10 @@ 0.125, 0.0 ], + "knowledge": "2024-09-30", "limit": 400000, + "max_output": 128000, + "released": "2025-09-15", "status": "deprecated" }, "gpt-5-mini": { @@ -2109,7 +2671,10 @@ 0.025, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "gpt-5-nano": { "cost": [ @@ -2118,7 +2683,10 @@ 0.005, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "gpt-5.1": { "cost": [ @@ -2127,7 +2695,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "gpt-5.1-chat-latest": { "cost": [ @@ -2136,7 +2707,10 @@ 0.0, 0.0 ], + "knowledge": "2024-09-30", "limit": 400000, + "max_output": 128000, + "released": "2025-11-13", "status": "deprecated" }, "gpt-5.1-codex": { @@ -2146,7 +2720,10 @@ 0.125, 0.0 ], + "knowledge": "2024-09-30", "limit": 400000, + "max_output": 128000, + "released": "2025-11-13", "status": "deprecated" }, "gpt-5.1-codex-max": { @@ -2156,7 +2733,10 @@ 0.0, 0.0 ], + "knowledge": "2024-09-30", "limit": 400000, + "max_output": 128000, + "released": "2025-11-13", "status": "deprecated" }, "gpt-5.2": { @@ -2166,7 +2746,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "gpt-5.2-chat-latest": { "cost": [ @@ -2175,7 +2758,10 @@ 0.0, 0.0 ], + "knowledge": "2024-09-30", "limit": 400000, + "max_output": 128000, + "released": "2025-12-11", "status": "deprecated" }, "gpt-5.2-codex": { @@ -2185,7 +2771,10 @@ 0.175, 0.0 ], + "knowledge": "2025-08-31", "limit": 400000, + "max_output": 128000, + "released": "2025-12-11", "status": "deprecated" }, "gpt-5.3-chat-latest": { @@ -2195,7 +2784,10 @@ 0.0, 0.0 ], + "knowledge": "2025-08-31", "limit": 400000, + "max_output": 128000, + "released": "2026-03-03", "status": "deprecated" }, "gpt-5.3-codex": { @@ -2205,7 +2797,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-02-05" }, "gpt-5.3-codex-xhigh": { "cost": [ @@ -2214,7 +2809,10 @@ 0.0, 0.0 ], + "knowledge": "2025-08-31", "limit": 400000, + "max_output": 128000, + "released": "2026-02-05", "status": "deprecated" }, "gpt-5.4": { @@ -2224,7 +2822,10 @@ 0.25, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-05" }, "gpt-5.4-mini": { "cost": [ @@ -2233,7 +2834,10 @@ 0.075, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "gpt-5.4-nano": { "cost": [ @@ -2242,7 +2846,10 @@ 0.02, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "gpt-5.5": { "cost": [ @@ -2251,7 +2858,10 @@ 0.5, 0.0 ], - "limit": 1000000 + "knowledge": "2025-12-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-23" }, "gpt-5.6-luna": { "cost": [ @@ -2260,7 +2870,10 @@ 0.02, 0.0 ], - "limit": 1000000 + "knowledge": "2026-02-16", + "limit": 1000000, + "max_output": 128000, + "released": "2026-07-09" }, "gpt-5.6-sol": { "cost": [ @@ -2269,7 +2882,10 @@ 0.4, 0.0 ], - "limit": 1000000 + "knowledge": "2026-02-16", + "limit": 1000000, + "max_output": 128000, + "released": "2026-07-09" }, "gpt-5.6-terra": { "cost": [ @@ -2278,7 +2894,10 @@ 0.2, 0.0 ], - "limit": 1000000 + "knowledge": "2026-02-16", + "limit": 1000000, + "max_output": 128000, + "released": "2026-07-09" }, "grok-4-0709": { "cost": [ @@ -2288,6 +2907,8 @@ 0.0 ], "limit": 256000, + "max_output": 16384, + "released": "2025-07-09", "status": "deprecated" }, "grok-4-1-fast-non-reasoning": { @@ -2298,6 +2919,8 @@ 0.0 ], "limit": 2000000, + "max_output": 16384, + "released": "2025-11-17", "status": "deprecated" }, "grok-4-fast-non-reasoning": { @@ -2308,6 +2931,8 @@ 0.0 ], "limit": 2000000, + "max_output": 16384, + "released": "2025-12-18", "status": "deprecated" }, "grok-4.3": { @@ -2317,7 +2942,9 @@ 0.2, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 32768, + "released": "2026-04-17" }, "grok-4.5": { "cost": [ @@ -2326,7 +2953,9 @@ 0.3, 0.0 ], - "limit": 500000 + "limit": 500000, + "max_output": 32768, + "released": "2026-07-08" }, "grok-4.6": { "cost": [ @@ -2335,7 +2964,10 @@ 0.5, 0.0 ], - "limit": 500000 + "knowledge": "2026-02-01", + "limit": 500000, + "max_output": 32768, + "released": "2026-08-12" }, "grok-code-fast-1": { "cost": [ @@ -2345,6 +2977,8 @@ 0.0 ], "limit": 256000, + "max_output": 16384, + "released": "2025-09-02", "status": "deprecated" }, "kimi-k2-turbo-preview": { @@ -2355,6 +2989,8 @@ 0.0 ], "limit": 256000, + "max_output": 8192, + "released": "2025-07-08", "status": "deprecated" }, "kimi-k2.5": { @@ -2364,7 +3000,11 @@ 0.0, 0.0 ], + "knowledge": "2025-01", "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-01-27", "status": "deprecated" }, "llama-3.3-70b-versatile": { @@ -2374,7 +3014,11 @@ 0.0, 0.0 ], + "knowledge": "2023-12", "limit": 128000, + "max_output": 32768, + "open": true, + "released": "2024-12-06", "status": "deprecated" }, "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8": { @@ -2384,7 +3028,11 @@ 0.0, 0.0 ], + "knowledge": "2024-08", "limit": 1048576, + "max_output": 8192, + "open": true, + "released": "2025-04-05", "status": "deprecated" }, "meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo": { @@ -2395,6 +3043,9 @@ 0.0 ], "limit": 128000, + "max_output": 4096, + "open": true, + "released": "2024-07-23", "status": "deprecated" }, "meta-llama/Meta-Llama-3.1-8B-Instruct": { @@ -2404,7 +3055,11 @@ 0.0, 0.0 ], + "knowledge": "2023-12", "limit": 128000, + "max_output": 4096, + "open": true, + "released": "2024-07-23", "status": "deprecated" }, "meta-llama/Meta-Llama-3.3-70B-Instruct": { @@ -2414,7 +3069,11 @@ 0.0, 0.0 ], + "knowledge": "2023-12", "limit": 131072, + "max_output": 8192, + "open": true, + "released": "2024-12-06", "status": "deprecated" }, "mimo-v2-pro": { @@ -2424,7 +3083,10 @@ 0.2, 0.0 ], - "limit": 1048576 + "knowledge": "2024-12", + "limit": 1048576, + "max_output": 131072, + "released": "2026-03-18" }, "moonshotai/Kimi-K2.6": { "cost": [ @@ -2433,7 +3095,11 @@ 0.16, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-20" }, "moonshotai/Kimi-K2.7-Code": { "cost": [ @@ -2442,7 +3108,11 @@ 0.19, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-06-12" }, "moonshotai/Kimi-K3": { "cost": [ @@ -2451,7 +3121,10 @@ 0.3, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-16" }, "muse-spark-1.1": { "cost": [ @@ -2460,7 +3133,9 @@ 0.15, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 32000, + "released": "2026-04-08" }, "muse-spark-1.2": { "cost": [ @@ -2469,7 +3144,9 @@ 0.15, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-08-05" }, "o3": { "cost": [ @@ -2478,7 +3155,10 @@ 0.5, 0.0 ], - "limit": 200000 + "knowledge": "2024-05", + "limit": 200000, + "max_output": 100000, + "released": "2025-04-16" }, "o3-mini": { "cost": [ @@ -2487,7 +3167,10 @@ 0.55, 0.0 ], - "limit": 200000 + "knowledge": "2024-05", + "limit": 200000, + "max_output": 100000, + "released": "2024-12-20" }, "o3-pro": { "cost": [ @@ -2496,7 +3179,10 @@ 0.0, 0.0 ], - "limit": 200000 + "knowledge": "2024-05", + "limit": 200000, + "max_output": 100000, + "released": "2025-06-10" }, "o4-mini": { "cost": [ @@ -2505,7 +3191,10 @@ 0.0, 0.0 ], - "limit": 200000 + "knowledge": "2024-05", + "limit": 200000, + "max_output": 100000, + "released": "2025-04-16" }, "openai/gpt-oss-120b": { "cost": [ @@ -2514,7 +3203,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-06", + "limit": 128000, + "max_output": 16384, + "open": true, + "released": "2025-08-05" }, "qwen-2.5-coder-32b": { "cost": [ @@ -2524,6 +3217,9 @@ 0.0 ], "limit": 128000, + "max_output": 8192, + "open": true, + "released": "2024-11-12", "status": "deprecated" }, "qwen3-max": { @@ -2533,7 +3229,10 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 131072, + "max_output": 16384, + "released": "2025-09-23", "status": "deprecated" }, "qwen3.7-max": { @@ -2543,7 +3242,9 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 64000, + "released": "2026-05-21" }, "qwen3.8-max": { "cost": [ @@ -2552,7 +3253,9 @@ 0.25, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-08-03" }, "route-llm": { "cost": [ @@ -2561,7 +3264,9 @@ 0.1, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 64000, + "released": "2024-01-01" }, "thinkingmachines/Inkling": { "cost": [ @@ -2570,7 +3275,10 @@ 0.748, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 131072, + "open": true, + "released": "2026-07-15" }, "zai-org/GLM-4.5": { "cost": [ @@ -2579,7 +3287,11 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 131072, + "max_output": 96000, + "open": true, + "released": "2025-07-28", "status": "deprecated" }, "zai-org/GLM-4.6": { @@ -2589,7 +3301,11 @@ 0.0, 0.0 ], - "limit": 202752 + "knowledge": "2025-04", + "limit": 202752, + "max_output": 131072, + "open": true, + "released": "2025-09-30" }, "zai-org/GLM-4.7": { "cost": [ @@ -2598,7 +3314,11 @@ 0.0, 0.0 ], - "limit": 204800 + "knowledge": "2025-04", + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-12-22" }, "zai-org/GLM-5": { "cost": [ @@ -2607,7 +3327,10 @@ 0.0, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-02-12" }, "zai-org/GLM-5.1": { "cost": [ @@ -2616,7 +3339,10 @@ 0.26, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-04-07" }, "zai-org/GLM-5.2": { "cost": [ @@ -2625,7 +3351,10 @@ 0.26, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-06-13" } }, "name": "Abacus" @@ -2639,7 +3368,10 @@ 0.3, 0.0 ], - "limit": 150000 + "limit": 150000, + "max_output": 8192, + "open": true, + "released": "2026-01-06" }, "abliterated-model-large": { "cost": [ @@ -2648,7 +3380,9 @@ 0.5, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 999990, + "released": "2026-07-25" }, "abliterated-model-large-v2": { "cost": [ @@ -2657,7 +3391,9 @@ 0.5, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 999990, + "released": "2026-08-29" } }, "name": "abliteration.ai" @@ -2671,7 +3407,11 @@ 0.0033, 0.0 ], + "knowledge": "2025-05", "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-09-10", "status": "deprecated" }, "deepseek-v4-pro": { @@ -2681,7 +3421,10 @@ 0.0242, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-08-13" }, "deepseek-v4.1-flash": { "cost": [ @@ -2690,7 +3433,11 @@ 0.0033, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-09-10" }, "glm-5.2": { "cost": [ @@ -2699,7 +3446,10 @@ 0.154, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "glm-5.2-fast": { "cost": [ @@ -2708,7 +3458,10 @@ 0.231, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "glm-5.3-flash": { "cost": [ @@ -2717,7 +3470,10 @@ 0.0319, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-26" }, "mimo-v2.6-flash": { "cost": [ @@ -2726,7 +3482,10 @@ 0.0034, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-09-22" }, "mimo-v2.6-pro": { "cost": [ @@ -2735,7 +3494,10 @@ 0.0042, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-09-22" }, "mimo-v2.6-pro-ultraspeed": { "cost": [ @@ -2744,7 +3506,10 @@ 0.0423, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-09-21" }, "qwen3.8-max": { "cost": [ @@ -2753,7 +3518,9 @@ 0.275, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 32768, + "released": "2026-08-03" } }, "name": "above.dev" @@ -2768,6 +3535,8 @@ 0.0 ], "limit": 512000, + "max_output": 65536, + "released": "2026-05-25", "status": "deprecated" }, "agnes-2.5-flash": { @@ -2777,7 +3546,9 @@ 0.0, 0.0 ], - "limit": 512000 + "limit": 512000, + "max_output": 65536, + "released": "2026-07" }, "agnes-2.5-pro-alpha": { "cost": [ @@ -2786,7 +3557,10 @@ 0.0038, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 65536, + "open": true, + "released": "2026-07-24" }, "agnes-3.0-flash": { "cost": [ @@ -2795,7 +3569,9 @@ 0.0, 0.0 ], - "limit": 512000 + "limit": 512000, + "max_output": 65536, + "released": "2026-09" } }, "name": "Agnes AI" @@ -2809,7 +3585,10 @@ 0.25, 0.0 ], - "limit": 1050000 + "knowledge": "2025-08-31", + "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05" }, "gpt-5.5": { "cost": [ @@ -2818,7 +3597,10 @@ 0.5, 0.0 ], - "limit": 1050000 + "knowledge": "2025-12-01", + "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23" }, "gpt-5.6-luna": { "cost": [ @@ -2827,7 +3609,10 @@ 0.1, 1.25 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "gpt-5.6-sol": { "cost": [ @@ -2836,7 +3621,10 @@ 0.5, 6.25 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "gpt-5.6-terra": { "cost": [ @@ -2845,7 +3633,10 @@ 0.25, 3.125 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" } }, "name": "AI-ROUTER" @@ -2859,7 +3650,11 @@ 0.0, 0.0 ], - "limit": 256000 + "knowledge": "2024-08-22", + "limit": 256000, + "max_output": 4096, + "open": true, + "released": "2025-07-03" }, "jamba-mini": { "cost": [ @@ -2868,22 +3663,17 @@ 0.0, 0.0 ], - "limit": 256000 + "knowledge": "2024-08-22", + "limit": 256000, + "max_output": 4096, + "open": true, + "released": "2026-01-08" } }, "name": "AI21 Labs" }, "aiand": { "models": { - "deepseek-ai/deepseek-v4-flash": { - "cost": [ - 0.15, - 0.25, - 0.08, - 0.0 - ], - "limit": 1048576 - }, "deepseek-ai/deepseek-v4-pro": { "cost": [ 1.0, @@ -2891,7 +3681,11 @@ 0.25, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "deepseek-ai/deepseek-v4.1-flash": { "cost": [ @@ -2900,7 +3694,11 @@ 0.02, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-09-10" }, "google/gemma-4-31b-it": { "cost": [ @@ -2909,16 +3707,11 @@ 0.05, 0.0 ], - "limit": 262144 - }, - "moonshotai/kimi-k2.7-code": { - "cost": [ - 0.75, - 3.5, - 0.2, - 0.0 - ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-04-02" }, "moonshotai/kimi-k3": { "cost": [ @@ -2927,7 +3720,10 @@ 0.5, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-16" }, "motif-technologies/motif-3": { "cost": [ @@ -2936,7 +3732,10 @@ 0.2, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-08-07" }, "openai/gpt-oss-120b": { "cost": [ @@ -2945,7 +3744,11 @@ 0.08, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "qwen/qwen3.6-27b": { "cost": [ @@ -2954,7 +3757,10 @@ 0.2, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-04-22" }, "qwen/qwen3.8-27b": { "cost": [ @@ -2963,16 +3769,10 @@ 0.2, 0.0 ], - "limit": 262144 - }, - "zai-org/glm-5.2": { - "cost": [ - 1.0, - 4.0, - 0.3, - 0.0 - ], - "limit": 1048576 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-08-14" }, "zai-org/glm-5.3": { "cost": [ @@ -2981,7 +3781,10 @@ 0.3, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "zai-org/glm-5.3-flash": { "cost": [ @@ -2990,7 +3793,10 @@ 0.03, 0.0 ], - "limit": 1048550 + "limit": 1048550, + "max_output": 131072, + "open": true, + "released": "2026-08-26" } }, "name": "ai&" @@ -3004,7 +3810,11 @@ 0.028, 0.0 ], + "knowledge": "2025-05", "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24", "status": "deprecated" }, "alicloud-deepseek-v4-pro": { @@ -3014,7 +3824,11 @@ 0.13, 0.0 ], + "knowledge": "2025-05", "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24", "status": "deprecated" }, "alicloud-glm-5.1": { @@ -3025,6 +3839,9 @@ 1.05625 ], "limit": 200000, + "max_output": 128000, + "open": true, + "released": "2026-04-07", "status": "deprecated" }, "claude-fable-5": { @@ -3034,7 +3851,10 @@ 1.1, 13.75 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-09" }, "claude-fable-5-1": { "cost": [ @@ -3043,7 +3863,10 @@ 0.275, 13.75 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-01" }, "claude-haiku-4-5": { "cost": [ @@ -3052,7 +3875,10 @@ 0.11, 1.375 ], - "limit": 200000 + "knowledge": "2025-02-28", + "limit": 200000, + "max_output": 64000, + "released": "2025-10-15" }, "claude-haiku-5-5": { "cost": [ @@ -3061,7 +3887,10 @@ 0.01, 0.125 ], + "knowledge": "2026-06", "limit": 1000000, + "max_output": 128000, + "released": "2026-10-07", "tiers": [ { "cost": [ @@ -3084,7 +3913,10 @@ 0.5, 6.25 ], - "limit": 200000 + "knowledge": "2025-05", + "limit": 200000, + "max_output": 64000, + "released": "2025-11-24" }, "claude-opus-4-5-think": { "cost": [ @@ -3093,7 +3925,10 @@ 0.5, 6.25 ], - "limit": 200000 + "knowledge": "2025-05", + "limit": 200000, + "max_output": 64000, + "released": "2025-11-24" }, "claude-opus-4-6": { "cost": [ @@ -3102,7 +3937,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2025-05-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-05" }, "claude-opus-4-6-think": { "cost": [ @@ -3111,7 +3949,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2025-05-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-05" }, "claude-opus-4-7": { "cost": [ @@ -3120,7 +3961,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-16" }, "claude-opus-4-7-think": { "cost": [ @@ -3129,7 +3973,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-16" }, "claude-opus-4-8": { "cost": [ @@ -3138,7 +3985,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-28" }, "claude-opus-4-8-think": { "cost": [ @@ -3147,7 +3997,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-28" }, "claude-opus-5": { "cost": [ @@ -3156,7 +4009,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-05", + "limit": 1000000, + "max_output": 128000, + "released": "2026-07-24" }, "claude-opus-5-5": { "cost": [ @@ -3165,7 +4021,10 @@ 0.2, 5.0 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-22" }, "claude-sonnet-4-5": { "cost": [ @@ -3174,7 +4033,10 @@ 0.33, 4.125 ], + "knowledge": "2025-07-31", "limit": 200000, + "max_output": 64000, + "released": "2025-09-29", "tiers": [ { "cost": [ @@ -3197,7 +4059,10 @@ 0.33, 4.125 ], + "knowledge": "2025-07-31", "limit": 200000, + "max_output": 64000, + "released": "2025-09-29", "tiers": [ { "cost": [ @@ -3220,7 +4085,10 @@ 0.3, 3.75 ], - "limit": 1000000 + "knowledge": "2025-08-31", + "limit": 1000000, + "max_output": 64000, + "released": "2026-02-17" }, "claude-sonnet-4-6-think": { "cost": [ @@ -3229,7 +4097,10 @@ 0.3, 3.75 ], - "limit": 1000000 + "knowledge": "2025-08-31", + "limit": 1000000, + "max_output": 64000, + "released": "2026-02-17" }, "claude-sonnet-5": { "cost": [ @@ -3238,7 +4109,10 @@ 0.2, 2.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-30" }, "claude-sonnet-5-5": { "cost": [ @@ -3247,7 +4121,10 @@ 0.1, 2.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-28" }, "coding-glm-5.1": { "cost": [ @@ -3256,7 +4133,10 @@ 0.013, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 131072, + "open": true, + "released": "2026-04-07" }, "coding-glm-5.1-free": { "cost": [ @@ -3265,7 +4145,10 @@ 0.0, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 131072, + "open": true, + "released": "2026-04-07" }, "coding-glm-5.2-free": { "cost": [ @@ -3274,7 +4157,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "coding-glm-5.3-flash-free": { "cost": [ @@ -3283,7 +4169,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-26" }, "coding-glm-5.3-free": { "cost": [ @@ -3292,7 +4181,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "coding-minimax-m2.7": { "cost": [ @@ -3301,7 +4193,10 @@ 0.0, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 128100, + "open": true, + "released": "2026-03-18" }, "coding-minimax-m2.7-free": { "cost": [ @@ -3310,7 +4205,10 @@ 0.0, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 128100, + "open": true, + "released": "2026-03-18" }, "coding-minimax-m2.7-highspeed": { "cost": [ @@ -3319,7 +4217,10 @@ 0.0, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 128100, + "open": true, + "released": "2026-03-18" }, "coding-xiaomi-mimo-v2.5": { "cost": [ @@ -3328,7 +4229,11 @@ 0.0016, 0.0 ], - "limit": 1048576 + "knowledge": "2024-12", + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-04-22" }, "coding-xiaomi-mimo-v2.5-pro": { "cost": [ @@ -3337,7 +4242,11 @@ 0.0016, 0.0 ], - "limit": 1048576 + "knowledge": "2024-12", + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-04-22" }, "deep-deepseek-v4-flash": { "cost": [ @@ -3346,7 +4255,11 @@ 0.0308, 0.0 ], + "knowledge": "2025-05", "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24", "status": "deprecated" }, "deep-deepseek-v4-pro": { @@ -3356,7 +4269,11 @@ 0.004302, 0.0 ], + "knowledge": "2025-05", "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24", "status": "deprecated" }, "deepseek-v4-flash-0731": { @@ -3366,7 +4283,11 @@ 0.0284, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-07-31" }, "deepseek-v4-flash-0731-fast": { "cost": [ @@ -3375,7 +4296,11 @@ 0.07, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-07-31" }, "deepseek-v4-flash-vision-exp": { "cost": [ @@ -3385,6 +4310,9 @@ 0.0 ], "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-08-21", "status": "deprecated" }, "deepseek-v4-pro-0813": { @@ -3394,7 +4322,10 @@ 0.023057694, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-08-13" }, "deepseek-v4.1-flash": { "cost": [ @@ -3403,7 +4334,11 @@ 0.0031, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-09-10" }, "doubao-seed-2-0-code-preview": { "cost": [ @@ -3413,6 +4348,8 @@ 0.0 ], "limit": 256000, + "max_output": 128000, + "released": "2026-02-14", "tiers": [ { "cost": [ @@ -3448,6 +4385,8 @@ 0.0 ], "limit": 256000, + "max_output": 128000, + "released": "2026-04-28", "tiers": [ { "cost": [ @@ -3483,6 +4422,8 @@ 0.0 ], "limit": 256000, + "max_output": 128000, + "released": "2026-04-28", "tiers": [ { "cost": [ @@ -3518,6 +4459,8 @@ 0.0 ], "limit": 256000, + "max_output": 128000, + "released": "2026-02-14", "tiers": [ { "cost": [ @@ -3552,7 +4495,10 @@ 0.03, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2025-06-17" }, "gemini-2.5-flash-image": { "cost": [ @@ -3561,7 +4507,11 @@ 0.03, 0.0 ], - "limit": 32768 + "knowledge": "2024-06", + "limit": 32768, + "max_output": 32768, + "released": "2025-08-26", + "type": "image" }, "gemini-2.5-flash-lite": { "cost": [ @@ -3570,7 +4520,10 @@ 0.01, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2025-06-17" }, "gemini-2.5-pro": { "cost": [ @@ -3579,7 +4532,10 @@ 0.125, 0.0 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2025-06-17", "tiers": [ { "cost": [ @@ -3602,7 +4558,10 @@ 0.05, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2025-12-17" }, "gemini-3-pro-image": { "cost": [ @@ -3611,7 +4570,11 @@ 0.0, 0.0 ], - "limit": 65536 + "knowledge": "2025-01", + "limit": 65536, + "max_output": 32768, + "released": "2026-05-28", + "type": "image" }, "gemini-3.1-flash-image": { "cost": [ @@ -3620,7 +4583,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2025-01", + "limit": 131072, + "max_output": 32768, + "released": "2026-05-28", + "type": "image" }, "gemini-3.1-flash-lite": { "cost": [ @@ -3629,7 +4596,10 @@ 0.025, 1.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-05-07" }, "gemini-3.1-flash-lite-image": { "cost": [ @@ -3638,7 +4608,11 @@ 0.025, 0.0 ], - "limit": 65536 + "knowledge": "2025-01", + "limit": 65536, + "max_output": 4096, + "released": "2026-06-30", + "type": "image" }, "gemini-3.1-pro-preview": { "cost": [ @@ -3647,7 +4621,10 @@ 0.2, 0.0 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2026-02-19", "tiers": [ { "cost": [ @@ -3670,7 +4647,10 @@ 0.2, 0.0 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2026-02-19", "tiers": [ { "cost": [ @@ -3693,7 +4673,10 @@ 0.075, 0.0 ], + "knowledge": "2025-01", "limit": 1000000, + "max_output": 64000, + "released": "2026-05-19", "status": "deprecated" }, "gemini-3.5-flash-lite": { @@ -3703,7 +4686,10 @@ 0.03, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-07-21" }, "gemini-3.6-flash": { "cost": [ @@ -3712,7 +4698,10 @@ 0.075, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-07-21" }, "gemini-3.7-flash": { "cost": [ @@ -3721,7 +4710,10 @@ 0.075, 0.0 ], + "knowledge": "2026-03", "limit": 1048576, + "max_output": 65536, + "released": "2026-08-13", "status": "deprecated" }, "gemini-3.8-flash": { @@ -3731,7 +4723,9 @@ 0.075, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65536, + "released": "2026-09-02" }, "gemini-4-argon": { "cost": [ @@ -3740,7 +4734,10 @@ 0.1, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-10-13" }, "glm-4.5v": { "cost": [ @@ -3749,7 +4746,11 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 64000, + "max_output": 16384, + "open": true, + "released": "2025-08-11", "tiers": [ { "cost": [ @@ -3772,7 +4773,11 @@ 0.0547948, 0.0 ], + "knowledge": "2025-04", "limit": 200000, + "max_output": 131072, + "open": true, + "released": "2025-09-30", "tiers": [ { "cost": [ @@ -3795,7 +4800,11 @@ 0.0274, 0.0 ], + "knowledge": "2025-04", "limit": 128000, + "max_output": 32768, + "open": true, + "released": "2025-12-08", "tiers": [ { "cost": [ @@ -3818,7 +4827,11 @@ 0.0547948, 0.0 ], + "knowledge": "2025-04", "limit": 200000, + "max_output": 131072, + "open": true, + "released": "2025-12-22", "tiers": [ { "cost": [ @@ -3841,7 +4854,11 @@ 0.0, 0.0 ], - "limit": 200000 + "knowledge": "2025-04", + "limit": 200000, + "max_output": 131072, + "open": true, + "released": "2026-01-19" }, "glm-5.2": { "cost": [ @@ -3850,7 +4867,10 @@ 0.2817, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "glm-5.3": { "cost": [ @@ -3859,7 +4879,10 @@ 0.2817, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "glm-5.3-flash": { "cost": [ @@ -3868,7 +4891,10 @@ 0.02817, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-26" }, "glm-5v-turbo": { "cost": [ @@ -3878,6 +4904,8 @@ 0.0 ], "limit": 200000, + "max_output": 131072, + "released": "2026-04-01", "tiers": [ { "cost": [ @@ -3900,7 +4928,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "gpt-5.1": { "cost": [ @@ -3909,7 +4940,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "gpt-5.1-codex": { "cost": [ @@ -3918,7 +4952,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "gpt-5.1-codex-mini": { "cost": [ @@ -3927,7 +4964,10 @@ 0.025, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "gpt-5.2": { "cost": [ @@ -3936,7 +4976,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "gpt-5.2-codex": { "cost": [ @@ -3945,7 +4988,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "gpt-5.3-codex": { "cost": [ @@ -3954,7 +5000,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-02-05" }, "gpt-5.4": { "cost": [ @@ -3963,7 +5012,10 @@ 0.25, 0.0 ], + "knowledge": "2025-08-31", "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05", "tiers": [ { "cost": [ @@ -3986,7 +5038,10 @@ 0.5, 0.0 ], - "limit": 1050000 + "knowledge": "2025-08-31", + "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05" }, "gpt-5.4-mini": { "cost": [ @@ -3995,7 +5050,10 @@ 0.075, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "gpt-5.4-mini-fast": { "cost": [ @@ -4004,7 +5062,10 @@ 0.15, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "gpt-5.4-nano": { "cost": [ @@ -4013,7 +5074,10 @@ 0.02, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "gpt-5.5": { "cost": [ @@ -4022,7 +5086,10 @@ 0.5, 0.0 ], + "knowledge": "2025-12-01", "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23", "tiers": [ { "cost": [ @@ -4045,7 +5112,10 @@ 1.25, 0.0 ], - "limit": 1050000 + "knowledge": "2025-12-01", + "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23" }, "gpt-5.5-pro": { "cost": [ @@ -4054,7 +5124,10 @@ 0.0, 0.0 ], + "knowledge": "2025-12-01", "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23", "tiers": [ { "cost": [ @@ -4077,7 +5150,10 @@ 0.02, 0.25 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -4100,7 +5176,10 @@ 0.4, 5.0 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -4123,7 +5202,10 @@ 0.2, 2.5 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -4146,7 +5228,10 @@ 1.0, 12.5 ], + "knowledge": "2026-04-30", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-04", "tiers": [ { "cost": [ @@ -4169,7 +5254,10 @@ 0.01, 0.125 ], + "knowledge": "2026-05-18", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -4192,7 +5280,10 @@ 0.2, 2.5 ], + "knowledge": "2026-04-20", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -4215,7 +5306,10 @@ 0.1, 2.5 ], + "knowledge": "2026-04-30", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-29", "tiers": [ { "cost": [ @@ -4237,7 +5331,9 @@ 32.0, 0.0, 0.0 - ] + ], + "released": "2025-11-25", + "type": "image" }, "gpt-image-2": { "cost": [ @@ -4245,7 +5341,9 @@ 30.0, 1.25, 0.0 - ] + ], + "released": "2026-04-21", + "type": "image" }, "gpt-image-2.5-flare": { "cost": [ @@ -4253,7 +5351,9 @@ 30.0, 1.25, 0.0 - ] + ], + "released": "2026-09-08", + "type": "image" }, "gpt-image-2.5-sunburst": { "cost": [ @@ -4261,7 +5361,9 @@ 30.0, 1.25, 0.0 - ] + ], + "released": "2026-09-08", + "type": "image" }, "grok-4.3": { "cost": [ @@ -4271,6 +5373,8 @@ 0.0 ], "limit": 1000000, + "max_output": 30000, + "released": "2026-04-17", "tiers": [ { "cost": [ @@ -4294,6 +5398,8 @@ 0.0 ], "limit": 500000, + "max_output": 1000000, + "released": "2026-07-08", "tiers": [ { "cost": [ @@ -4316,7 +5422,10 @@ 0.5, 0.0 ], + "knowledge": "2026-02-01", "limit": 500000, + "max_output": 500000, + "released": "2026-08-12", "tiers": [ { "cost": [ @@ -4339,7 +5448,10 @@ 0.5, 0.0 ], + "knowledge": "2026-05", "limit": 500000, + "max_output": 500000, + "released": "2026-09-21", "tiers": [ { "cost": [ @@ -4362,7 +5474,9 @@ 0.2, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 256000, + "released": "2026-04-16" }, "hy3": { "cost": [ @@ -4371,7 +5485,10 @@ 0.03905, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 128000, + "open": true, + "released": "2026-07-06" }, "hy3-preview": { "cost": [ @@ -4381,6 +5498,9 @@ 0.0 ], "limit": 256000, + "max_output": 128000, + "open": true, + "released": "2026-04-20", "status": "deprecated" }, "hy4-preview": { @@ -4390,7 +5510,10 @@ 0.04225, 0.0 ], - "limit": 1024000 + "limit": 1024000, + "max_output": 64000, + "open": true, + "released": "2026-08-28" }, "kimi-k2.5": { "cost": [ @@ -4399,7 +5522,11 @@ 0.1, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-01-27" }, "kimi-k2.6": { "cost": [ @@ -4408,7 +5535,11 @@ 0.16, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-04-20" }, "kimi-k2.7-code": { "cost": [ @@ -4417,7 +5548,11 @@ 0.160835, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-06-12" }, "kimi-k2.7-code-highspeed": { "cost": [ @@ -4426,7 +5561,11 @@ 0.32167, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-06-12" }, "kimi-k3": { "cost": [ @@ -4435,7 +5574,10 @@ 0.3, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-16" }, "ling-3.0-flash-free": { "cost": [ @@ -4444,7 +5586,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-07-23" }, "longcat-2.0": { "cost": [ @@ -4453,7 +5598,10 @@ 0.015492, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-30" }, "mimo-v2.5": { "cost": [ @@ -4462,7 +5610,11 @@ 0.0031, 0.0 ], + "knowledge": "2024-12", "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-04-22", "status": "deprecated" }, "mimo-v2.5-pro": { @@ -4472,7 +5624,11 @@ 0.00384, 0.0 ], + "knowledge": "2024-12", "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-04-22", "status": "deprecated" }, "mimo-v2.6-flash": { @@ -4482,7 +5638,10 @@ 0.0031, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-09-22" }, "mimo-v2.6-pro": { "cost": [ @@ -4491,7 +5650,10 @@ 0.00384, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-09-22" }, "mimo-v2.6-pro-ultraspeed": { "cost": [ @@ -4500,7 +5662,10 @@ 0.0384, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-09-21" }, "minimax-m2.7": { "cost": [ @@ -4509,7 +5674,10 @@ 0.06, 0.375 ], - "limit": 204800 + "limit": 204800, + "max_output": 128000, + "open": true, + "released": "2026-03-18" }, "minimax-m3": { "cost": [ @@ -4518,7 +5686,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 512000, + "open": true, + "released": "2026-06-01" }, "muse-spark-1.1": { "cost": [ @@ -4527,7 +5698,9 @@ 0.0, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-04-08" }, "muse-spark-1.2": { "cost": [ @@ -4536,7 +5709,9 @@ 0.0, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-08-05" }, "muse-spark-1.3": { "cost": [ @@ -4545,7 +5720,9 @@ 0.165, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-09-02" }, "nemotron-3-nano-omni-30b-a3b-reasoning-free": { "cost": [ @@ -4554,7 +5731,10 @@ 0.0, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 65536, + "open": true, + "released": "2026-04-28" }, "nemotron-3-super-120b-a12b-free": { "cost": [ @@ -4563,7 +5743,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-06", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-03-11" }, "nemotron-3-ultra-550b-a55b-free": { "cost": [ @@ -4572,7 +5756,11 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-09", + "limit": 1000000, + "max_output": 128000, + "open": true, + "released": "2026-06-04" }, "nemotron-3.5-content-safety-free": { "cost": [ @@ -4581,7 +5769,10 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 8192, + "open": true, + "released": "2026-06-02" }, "nemotron-3.5-lightning-free": { "cost": [ @@ -4590,7 +5781,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-09", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-08-11" }, "o3": { "cost": [ @@ -4599,7 +5794,10 @@ 0.5, 0.0 ], - "limit": 200000 + "knowledge": "2024-05", + "limit": 200000, + "max_output": 100000, + "released": "2025-04-16" }, "o4-mini": { "cost": [ @@ -4608,7 +5806,10 @@ 0.275, 0.0 ], - "limit": 200000 + "knowledge": "2024-05", + "limit": 200000, + "max_output": 100000, + "released": "2025-04-16" }, "qwen3-max": { "cost": [ @@ -4617,7 +5818,10 @@ 0.09016, 0.5635 ], + "knowledge": "2025-04", "limit": 262144, + "max_output": 65536, + "released": "2025-09-23", "status": "deprecated", "tiers": [ { @@ -4653,7 +5857,10 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 262144, + "max_output": 32768, + "released": "2025-09-23", "tiers": [ { "cost": [ @@ -4689,6 +5896,9 @@ 0.0 ], "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-23", "tiers": [ { "cost": [ @@ -4712,6 +5922,9 @@ 0.0 ], "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-23", "tiers": [ { "cost": [ @@ -4735,6 +5948,9 @@ 0.0 ], "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-23", "tiers": [ { "cost": [ @@ -4758,6 +5974,9 @@ 0.0 ], "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-15", "tiers": [ { "cost": [ @@ -4781,6 +6000,8 @@ 0.03525 ], "limit": 1000000, + "max_output": 65536, + "released": "2026-02-23", "tiers": [ { "cost": [ @@ -4815,7 +6036,10 @@ 0.01096, 0.137 ], + "knowledge": "2025-04", "limit": 1000000, + "max_output": 65536, + "released": "2026-02-16", "tiers": [ { "cost": [ @@ -4850,7 +6074,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-04-17" }, "qwen3.6-flash": { "cost": [ @@ -4859,7 +6086,10 @@ 0.0169, 0.21125 ], + "knowledge": "2025-04", "limit": 991000, + "max_output": 65536, + "released": "2026-04-27", "tiers": [ { "cost": [ @@ -4882,7 +6112,10 @@ 0.1268, 1.585 ], + "knowledge": "2025-04", "limit": 240000, + "max_output": 64000, + "released": "2026-04-20", "status": "deprecated", "tiers": [ { @@ -4906,7 +6139,10 @@ 0.0282, 0.3525 ], + "knowledge": "2025-04", "limit": 991000, + "max_output": 65536, + "released": "2026-04-02", "tiers": [ { "cost": [ @@ -4930,6 +6166,8 @@ 0.03525 ], "limit": 991000, + "max_output": 131072, + "released": "2026-07-15", "tiers": [ { "cost": [ @@ -4964,7 +6202,9 @@ 0.169, 2.1125 ], - "limit": 991000 + "limit": 991000, + "max_output": 131072, + "released": "2026-05-21" }, "qwen3.7-plus": { "cost": [ @@ -4973,7 +6213,10 @@ 0.0564, 0.3525 ], + "knowledge": "2025-04", "limit": 991000, + "max_output": 64000, + "released": "2026-06-02", "tiers": [ { "cost": [ @@ -4996,7 +6239,10 @@ 0.5, 0.0 ], - "limit": 262000 + "limit": 262000, + "max_output": 131072, + "open": true, + "released": "2026-08-12" }, "qwen3.8-flash": { "cost": [ @@ -5005,7 +6251,9 @@ 0.014075, 0.1759375 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-08-26" }, "qwen3.8-flash-free": { "cost": [ @@ -5014,7 +6262,9 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-08-26" }, "qwen3.8-max": { "cost": [ @@ -5023,7 +6273,9 @@ 0.169, 2.1125 ], - "limit": 991000 + "limit": 991000, + "max_output": 131072, + "released": "2026-08-03" }, "qwen3.8-max-free": { "cost": [ @@ -5032,7 +6284,9 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-08-03" }, "qwen3.8-max-preview": { "cost": [ @@ -5042,6 +6296,8 @@ 0.4225 ], "limit": 1000000, + "max_output": 131072, + "released": "2026-07-19", "status": "deprecated" }, "qwen3.8-omni-flash": { @@ -5051,7 +6307,9 @@ 0.014075, 0.1759375 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-09-17" }, "step-3.7-flash": { "cost": [ @@ -5060,7 +6318,11 @@ 0.044, 0.0 ], - "limit": 256000 + "knowledge": "2026-03-01", + "limit": 256000, + "max_output": 256000, + "open": true, + "released": "2026-05-29" }, "step-5-preview": { "cost": [ @@ -5069,7 +6331,10 @@ 0.054, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 64000, + "open": true, + "released": "2026-09-16" }, "xiaomi-mimo-v2.5": { "cost": [ @@ -5078,7 +6343,11 @@ 0.088, 0.0 ], + "knowledge": "2024-12", "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-04-22", "status": "deprecated", "tiers": [ { @@ -5102,7 +6371,11 @@ 0.0, 0.0 ], + "knowledge": "2024-12", "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-04-22", "status": "deprecated" }, "xiaomi-mimo-v2.5-pro": { @@ -5112,7 +6385,11 @@ 0.22, 0.0 ], + "knowledge": "2024-12", "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-04-22", "status": "deprecated", "tiers": [ { @@ -5136,7 +6413,11 @@ 0.0, 0.0 ], + "knowledge": "2024-12", "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-04-22", "status": "deprecated" }, "zai-glm-5.1": { @@ -5147,6 +6428,9 @@ 0.0 ], "limit": 200000, + "max_output": 128000, + "open": true, + "released": "2026-04-07", "status": "deprecated" } }, @@ -5161,7 +6445,11 @@ 0.0, 0.0 ], - "limit": 32768 + "knowledge": "2023-12-31", + "limit": 32768, + "max_output": 32768, + "open": true, + "released": "2025-02-04" }, "alibaba/qwen-max": { "cost": [ @@ -5170,7 +6458,10 @@ 0.32, 0.0 ], - "limit": 32000 + "knowledge": "2024-04", + "limit": 32000, + "max_output": 8192, + "released": "2024-04-03" }, "alibaba/qwen-plus": { "cost": [ @@ -5179,7 +6470,10 @@ 0.08, 0.0 ], - "limit": 131000 + "knowledge": "2024-04", + "limit": 131000, + "max_output": 16384, + "released": "2024-01-25" }, "alibaba/qwen3-coder-480b-a35b-instruct": { "cost": [ @@ -5188,7 +6482,11 @@ 1.058, 0.0 ], - "limit": 262000 + "knowledge": "2025-04", + "limit": 262000, + "max_output": 65536, + "open": true, + "released": "2025-07-22" }, "alibaba/qwen3-next-80b-a3b-instruct": { "cost": [ @@ -5197,7 +6495,11 @@ 0.0, 0.0 ], - "limit": 129024 + "knowledge": "2025-04", + "limit": 129024, + "max_output": 16384, + "open": true, + "released": "2025-09" }, "alibaba/qwen3.8-2.4t-a95b": { "cost": [ @@ -5206,7 +6508,10 @@ 0.529, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 52429, + "open": true, + "released": "2026-08-12" }, "alibaba/qwen3.8-27b": { "cost": [ @@ -5215,7 +6520,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "alibaba/qwen3.8-flash": { "cost": [ @@ -5224,7 +6532,9 @@ 0.016, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-08-26" }, "alibaba/qwen3.8-max": { "cost": [ @@ -5233,7 +6543,9 @@ 0.25, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-08-03" }, "alibaba/qwen3.8-max-prime": { "cost": [ @@ -5242,7 +6554,9 @@ 0.529, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-09-23" }, "amazon/nova-lite-v1": { "cost": [ @@ -5251,7 +6565,10 @@ 0.0, 0.0 ], - "limit": 300000 + "knowledge": "2024-10-31", + "limit": 300000, + "max_output": 5120, + "released": "2024-12-05" }, "amazon/nova-micro-v1": { "cost": [ @@ -5260,7 +6577,10 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-10-31", + "limit": 128000, + "max_output": 5120, + "released": "2024-12-05" }, "amazon/nova-pro-v1": { "cost": [ @@ -5269,7 +6589,10 @@ 0.0, 0.0 ], - "limit": 300000 + "knowledge": "2024-10-31", + "limit": 300000, + "max_output": 5120, + "released": "2024-12-05" }, "anthracite-org/magnum-v4-72b": { "cost": [ @@ -5278,7 +6601,11 @@ 0.0, 0.0 ], - "limit": 32000 + "knowledge": "2024-06-30", + "limit": 32000, + "max_output": 16384, + "open": true, + "released": "2024-10-22" }, "anthropic/claude-fable-5": { "cost": [ @@ -5287,7 +6614,10 @@ 1.0, 12.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-09" }, "anthropic/claude-fable-5.1": { "cost": [ @@ -5296,7 +6626,10 @@ 0.25, 12.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-01" }, "anthropic/claude-haiku-4.5": { "cost": [ @@ -5305,7 +6638,10 @@ 0.1058, 1.3225 ], - "limit": 200000 + "knowledge": "2025-02-28", + "limit": 200000, + "max_output": 64000, + "released": "2025-10-15" }, "anthropic/claude-haiku-5.5": { "cost": [ @@ -5314,7 +6650,10 @@ 0.01, 0.125 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-10-07" }, "anthropic/claude-opus-4.5": { "cost": [ @@ -5323,7 +6662,10 @@ 0.529, 6.6125 ], - "limit": 200000 + "knowledge": "2025-05", + "limit": 200000, + "max_output": 64000, + "released": "2025-11-24" }, "anthropic/claude-opus-4.7": { "cost": [ @@ -5332,7 +6674,10 @@ 0.529, 6.6125 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-16" }, "anthropic/claude-opus-4.8": { "cost": [ @@ -5341,7 +6686,10 @@ 0.529, 6.6125 ], - "limit": 1000000 + "knowledge": "2026-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-28" }, "anthropic/claude-opus-5": { "cost": [ @@ -5350,7 +6698,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-05", + "limit": 1000000, + "max_output": 128000, + "released": "2026-07-24" }, "anthropic/claude-opus-5.5": { "cost": [ @@ -5359,7 +6710,10 @@ 0.2, 5.0 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-22" }, "anthropic/claude-sonnet-4.5": { "cost": [ @@ -5368,7 +6722,10 @@ 0.3174, 3.9675 ], - "limit": 200000 + "knowledge": "2025-07-31", + "limit": 200000, + "max_output": 64000, + "released": "2025-09-29" }, "anthropic/claude-sonnet-4.6": { "cost": [ @@ -5377,7 +6734,10 @@ 0.3174, 3.9675 ], - "limit": 200000 + "knowledge": "2025-08-31", + "limit": 200000, + "max_output": 64000, + "released": "2026-02-17" }, "anthropic/claude-sonnet-5": { "cost": [ @@ -5386,7 +6746,10 @@ 0.2, 2.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-30" }, "anthropic/claude-sonnet-5.5": { "cost": [ @@ -5395,7 +6758,10 @@ 0.2, 2.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-28" }, "bytedance-seed/seed-1.6-flash": { "cost": [ @@ -5404,7 +6770,9 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "released": "2025-08-28" }, "bytedance-seed/seed-2.0-code": { "cost": [ @@ -5413,7 +6781,9 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 131072, + "released": "2026-02-14" }, "bytedance-seed/seed-2.0-lite": { "cost": [ @@ -5422,7 +6792,9 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 131072, + "released": "2026-02-14" }, "bytedance-seed/seed-2.0-mini": { "cost": [ @@ -5431,7 +6803,9 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 131072, + "released": "2026-02-14" }, "cognitivecomputations/dolphin-mistral-24b-venice-edition": { "cost": [ @@ -5440,7 +6814,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-04-30", + "limit": 128000, + "max_output": 8192, + "open": true, + "released": "2025-07-09" }, "cohere/command-a": { "cost": [ @@ -5449,7 +6827,11 @@ 0.0, 0.0 ], - "limit": 256000 + "knowledge": "2024-08-31", + "limit": 256000, + "max_output": 256000, + "open": true, + "released": "2025-03-13" }, "cohere/command-r-08-2024": { "cost": [ @@ -5458,7 +6840,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-06-01", + "limit": 128000, + "max_output": 4000, + "open": true, + "released": "2024-08-30" }, "cohere/command-r-plus-08-2024": { "cost": [ @@ -5467,7 +6853,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-06-01", + "limit": 128000, + "max_output": 4000, + "open": true, + "released": "2024-08-30" }, "cohere/command-r7b-12-2024": { "cost": [ @@ -5476,7 +6866,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-06-01", + "limit": 128000, + "max_output": 4000, + "open": true, + "released": "2024-12-13" }, "deepseek/deepseek-chat": { "cost": [ @@ -5485,7 +6879,11 @@ 0.0078, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "deepseek/deepseek-chat-v3-0324": { "cost": [ @@ -5494,7 +6892,11 @@ 0.14812, 0.0 ], - "limit": 128000 + "knowledge": "2024-07-31", + "limit": 128000, + "max_output": 124000, + "open": true, + "released": "2025-03-24" }, "deepseek/deepseek-v4-flash": { "cost": [ @@ -5503,7 +6905,11 @@ 0.006, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "deepseek/deepseek-v4-flash-vision-exp": { "cost": [ @@ -5512,7 +6918,10 @@ 0.014, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-08-21" }, "deepseek/deepseek-v4-pro": { "cost": [ @@ -5521,7 +6930,11 @@ 0.03, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "deepseek/deepseek-v4-pro-0813": { "cost": [ @@ -5530,7 +6943,10 @@ 0.15341, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-08-13" }, "deepseek/deepseek-v4.1-flash": { "cost": [ @@ -5539,7 +6955,11 @@ 0.006, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-09-10" }, "google/gemini-3-8-flash": { "cost": [ @@ -5548,7 +6968,9 @@ 0.075, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65536, + "released": "2026-09-02" }, "google/gemini-3.1-flash-lite-preview": { "cost": [ @@ -5557,7 +6979,10 @@ 0.02645, 0.088167 ], - "limit": 1000000 + "knowledge": "2025-01", + "limit": 1000000, + "max_output": 65536, + "released": "2026-03-03" }, "google/gemini-3.1-pro-preview": { "cost": [ @@ -5566,7 +6991,10 @@ 0.5, 0.0 ], - "limit": 1000000 + "knowledge": "2025-01", + "limit": 1000000, + "max_output": 65536, + "released": "2026-02-19" }, "google/gemini-3.1-pro-preview-customtools": { "cost": [ @@ -5575,7 +7003,10 @@ 0.2116, 0.39675 ], - "limit": 1048756 + "knowledge": "2025-01", + "limit": 1048756, + "max_output": 65536, + "released": "2026-02-19" }, "google/gemini-3.6-flash": { "cost": [ @@ -5584,7 +7015,10 @@ 0.15, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-07-21" }, "google/gemini-3.7-flash": { "cost": [ @@ -5593,7 +7027,10 @@ 0.075, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-08-13" }, "google/gemini-3.8-flash": { "cost": [ @@ -5602,7 +7039,9 @@ 0.075, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65536, + "released": "2026-09-02" }, "google/gemini-flash-latest": { "cost": [ @@ -5611,7 +7050,10 @@ 0.1587, 0.088167 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-08-13" }, "google/gemma-2-27b-it": { "cost": [ @@ -5620,7 +7062,11 @@ 0.0, 0.0 ], - "limit": 8192 + "knowledge": "2024-06-30", + "limit": 8192, + "max_output": 2048, + "open": true, + "released": "2024-07-13" }, "google/gemma-3-12b-it": { "cost": [ @@ -5629,7 +7075,11 @@ 0.04232, 0.0 ], - "limit": 131000 + "knowledge": "2024-08", + "limit": 131000, + "max_output": 96000, + "open": true, + "released": "2025-03-12" }, "google/gemma-3-27b-it": { "cost": [ @@ -5638,7 +7088,11 @@ 0.07935, 0.0 ], - "limit": 128000 + "knowledge": "2024-08", + "limit": 128000, + "max_output": 117964, + "open": true, + "released": "2025-03-12" }, "google/gemma-3-4b-it": { "cost": [ @@ -5647,7 +7101,11 @@ 0.04232, 0.0 ], - "limit": 131000 + "knowledge": "2024-08", + "limit": 131000, + "max_output": 32768, + "open": true, + "released": "2025-03-12" }, "google/gemma-4-26b-a4b-it": { "cost": [ @@ -5656,7 +7114,10 @@ 0.1587, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 128000, + "open": true, + "released": "2026-04-02" }, "google/gemma-4-31b-it": { "cost": [ @@ -5665,7 +7126,11 @@ 1.04742, 0.0 ], - "limit": 256000 + "knowledge": "2025-01", + "limit": 256000, + "max_output": 16384, + "open": true, + "released": "2026-04-02" }, "gryphe/mythomax-l2-13b": { "cost": [ @@ -5674,7 +7139,10 @@ 1.98375, 0.0 ], - "limit": 4096 + "limit": 4096, + "max_output": 4096, + "open": true, + "released": "2023-08-10" }, "ibm-granite/granite-4.0-h-micro": { "cost": [ @@ -5683,7 +7151,10 @@ 0.0, 0.0 ], - "limit": 131000 + "limit": 131000, + "max_output": 131000, + "open": true, + "released": "2025-10-02" }, "inception/mercury-2": { "cost": [ @@ -5692,7 +7163,9 @@ 0.02645, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 50000, + "released": "2026-02-24" }, "inception/mercury-2.5": { "cost": [ @@ -5701,7 +7174,9 @@ 0.02116, 0.0 ], - "limit": 260000 + "limit": 260000, + "max_output": 65536, + "released": "2026-09-08" }, "inference-net/schematron-v2-small": { "cost": [ @@ -5710,7 +7185,9 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 4096, + "released": "2026-04-16" }, "inference-net/schematron-v2-turbo": { "cost": [ @@ -5719,7 +7196,9 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 8192, + "released": "2026-04-16" }, "mancer/weaver": { "cost": [ @@ -5728,16 +7207,23 @@ 0.0, 0.0 ], - "limit": 8000 + "knowledge": "2023-06-30", + "limit": 8000, + "max_output": 2000, + "released": "2023-08-02" }, "meta-llama/Llama-3.3-70B-Instruct-Turbo": { "cost": [ - 1.04, - 1.04, + 0.76176, + 2.383674, 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2023-12", + "limit": 128000, + "max_output": 127000, + "open": true, + "released": "2024-12-06" }, "meta/muse-glimmer-30b": { "cost": [ @@ -5746,7 +7232,11 @@ 0.04232, 0.0 ], - "limit": 131072 + "knowledge": "2026-01-04", + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2026-08-10" }, "meta/muse-spark-1.1": { "cost": [ @@ -5755,7 +7245,9 @@ 0.1587, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-04-08" }, "meta/muse-spark-1.2": { "cost": [ @@ -5764,7 +7256,9 @@ 0.1587, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-08-05" }, "meta/muse-spark-1.3": { "cost": [ @@ -5773,7 +7267,9 @@ 0.1587, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-09-02" }, "mistralai/codestral-2508": { "cost": [ @@ -5782,7 +7278,9 @@ 0.03174, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 8192, + "released": "2025-07-30" }, "mistralai/devstral-2512": { "cost": [ @@ -5791,7 +7289,11 @@ 0.046552, 0.0 ], - "limit": 262144 + "knowledge": "2025-12", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2025-12-09" }, "mistralai/ministral-14b-2512": { "cost": [ @@ -5800,7 +7302,10 @@ 0.02116, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 209715, + "open": true, + "released": "2025-12-02" }, "mistralai/ministral-3b-2512": { "cost": [ @@ -5809,7 +7314,10 @@ 0.01058, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 104857, + "open": true, + "released": "2025-12-02" }, "mistralai/ministral-8b-2512": { "cost": [ @@ -5818,7 +7326,10 @@ 0.01587, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 209715, + "open": true, + "released": "2025-12-02" }, "mistralai/mistral-large": { "cost": [ @@ -5827,7 +7338,10 @@ 0.2116, 0.0 ], - "limit": 128000 + "knowledge": "2024-11-30", + "limit": 128000, + "max_output": 102400, + "released": "2024-02-26" }, "mistralai/mistral-large-2407": { "cost": [ @@ -5836,7 +7350,11 @@ 0.2116, 0.0 ], - "limit": 131072 + "knowledge": "2024-03-31", + "limit": 131072, + "max_output": 104857, + "open": true, + "released": "2024-07-24" }, "mistralai/mistral-medium-3": { "cost": [ @@ -5845,7 +7363,10 @@ 0.04232, 0.0 ], - "limit": 131072 + "knowledge": "2025-03-31", + "limit": 131072, + "max_output": 104857, + "released": "2025-05-07" }, "mistralai/mistral-medium-3-5": { "cost": [ @@ -5854,7 +7375,9 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 209715, + "released": "2026-04-30" }, "mistralai/mistral-medium-3.1": { "cost": [ @@ -5863,7 +7386,10 @@ 0.04232, 0.0 ], - "limit": 131072 + "knowledge": "2025-06-30", + "limit": 131072, + "max_output": 104857, + "released": "2025-08-12" }, "mistralai/mistral-nemo": { "cost": [ @@ -5872,7 +7398,11 @@ 0.1587, 0.0 ], - "limit": 128000 + "knowledge": "2024-07", + "limit": 128000, + "max_output": 16384, + "open": true, + "released": "2024-07-18" }, "mistralai/mistral-saba": { "cost": [ @@ -5881,7 +7411,10 @@ 0.02116, 0.0 ], - "limit": 32768 + "knowledge": "2024-09-30", + "limit": 32768, + "max_output": 26214, + "released": "2025-02-17" }, "mistralai/mistral-small-24b-instruct-2501": { "cost": [ @@ -5890,7 +7423,11 @@ 0.0, 0.0 ], - "limit": 32768 + "knowledge": "2023-10-31", + "limit": 32768, + "max_output": 16384, + "open": true, + "released": "2025-01-30" }, "mistralai/mistral-small-2603": { "cost": [ @@ -5899,7 +7436,11 @@ 0.01587, 0.0 ], - "limit": 262144 + "knowledge": "2025-06", + "limit": 262144, + "max_output": 256000, + "open": true, + "released": "2026-03-16" }, "mistralai/mistral-small-3.1-24b-instruct": { "cost": [ @@ -5908,7 +7449,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2023-10-31", + "limit": 128000, + "max_output": 128000, + "open": true, + "released": "2025-03-17" }, "mistralai/mistral-small-3.2-24b-instruct": { "cost": [ @@ -5917,7 +7462,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2023-10-31", + "limit": 128000, + "max_output": 16384, + "open": true, + "released": "2025-06-20" }, "mistralai/mixtral-8x22b-instruct": { "cost": [ @@ -5926,7 +7475,11 @@ 0.2116, 0.0 ], - "limit": 65536 + "knowledge": "2024-01-31", + "limit": 65536, + "max_output": 52428, + "open": true, + "released": "2024-04-17" }, "mistralai/voxtral-small-24b-2507": { "cost": [ @@ -5935,7 +7488,10 @@ 0.01058, 0.0 ], - "limit": 32000 + "limit": 32000, + "max_output": 32768, + "open": true, + "released": "2025-07-15" }, "moonshot/kimi-k3": { "cost": [ @@ -5944,7 +7500,10 @@ 0.3, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-16" }, "moonshotai/kimi-k2": { "cost": [ @@ -5953,7 +7512,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-12-31", + "limit": 131072, + "max_output": 98304, + "open": true, + "released": "2025-07-11" }, "moonshotai/kimi-k2-0905": { "cost": [ @@ -5962,7 +7525,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 98304, + "open": true, + "released": "2025-09-05" }, "moonshotai/kimi-k2-thinking": { "cost": [ @@ -5971,7 +7537,11 @@ 0.1587, 0.0 ], - "limit": 262144 + "knowledge": "2024-08", + "limit": 262144, + "max_output": 98304, + "open": true, + "released": "2025-11-06" }, "morph/morph-v3-fast": { "cost": [ @@ -5980,7 +7550,9 @@ 0.0, 0.0 ], - "limit": 81920 + "limit": 81920, + "max_output": 38000, + "released": "2025-07-07" }, "morph/morph-v3-large": { "cost": [ @@ -5989,7 +7561,9 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 131072, + "released": "2025-07-07" }, "nousresearch/hermes-3-llama-3.1-405b": { "cost": [ @@ -5998,7 +7572,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2023-12-31", + "limit": 131072, + "max_output": 16384, + "open": true, + "released": "2024-08-16" }, "nousresearch/hermes-3-llama-3.1-70b": { "cost": [ @@ -6007,34 +7585,11 @@ 0.0, 0.0 ], - "limit": 131072 - }, - "openai/gpt-3.5-turbo": { - "cost": [ - 0.5, - 1.5, - 0.0, - 0.0 - ], - "limit": 16000 - }, - "openai/gpt-4": { - "cost": [ - 30.0, - 60.0, - 30.0, - 0.0 - ], - "limit": 8000 - }, - "openai/gpt-4-turbo": { - "cost": [ - 10.0, - 30.0, - 0.0, - 0.0 - ], - "limit": 128000 + "knowledge": "2023-12-31", + "limit": 131072, + "max_output": 16384, + "open": true, + "released": "2024-08-18" }, "openai/gpt-4.1": { "cost": [ @@ -6043,7 +7598,10 @@ 0.5, 0.0 ], - "limit": 1047576 + "knowledge": "2024-04", + "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14" }, "openai/gpt-4.1-mini": { "cost": [ @@ -6052,16 +7610,10 @@ 0.1, 0.0 ], - "limit": 1000000 - }, - "openai/gpt-4.1-nano": { - "cost": [ - 0.1, - 0.4, - 0.025, - 0.0 - ], - "limit": 1000000 + "knowledge": "2024-04", + "limit": 1000000, + "max_output": 32768, + "released": "2025-04-14" }, "openai/gpt-4o": { "cost": [ @@ -6070,16 +7622,22 @@ 1.25, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-05-13" }, "openai/gpt-4o-2024-05-13": { "cost": [ - 5.0, - 15.0, + 5.29, + 15.87, 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-05-13" }, "openai/gpt-4o-2024-08-06": { "cost": [ @@ -6088,7 +7646,10 @@ 1.25, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-08-06" }, "openai/gpt-4o-2024-11-20": { "cost": [ @@ -6097,7 +7658,10 @@ 1.25, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-11-20" }, "openai/gpt-4o-mini": { "cost": [ @@ -6106,7 +7670,10 @@ 0.075, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-07-18" }, "openai/gpt-5": { "cost": [ @@ -6115,7 +7682,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "openai/gpt-5-1": { "cost": [ @@ -6124,7 +7694,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "openai/gpt-5-2": { "cost": [ @@ -6133,7 +7706,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "openai/gpt-5-4": { "cost": [ @@ -6142,7 +7718,10 @@ 0.25, 0.0 ], - "limit": 1050000 + "knowledge": "2025-08-31", + "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05" }, "openai/gpt-5-5": { "cost": [ @@ -6151,7 +7730,10 @@ 0.5, 0.0 ], - "limit": 1050000 + "knowledge": "2025-12-01", + "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23" }, "openai/gpt-5-mini": { "cost": [ @@ -6160,7 +7742,10 @@ 0.025, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "openai/gpt-5-nano": { "cost": [ @@ -6169,7 +7754,10 @@ 0.005, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "openai/gpt-5-pro": { "cost": [ @@ -6178,7 +7766,10 @@ 0.0, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 272000, + "released": "2025-10-06" }, "openai/gpt-5.1-codex-max": { "cost": [ @@ -6187,7 +7778,10 @@ 0.2645, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "openai/gpt-5.2-pro": { "cost": [ @@ -6196,7 +7790,10 @@ 0.0, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "openai/gpt-5.3-codex": { "cost": [ @@ -6205,7 +7802,10 @@ 0.3703, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-02-05" }, "openai/gpt-5.4-image-2": { "cost": [ @@ -6214,7 +7814,10 @@ 2.116, 0.0 ], - "limit": 272000 + "limit": 272000, + "max_output": 128000, + "released": "2026-04-21", + "type": "image" }, "openai/gpt-5.4-mini": { "cost": [ @@ -6223,7 +7826,10 @@ 0.1587, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "openai/gpt-5.4-nano": { "cost": [ @@ -6232,7 +7838,10 @@ 0.02116, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "openai/gpt-5.4-pro": { "cost": [ @@ -6241,7 +7850,10 @@ 0.0, 0.0 ], - "limit": 1050000 + "knowledge": "2025-08-31", + "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05" }, "openai/gpt-5.5-pro": { "cost": [ @@ -6250,7 +7862,10 @@ 0.0, 0.0 ], - "limit": 1050000 + "knowledge": "2025-12-01", + "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23" }, "openai/gpt-5.6-luna": { "cost": [ @@ -6259,7 +7874,10 @@ 0.02, 0.25 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "openai/gpt-5.6-luna-pro": { "cost": [ @@ -6268,7 +7886,10 @@ 0.02116, 0.0 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "openai/gpt-5.6-sol": { "cost": [ @@ -6277,7 +7898,10 @@ 0.4, 5.0 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "openai/gpt-5.6-sol-pro": { "cost": [ @@ -6286,7 +7910,10 @@ 0.4232, 0.0 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "openai/gpt-5.6-terra": { "cost": [ @@ -6295,7 +7922,10 @@ 0.2, 2.5 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "openai/gpt-5.6-terra-pro": { "cost": [ @@ -6304,7 +7934,10 @@ 0.2116, 0.0 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "openai/gpt-6-astra": { "cost": [ @@ -6313,7 +7946,10 @@ 1.0, 12.5 ], - "limit": 1050000 + "knowledge": "2026-04-30", + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-04" }, "openai/gpt-6-luna": { "cost": [ @@ -6322,7 +7958,10 @@ 0.01, 0.125 ], - "limit": 1050000 + "knowledge": "2026-05-18", + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22" }, "openai/gpt-6-sol": { "cost": [ @@ -6331,7 +7970,10 @@ 0.2, 2.5 ], - "limit": 1050000 + "knowledge": "2026-04-20", + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22" }, "openai/gpt-6.1-sol": { "cost": [ @@ -6340,7 +7982,22 @@ 0.1, 2.5 ], - "limit": 1050000 + "knowledge": "2026-04-30", + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-29" + }, + "openai/gpt-6.1-terra": { + "cost": [ + 1.0, + 5.0, + 0.05, + 1.25 + ], + "knowledge": "2026-06-01", + "limit": 1050000, + "max_output": 128000, + "released": "2026-10-26" }, "openai/gpt-oss-120b": { "cost": [ @@ -6349,7 +8006,11 @@ 0.3703, 0.0 ], - "limit": 131000 + "knowledge": "2024-06", + "limit": 131000, + "max_output": 117964, + "open": true, + "released": "2025-08-05" }, "openai/gpt-oss-20b": { "cost": [ @@ -6358,7 +8019,11 @@ 0.039675, 0.0 ], - "limit": 131000 + "knowledge": "2024-06", + "limit": 131000, + "max_output": 117964, + "open": true, + "released": "2025-08-05" }, "openai/gpt-oss-safeguard-20b": { "cost": [ @@ -6367,43 +8032,33 @@ 0.039675, 0.0 ], - "limit": 131072 - }, - "openai/o1": { - "cost": [ - 15.0, - 60.0, - 7.5, - 0.0 - ], - "limit": 128000 + "limit": 131072, + "max_output": 65536, + "open": true, + "released": "2025-10-29" }, - "openai/o1-pro": { + "openai/o3-pro": { "cost": [ - 158.7, - 634.8, + 21.16, + 84.64, 0.0, 0.0 ], - "limit": 200000 - }, - "openai/o3-mini": { - "cost": [ - 1.1, - 4.4, - 0.55, - 0.0 - ], - "limit": 200000 + "knowledge": "2024-05", + "limit": 200000, + "max_output": 100000, + "released": "2025-06-10" }, - "openai/o3-pro": { + "perceptron/perceptron-mk1.5": { "cost": [ - 21.16, - 84.64, + 0.1587, + 1.587, 0.0, 0.0 ], - "limit": 200000 + "limit": 36864, + "max_output": 8192, + "released": "2026-09-25" }, "perplexity/sonar": { "cost": [ @@ -6412,7 +8067,10 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2025-09-01", + "limit": 128000, + "max_output": 100000, + "released": "2024-01-01" }, "perplexity/sonar-pro": { "cost": [ @@ -6421,7 +8079,10 @@ 0.0, 0.0 ], - "limit": 200000 + "knowledge": "2025-09-01", + "limit": 200000, + "max_output": 100000, + "released": "2024-01-01" }, "rekaai/reka-edge": { "cost": [ @@ -6430,7 +8091,10 @@ 0.0, 0.0 ], - "limit": 16384 + "limit": 16384, + "max_output": 16384, + "open": true, + "released": "2026-03-11" }, "relace/relace-apply-3": { "cost": [ @@ -6439,7 +8103,9 @@ 0.0, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 128000, + "released": "2025-09-26" }, "relace/relace-search": { "cost": [ @@ -6448,7 +8114,9 @@ 0.0, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 128000, + "released": "2025-12-08" }, "sakana/fugu-max": { "cost": [ @@ -6457,7 +8125,9 @@ 0.2645, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-11" }, "sakana/fugu-ultra": { "cost": [ @@ -6466,7 +8136,9 @@ 0.529, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-15" }, "sakana/fugu-ultra-v2": { "cost": [ @@ -6475,7 +8147,10 @@ 0.529, 0.0 ], - "limit": 1000000 + "knowledge": "2026-08-28", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-11" }, "sao10k/l3-lunaris-8b": { "cost": [ @@ -6484,7 +8159,11 @@ 0.0, 0.0 ], - "limit": 8192 + "knowledge": "2023-12-31", + "limit": 8192, + "max_output": 7372, + "open": true, + "released": "2024-08-13" }, "sao10k/l3.1-euryale-70b": { "cost": [ @@ -6493,7 +8172,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2023-12-31", + "limit": 131072, + "max_output": 16384, + "open": true, + "released": "2024-08-28" }, "sao10k/l3.3-euryale-70b": { "cost": [ @@ -6502,7 +8185,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2023-12-31", + "limit": 131072, + "max_output": 16384, + "open": true, + "released": "2024-12-18" }, "stepfun/step-5-preview": { "cost": [ @@ -6511,7 +8198,10 @@ 0.0529, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 64000, + "open": true, + "released": "2026-09-16" }, "tencent/hy-mt2-1.8b": { "cost": [ @@ -6520,7 +8210,10 @@ 0.0, 0.0 ], - "limit": 8192 + "limit": 8192, + "max_output": 4096, + "open": true, + "released": "2026-05-21" }, "tencent/hy-mt2-30b-a3b": { "cost": [ @@ -6529,7 +8222,10 @@ 0.0, 0.0 ], - "limit": 8192 + "limit": 8192, + "max_output": 4096, + "open": true, + "released": "2026-05-21" }, "tencent/hy-mt2-7b": { "cost": [ @@ -6538,7 +8234,10 @@ 0.0, 0.0 ], - "limit": 8192 + "limit": 8192, + "max_output": 4096, + "open": true, + "released": "2026-05-21" }, "tencent/hy3": { "cost": [ @@ -6547,7 +8246,10 @@ 0.0529, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 131072, + "open": true, + "released": "2026-07-06" }, "tencent/hy4-preview": { "cost": [ @@ -6556,7 +8258,10 @@ 0.044436, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 64000, + "open": true, + "released": "2026-08-28" }, "thedrummer/cydonia-24b-v4.1": { "cost": [ @@ -6565,7 +8270,11 @@ 0.1587, 0.0 ], - "limit": 131072 + "knowledge": "2024-04-30", + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2025-09-27" }, "thedrummer/skyfall-36b-v2": { "cost": [ @@ -6574,7 +8283,11 @@ 0.2645, 0.0 ], - "limit": 32768 + "knowledge": "2024-06-30", + "limit": 32768, + "max_output": 32768, + "open": true, + "released": "2025-03-10" }, "thedrummer/unslopnemo-12b": { "cost": [ @@ -6583,7 +8296,11 @@ 0.0, 0.0 ], - "limit": 32768 + "knowledge": "2024-04-30", + "limit": 32768, + "max_output": 32768, + "open": true, + "released": "2024-11-08" }, "thinkingmachines/inkling": { "cost": [ @@ -6592,7 +8309,10 @@ 0.17986, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-07-15" }, "thinkingmachines/inkling-small": { "cost": [ @@ -6601,7 +8321,10 @@ 0.122728, 0.0 ], - "limit": 524288 + "limit": 524288, + "max_output": 262144, + "open": true, + "released": "2026-07-30" }, "unbiased/pareto": { "cost": [ @@ -6610,7 +8333,9 @@ 0.2645, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 131072, + "released": "2026-09-17" }, "undi95/remm-slerp-l2-13b": { "cost": [ @@ -6619,7 +8344,11 @@ 0.0, 0.0 ], - "limit": 6144 + "knowledge": "2023-06-30", + "limit": 6144, + "max_output": 4096, + "open": true, + "released": "2023-07-22" }, "upstage/solar-pro-3": { "cost": [ @@ -6628,7 +8357,10 @@ 0.01587, 0.0 ], - "limit": 128000 + "knowledge": "2025-07", + "limit": 128000, + "max_output": 8192, + "released": "2026-01-26" }, "upstage/solar-pro4": { "cost": [ @@ -6637,7 +8369,10 @@ 0.006348, 0.0 ], - "limit": 524288 + "knowledge": "2026-02", + "limit": 524288, + "max_output": 131072, + "released": "2026-08-06" }, "x-ai/grok-4-20-0309-non-reasoning": { "cost": [ @@ -6646,7 +8381,9 @@ 0.2, 0.0 ], - "limit": 2000000 + "limit": 2000000, + "max_output": 1999000, + "released": "2026-03-09" }, "x-ai/grok-4-fast-non-reasoning": { "cost": [ @@ -6655,7 +8392,9 @@ 0.2, 0.0 ], - "limit": 2000000 + "limit": 2000000, + "max_output": 1999000, + "released": "2025-12-18" }, "xiaomi/mimo-v2.5": { "cost": [ @@ -6664,7 +8403,11 @@ 0.002962, 0.0 ], - "limit": 1000000 + "knowledge": "2024-12", + "limit": 1000000, + "max_output": 128000, + "open": true, + "released": "2026-04-22" }, "xiaomi/mimo-v2.5-pro": { "cost": [ @@ -6673,7 +8416,11 @@ 0.003809, 0.0 ], - "limit": 1000000 + "knowledge": "2024-12", + "limit": 1000000, + "max_output": 128000, + "open": true, + "released": "2026-04-22" }, "z-ai/glm-4.5v": { "cost": [ @@ -6682,7 +8429,11 @@ 0.11638, 0.0 ], - "limit": 65536 + "knowledge": "2025-04", + "limit": 65536, + "max_output": 16384, + "open": true, + "released": "2025-08-11" }, "z-ai/glm-4.6v": { "cost": [ @@ -6691,7 +8442,11 @@ 0.05819, 0.0 ], - "limit": 131072 + "knowledge": "2025-04", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-12-08" }, "z-ai/glm-4.7-flash": { "cost": [ @@ -6700,7 +8455,11 @@ 0.01058, 0.0 ], - "limit": 202752 + "knowledge": "2025-04", + "limit": 202752, + "max_output": 16384, + "open": true, + "released": "2026-01-19" }, "z-ai/glm-5-turbo": { "cost": [ @@ -6709,7 +8468,9 @@ 0.24, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 131072, + "released": "2026-03-16" }, "z-ai/glm-5.3-flash": { "cost": [ @@ -6718,7 +8479,10 @@ 0.03, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-08-26" }, "z-ai/glm-5v-turbo": { "cost": [ @@ -6727,7 +8491,9 @@ 0.24, 0.0 ], - "limit": 202752 + "limit": 202752, + "max_output": 131072, + "released": "2026-04-01" }, "zhipu/glm-5.2": { "cost": [ @@ -6736,7 +8502,10 @@ 0.26, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "zhipu/glm-5.3": { "cost": [ @@ -6745,7 +8514,10 @@ 0.26, 0.0 ], - "limit": 1024000 + "limit": 1024000, + "max_output": 131072, + "open": true, + "released": "2026-08-14" } }, "name": "AI/ML API" @@ -6759,7 +8531,10 @@ 0.3, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-07-16" } }, "name": "ainetcafe" @@ -6773,7 +8548,10 @@ 0.25, 12.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-01" }, "anthropic/claude-haiku-5-5": { "cost": [ @@ -6782,7 +8560,10 @@ 0.01, 0.125 ], + "knowledge": "2026-06", "limit": 1000000, + "max_output": 128000, + "released": "2026-10-07", "tiers": [ { "cost": [ @@ -6805,7 +8586,10 @@ 0.2, 5.0 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-22" }, "anthropic/claude-sonnet-5-5": { "cost": [ @@ -6814,7 +8598,10 @@ 0.1, 2.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-28" }, "gemini/gemini-3.8-flash": { "cost": [ @@ -6823,7 +8610,9 @@ 0.075, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65536, + "released": "2026-09-02" }, "gemini/gemini-4-argon": { "cost": [ @@ -6832,7 +8621,10 @@ 0.1, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 32768, + "released": "2026-10-13" }, "openai/gpt-5.6-luna": { "cost": [ @@ -6841,7 +8633,10 @@ 0.02, 0.25 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -6864,7 +8659,10 @@ 0.4, 5.0 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -6887,7 +8685,10 @@ 0.2, 2.5 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -6910,7 +8711,10 @@ 1.0, 12.5 ], + "knowledge": "2026-04-30", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-04", "tiers": [ { "cost": [ @@ -6933,7 +8737,10 @@ 0.01, 0.125 ], + "knowledge": "2026-05-18", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -6956,7 +8763,10 @@ 0.2, 2.5 ], + "knowledge": "2026-04-20", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -6979,7 +8789,10 @@ 0.1, 2.5 ], + "knowledge": "2026-04-30", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-29", "tiers": [ { "cost": [ @@ -7007,7 +8820,11 @@ 0.11215, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 81920, + "open": true, + "released": "2026-09-10" }, "gemma4-26b": { "cost": [ @@ -7016,7 +8833,10 @@ 0.0, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 32768, + "open": true, + "released": "2026-04-02" }, "glm5.3-754b": { "cost": [ @@ -7025,7 +8845,10 @@ 0.280375, 0.0 ], - "limit": 524288 + "limit": 524288, + "max_output": 81920, + "open": true, + "released": "2026-08-14" }, "gpt-oss-120b": { "cost": [ @@ -7034,7 +8857,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-06", + "limit": 128000, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "mistral4-119b": { "cost": [ @@ -7043,7 +8870,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-06", + "limit": 262144, + "max_output": 81920, + "open": true, + "released": "2026-03-16" }, "qwen3.6-35b": { "cost": [ @@ -7053,6 +8884,9 @@ 0.0 ], "limit": 256000, + "max_output": 32768, + "open": true, + "released": "2026-04-17", "status": "deprecated" }, "qwen3.8-27b": { @@ -7062,7 +8896,10 @@ 0.11215, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-08-14" } }, "name": "AKI.IO" @@ -7076,7 +8913,11 @@ 0.088, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-07-31" }, "glm-5.2": { "cost": [ @@ -7085,7 +8926,10 @@ 0.28, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "kimi-k3": { "cost": [ @@ -7094,7 +8938,10 @@ 0.3, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-07-16" }, "qvq-max": { "cost": [ @@ -7103,7 +8950,10 @@ 0.0, 0.0 ], + "knowledge": "2024-04", "limit": 131072, + "max_output": 8192, + "released": "2025-03-25", "status": "deprecated" }, "qwen-flash": { @@ -7113,7 +8963,10 @@ 0.01, 0.0625 ], + "knowledge": "2024-04", "limit": 1000000, + "max_output": 32768, + "released": "2025-07-28", "tiers": [ { "cost": [ @@ -7136,7 +8989,10 @@ 0.0, 0.0 ], - "limit": 32768 + "knowledge": "2024-04", + "limit": 32768, + "max_output": 8192, + "released": "2024-04-03" }, "qwen-mt-plus": { "cost": [ @@ -7145,7 +9001,10 @@ 0.0, 0.0 ], - "limit": 16384 + "knowledge": "2024-04", + "limit": 16384, + "max_output": 8192, + "released": "2025-01" }, "qwen-mt-turbo": { "cost": [ @@ -7154,7 +9013,10 @@ 0.0, 0.0 ], + "knowledge": "2024-04", "limit": 16384, + "max_output": 8192, + "released": "2025-01", "status": "deprecated" }, "qwen-omni-turbo": { @@ -7164,7 +9026,10 @@ 0.0, 0.0 ], + "knowledge": "2024-04", "limit": 32768, + "max_output": 2048, + "released": "2025-01-19", "status": "deprecated" }, "qwen-omni-turbo-realtime": { @@ -7174,8 +9039,12 @@ 0.0, 0.0 ], + "knowledge": "2024-04", "limit": 32768, - "status": "deprecated" + "max_output": 2048, + "released": "2025-05-08", + "status": "deprecated", + "type": "realtime" }, "qwen-plus": { "cost": [ @@ -7184,7 +9053,11 @@ 0.08, 0.5 ], + "knowledge": "2024-04", "limit": 1000000, + "max_output": 32768, + "reasoning": 4.0, + "released": "2024-01-25", "tiers": [ { "cost": [ @@ -7193,6 +9066,7 @@ 0.24, 1.5 ], + "reasoning": 12.0, "tier": { "size": 256000, "type": "context" @@ -7207,7 +9081,10 @@ 0.0, 0.0 ], - "limit": 8192 + "knowledge": "2024-04", + "limit": 8192, + "max_output": 512, + "released": "2024-01" }, "qwen-turbo": { "cost": [ @@ -7216,7 +9093,11 @@ 0.0, 0.0 ], + "knowledge": "2024-04", "limit": 1000000, + "max_output": 16384, + "reasoning": 0.5, + "released": "2024-11-01", "status": "deprecated" }, "qwen-vl-max": { @@ -7226,7 +9107,10 @@ 0.0, 0.0 ], + "knowledge": "2024-04", "limit": 131072, + "max_output": 8192, + "released": "2024-04-08", "status": "deprecated" }, "qwen-vl-ocr": { @@ -7236,7 +9120,10 @@ 0.0, 0.0 ], - "limit": 34096 + "knowledge": "2024-04", + "limit": 34096, + "max_output": 4096, + "released": "2024-10-28" }, "qwen-vl-plus": { "cost": [ @@ -7245,7 +9132,10 @@ 0.0, 0.0 ], + "knowledge": "2024-04", "limit": 131072, + "max_output": 8192, + "released": "2024-01-25", "status": "deprecated" }, "qwen2-5-omni-7b": { @@ -7255,7 +9145,11 @@ 0.0, 0.0 ], + "knowledge": "2024-04", "limit": 32768, + "max_output": 2048, + "open": true, + "released": "2024-12", "status": "deprecated" }, "qwen3-14b": { @@ -7265,7 +9159,12 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 131072, + "max_output": 8192, + "open": true, + "reasoning": 4.2, + "released": "2025-04", "status": "deprecated" }, "qwen3-235b-a22b": { @@ -7275,7 +9174,12 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 131072, + "max_output": 16384, + "open": true, + "reasoning": 8.4, + "released": "2025-04", "status": "deprecated" }, "qwen3-32b": { @@ -7285,7 +9189,12 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 131072, + "max_output": 16384, + "open": true, + "reasoning": 8.4, + "released": "2025-04", "status": "deprecated" }, "qwen3-8b": { @@ -7295,7 +9204,12 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 131072, + "max_output": 8192, + "open": true, + "reasoning": 2.1, + "released": "2025-04", "status": "deprecated" }, "qwen3-coder-30b-a3b-instruct": { @@ -7305,7 +9219,11 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2025-04", "status": "deprecated", "tiers": [ { @@ -7341,7 +9259,11 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2025-04", "status": "deprecated", "tiers": [ { @@ -7377,7 +9299,10 @@ 0.06, 0.375 ], + "knowledge": "2025-04", "limit": 1000000, + "max_output": 65536, + "released": "2025-07-28", "tiers": [ { "cost": [ @@ -7424,7 +9349,11 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 1048576, + "max_output": 65536, + "open": true, + "released": "2025-07-23", "status": "deprecated" }, "qwen3-livetranslate-flash-realtime": { @@ -7434,8 +9363,12 @@ 0.0, 0.0 ], + "knowledge": "2024-04", "limit": 53248, - "status": "deprecated" + "max_output": 4096, + "released": "2025-09-22", + "status": "deprecated", + "type": "realtime" }, "qwen3-max": { "cost": [ @@ -7444,7 +9377,10 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 262144, + "max_output": 65536, + "released": "2025-09-23", "status": "deprecated" }, "qwen3-next-80b-a3b-instruct": { @@ -7454,7 +9390,11 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-09", "status": "deprecated" }, "qwen3-next-80b-a3b-thinking": { @@ -7464,7 +9404,11 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-09", "status": "deprecated" }, "qwen3-omni-flash": { @@ -7474,7 +9418,10 @@ 0.0, 0.0 ], - "limit": 65536 + "knowledge": "2024-04", + "limit": 65536, + "max_output": 16384, + "released": "2025-09-15" }, "qwen3-omni-flash-realtime": { "cost": [ @@ -7483,8 +9430,12 @@ 0.0, 0.0 ], + "knowledge": "2024-04", "limit": 65536, - "status": "deprecated" + "max_output": 16384, + "released": "2025-09-15", + "status": "deprecated", + "type": "realtime" }, "qwen3-vl-235b-a22b": { "cost": [ @@ -7493,7 +9444,12 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 131072, + "max_output": 32768, + "open": true, + "reasoning": 8.4, + "released": "2025-04", "status": "deprecated" }, "qwen3-vl-30b-a3b": { @@ -7503,7 +9459,12 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2025-04", + "limit": 131072, + "max_output": 32768, + "open": true, + "reasoning": 2.4, + "released": "2025-04" }, "qwen3-vl-plus": { "cost": [ @@ -7512,7 +9473,10 @@ 0.04, 0.25 ], + "knowledge": "2025-04", "limit": 262144, + "max_output": 32768, + "released": "2025-09-23", "tiers": [ { "cost": [ @@ -7547,7 +9511,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-23" }, "qwen3.5-27b": { "cost": [ @@ -7556,7 +9523,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-23" }, "qwen3.5-35b-a3b": { "cost": [ @@ -7565,7 +9535,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-23" }, "qwen3.5-397b-a17b": { "cost": [ @@ -7574,7 +9547,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-15" }, "qwen3.5-flash": { "cost": [ @@ -7583,7 +9559,9 @@ 0.01, 0.125 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 65536, + "released": "2026-02-23" }, "qwen3.5-plus": { "cost": [ @@ -7592,7 +9570,10 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 1000000, + "max_output": 65536, + "released": "2026-02-16", "tiers": [ { "cost": [ @@ -7615,7 +9596,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-04-22" }, "qwen3.6-35b-a3b": { "cost": [ @@ -7624,7 +9608,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-04-17" }, "qwen3.6-flash": { "cost": [ @@ -7634,6 +9621,8 @@ 0.3125 ], "limit": 1000000, + "max_output": 65536, + "released": "2026-04-27", "tiers": [ { "cost": [ @@ -7656,7 +9645,10 @@ 0.13, 1.625 ], + "knowledge": "2025-04", "limit": 262144, + "max_output": 65536, + "released": "2026-04-20", "status": "deprecated" }, "qwen3.6-plus": { @@ -7666,7 +9658,10 @@ 0.05, 0.625 ], + "knowledge": "2025-04", "limit": 1000000, + "max_output": 65536, + "released": "2026-04-02", "tiers": [ { "cost": [ @@ -7690,6 +9685,8 @@ 0.0375 ], "limit": 1000000, + "max_output": 131072, + "released": "2026-07-15", "tiers": [ { "cost": [ @@ -7724,7 +9721,9 @@ 0.5, 3.125 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-05-21" }, "qwen3.7-plus": { "cost": [ @@ -7733,7 +9732,10 @@ 0.08, 0.5 ], + "knowledge": "2025-04", "limit": 1000000, + "max_output": 131072, + "released": "2026-06-02", "tiers": [ { "cost": [ @@ -7756,7 +9758,9 @@ 0.016, 0.2 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-08-26" }, "qwen3.8-max": { "cost": [ @@ -7765,7 +9769,9 @@ 0.25, 2.5 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-08-03" }, "qwen3.8-omni-flash": { "cost": [ @@ -7774,7 +9780,9 @@ 0.016, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-09-17" }, "qwq-plus": { "cost": [ @@ -7783,7 +9791,10 @@ 0.0, 0.0 ], + "knowledge": "2024-04", "limit": 131072, + "max_output": 8192, + "released": "2025-03-05", "status": "deprecated" } }, @@ -7798,7 +9809,10 @@ 0.0, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-02-12" }, "MiniMax/MiniMax-M2.7": { "cost": [ @@ -7807,7 +9821,10 @@ 0.06, 0.375 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-03-18" }, "deepseek-r1": { "cost": [ @@ -7817,6 +9834,8 @@ 0.0 ], "limit": 131072, + "max_output": 16384, + "released": "2025-01-01", "status": "deprecated" }, "deepseek-r1-0528": { @@ -7827,6 +9846,8 @@ 0.0 ], "limit": 131072, + "max_output": 16384, + "released": "2025-05-28", "status": "deprecated" }, "deepseek-r1-distill-llama-70b": { @@ -7836,7 +9857,9 @@ 0.0, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 16384, + "released": "2025-01-01" }, "deepseek-r1-distill-llama-8b": { "cost": [ @@ -7846,6 +9869,8 @@ 0.0 ], "limit": 32768, + "max_output": 16384, + "released": "2025-01-01", "status": "deprecated" }, "deepseek-r1-distill-qwen-1-5b": { @@ -7855,7 +9880,9 @@ 0.0, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 16384, + "released": "2025-01-01" }, "deepseek-r1-distill-qwen-14b": { "cost": [ @@ -7865,6 +9892,8 @@ 0.0 ], "limit": 32768, + "max_output": 16384, + "released": "2025-01-01", "status": "deprecated" }, "deepseek-r1-distill-qwen-32b": { @@ -7875,6 +9904,8 @@ 0.0 ], "limit": 32768, + "max_output": 16384, + "released": "2025-01-01", "status": "deprecated" }, "deepseek-r1-distill-qwen-7b": { @@ -7885,6 +9916,8 @@ 0.0 ], "limit": 32768, + "max_output": 16384, + "released": "2025-01-01", "status": "deprecated" }, "deepseek-v3": { @@ -7895,6 +9928,8 @@ 0.0 ], "limit": 65536, + "max_output": 8192, + "released": "2024-12-01", "status": "deprecated" }, "deepseek-v3-1": { @@ -7905,6 +9940,8 @@ 0.0 ], "limit": 131072, + "max_output": 65536, + "released": "2025-01-01", "status": "deprecated" }, "deepseek-v3-2-exp": { @@ -7915,6 +9952,8 @@ 0.0 ], "limit": 131072, + "max_output": 65536, + "released": "2025-01-01", "status": "deprecated" }, "deepseek-v4-flash": { @@ -7924,7 +9963,11 @@ 0.0028, 0.0 ], + "knowledge": "2025-05", "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24", "status": "deprecated" }, "deepseek-v4-pro": { @@ -7934,7 +9977,11 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "deepseek-v4.1-flash": { "cost": [ @@ -7943,7 +9990,11 @@ 0.01488, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-09-10" }, "glm-5": { "cost": [ @@ -7953,6 +10004,8 @@ 0.0 ], "limit": 202752, + "max_output": 16384, + "released": "2026-02-11", "tiers": [ { "cost": [ @@ -7976,6 +10029,9 @@ 1.03125 ], "limit": 202752, + "max_output": 128000, + "open": true, + "released": "2026-04-14", "tiers": [ { "cost": [ @@ -7998,7 +10054,10 @@ 0.275, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 128000, + "open": true, + "released": "2026-06-13" }, "glm-5.3": { "cost": [ @@ -8007,7 +10066,10 @@ 0.275, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "kimi-k2-thinking": { "cost": [ @@ -8017,6 +10079,9 @@ 0.0 ], "limit": 262144, + "max_output": 16384, + "open": true, + "released": "2025-11-06", "status": "deprecated" }, "kimi-k2.5": { @@ -8026,7 +10091,11 @@ 0.1148, 0.7175 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-01-27" }, "kimi-k2.6": { "cost": [ @@ -8035,7 +10104,11 @@ 0.1858, 1.16125 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 16384, + "open": true, + "released": "2026-04-21" }, "kimi-k3": { "cost": [ @@ -8044,7 +10117,10 @@ 0.283, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-07-16" }, "kimi/kimi-k2.5": { "cost": [ @@ -8053,7 +10129,11 @@ 0.1, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-01-27" }, "moonshot-kimi-k2-instruct": { "cost": [ @@ -8063,6 +10143,9 @@ 0.0 ], "limit": 131072, + "max_output": 8192, + "open": true, + "released": "2025-01-01", "status": "deprecated" }, "qvq-max": { @@ -8072,7 +10155,10 @@ 0.0, 0.0 ], + "knowledge": "2024-04", "limit": 131072, + "max_output": 8192, + "released": "2025-03-25", "status": "deprecated" }, "qwen-deep-research": { @@ -8082,7 +10168,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2024-04", + "limit": 1000000, + "max_output": 32768, + "released": "2024-01" }, "qwen-doc-turbo": { "cost": [ @@ -8091,7 +10180,10 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-04", + "limit": 131072, + "max_output": 8192, + "released": "2024-01" }, "qwen-flash": { "cost": [ @@ -8100,7 +10192,10 @@ 0.0044, 0.0275 ], + "knowledge": "2024-04", "limit": 1000000, + "max_output": 32768, + "released": "2025-07-28", "tiers": [ { "cost": [ @@ -8135,7 +10230,10 @@ 0.0, 0.0 ], - "limit": 10000000 + "knowledge": "2024-04", + "limit": 10000000, + "max_output": 8192, + "released": "2025-01-25" }, "qwen-math-plus": { "cost": [ @@ -8144,7 +10242,10 @@ 0.0, 0.0 ], + "knowledge": "2024-04", "limit": 4096, + "max_output": 3072, + "released": "2024-08-16", "status": "deprecated" }, "qwen-math-turbo": { @@ -8154,7 +10255,10 @@ 0.0, 0.0 ], + "knowledge": "2024-04", "limit": 4096, + "max_output": 3072, + "released": "2024-09-19", "status": "deprecated" }, "qwen-max": { @@ -8164,7 +10268,10 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-04", + "limit": 131072, + "max_output": 8192, + "released": "2024-04-03" }, "qwen-mt-plus": { "cost": [ @@ -8173,7 +10280,10 @@ 0.0, 0.0 ], - "limit": 16384 + "knowledge": "2024-04", + "limit": 16384, + "max_output": 8192, + "released": "2025-01" }, "qwen-mt-turbo": { "cost": [ @@ -8182,7 +10292,10 @@ 0.0, 0.0 ], + "knowledge": "2024-04", "limit": 16384, + "max_output": 8192, + "released": "2025-01", "status": "deprecated" }, "qwen-omni-turbo": { @@ -8192,7 +10305,10 @@ 0.0, 0.0 ], + "knowledge": "2024-04", "limit": 32768, + "max_output": 2048, + "released": "2025-01-19", "status": "deprecated" }, "qwen-omni-turbo-realtime": { @@ -8202,8 +10318,12 @@ 0.0, 0.0 ], + "knowledge": "2024-04", "limit": 32768, - "status": "deprecated" + "max_output": 2048, + "released": "2025-05-08", + "status": "deprecated", + "type": "realtime" }, "qwen-plus": { "cost": [ @@ -8212,7 +10332,11 @@ 0.023, 0.144 ], + "knowledge": "2024-04", "limit": 1000000, + "max_output": 32768, + "reasoning": 1.147, + "released": "2024-01-25", "tiers": [ { "cost": [ @@ -8221,6 +10345,7 @@ 0.069, 0.43125 ], + "reasoning": 3.441, "tier": { "size": 128000, "type": "context" @@ -8233,6 +10358,7 @@ 0.1378, 0.86125 ], + "reasoning": 9.175, "tier": { "size": 256000, "type": "context" @@ -8247,7 +10373,10 @@ 0.0, 0.0 ], - "limit": 32768 + "knowledge": "2024-04", + "limit": 32768, + "max_output": 4096, + "released": "2024-01" }, "qwen-turbo": { "cost": [ @@ -8256,7 +10385,11 @@ 0.0, 0.0 ], + "knowledge": "2024-04", "limit": 1000000, + "max_output": 16384, + "reasoning": 0.431, + "released": "2024-11-01", "status": "deprecated" }, "qwen-vl-max": { @@ -8266,7 +10399,10 @@ 0.0, 0.0 ], + "knowledge": "2024-04", "limit": 131072, + "max_output": 8192, + "released": "2024-04-08", "status": "deprecated" }, "qwen-vl-ocr": { @@ -8276,7 +10412,10 @@ 0.0, 0.0 ], - "limit": 34096 + "knowledge": "2024-04", + "limit": 34096, + "max_output": 4096, + "released": "2024-10-28" }, "qwen-vl-plus": { "cost": [ @@ -8285,7 +10424,10 @@ 0.0, 0.0 ], + "knowledge": "2024-04", "limit": 131072, + "max_output": 8192, + "released": "2024-01-25", "status": "deprecated" }, "qwen2-5-omni-7b": { @@ -8295,7 +10437,11 @@ 0.0, 0.0 ], + "knowledge": "2024-04", "limit": 32768, + "max_output": 2048, + "open": true, + "released": "2024-12", "status": "deprecated" }, "qwen3-14b": { @@ -8305,7 +10451,12 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 131072, + "max_output": 8192, + "open": true, + "reasoning": 1.434, + "released": "2025-04", "status": "deprecated" }, "qwen3-235b-a22b": { @@ -8315,7 +10466,12 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 131072, + "max_output": 16384, + "open": true, + "reasoning": 2.868, + "released": "2025-04", "status": "deprecated" }, "qwen3-32b": { @@ -8325,7 +10481,12 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 131072, + "max_output": 16384, + "open": true, + "reasoning": 2.868, + "released": "2025-04", "status": "deprecated" }, "qwen3-8b": { @@ -8335,7 +10496,12 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 131072, + "max_output": 8192, + "open": true, + "reasoning": 0.717, + "released": "2025-04", "status": "deprecated" }, "qwen3-coder-30b-a3b-instruct": { @@ -8345,7 +10511,11 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2025-04", "status": "deprecated", "tiers": [ { @@ -8381,7 +10551,11 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2025-04", "status": "deprecated", "tiers": [ { @@ -8417,7 +10591,10 @@ 0.0288, 0.18 ], + "knowledge": "2025-04", "limit": 1000000, + "max_output": 65536, + "released": "2025-07-28", "tiers": [ { "cost": [ @@ -8464,7 +10641,11 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 1048576, + "max_output": 65536, + "open": true, + "released": "2025-07-23", "status": "deprecated", "tiers": [ { @@ -8512,7 +10693,10 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 262144, + "max_output": 65536, + "released": "2026-01-23", "status": "deprecated", "tiers": [ { @@ -8548,7 +10732,11 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-09", "status": "deprecated" }, "qwen3-next-80b-a3b-thinking": { @@ -8558,7 +10746,11 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-09", "status": "deprecated" }, "qwen3-omni-flash": { @@ -8568,7 +10760,10 @@ 0.0, 0.0 ], - "limit": 65536 + "knowledge": "2024-04", + "limit": 65536, + "max_output": 16384, + "released": "2025-09-15" }, "qwen3-omni-flash-realtime": { "cost": [ @@ -8577,8 +10772,12 @@ 0.0, 0.0 ], + "knowledge": "2024-04", "limit": 65536, - "status": "deprecated" + "max_output": 16384, + "released": "2025-09-15", + "status": "deprecated", + "type": "realtime" }, "qwen3-vl-235b-a22b": { "cost": [ @@ -8587,7 +10786,12 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 131072, + "max_output": 32768, + "open": true, + "reasoning": 2.867051, + "released": "2025-04", "status": "deprecated" }, "qwen3-vl-30b-a3b": { @@ -8597,7 +10801,12 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 131072, + "max_output": 32768, + "open": true, + "reasoning": 1.076, + "released": "2025-04", "status": "deprecated" }, "qwen3-vl-plus": { @@ -8607,7 +10816,10 @@ 0.028671, 0.179191 ], + "knowledge": "2025-04", "limit": 262144, + "max_output": 32768, + "released": "2025-09-23", "tiers": [ { "cost": [ @@ -8642,7 +10854,11 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-16", "tiers": [ { "cost": [ @@ -8665,7 +10881,10 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 1000000, + "max_output": 65536, + "released": "2026-02-23", "tiers": [ { "cost": [ @@ -8700,7 +10919,10 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 1000000, + "max_output": 65536, + "released": "2026-02-16", "tiers": [ { "cost": [ @@ -8736,6 +10958,8 @@ 0.20625 ], "limit": 1000000, + "max_output": 65536, + "released": "2026-04-27", "tiers": [ { "cost": [ @@ -8759,6 +10983,8 @@ 0.0 ], "limit": 245800, + "max_output": 65536, + "released": "2026-04-20", "status": "deprecated" }, "qwen3.6-plus": { @@ -8768,7 +10994,10 @@ 0.0276, 0.345 ], + "knowledge": "2025-04", "limit": 1000000, + "max_output": 65536, + "released": "2026-04-02", "tiers": [ { "cost": [ @@ -8792,6 +11021,8 @@ 0.03703 ], "limit": 1000000, + "max_output": 131072, + "released": "2026-07-15", "tiers": [ { "cost": [ @@ -8826,7 +11057,9 @@ 0.33, 2.0625 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-05-21" }, "qwen3.7-plus": { "cost": [ @@ -8835,7 +11068,10 @@ 0.0552, 0.345 ], + "knowledge": "2025-04", "limit": 1000000, + "max_output": 64000, + "released": "2026-06-02", "tiers": [ { "cost": [ @@ -8858,7 +11094,9 @@ 0.014844, 0.185547 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-08-26" }, "qwen3.8-max": { "cost": [ @@ -8867,7 +11105,9 @@ 0.22218, 2.22179 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-08-03" }, "qwen3.8-omni-flash": { "cost": [ @@ -8876,7 +11116,9 @@ 0.014, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-09-17" }, "qwq-plus": { "cost": [ @@ -8885,7 +11127,10 @@ 0.0, 0.0 ], + "knowledge": "2024-04", "limit": 131072, + "max_output": 8192, + "released": "2025-03-05", "status": "deprecated" }, "siliconflow/deepseek-r1-0528": { @@ -8895,7 +11140,9 @@ 0.0, 0.0 ], - "limit": 163840 + "limit": 163840, + "max_output": 32768, + "released": "2025-05-28" }, "siliconflow/deepseek-v3-0324": { "cost": [ @@ -8904,7 +11151,9 @@ 0.0, 0.0 ], - "limit": 163840 + "limit": 163840, + "max_output": 163840, + "released": "2024-12-26" }, "siliconflow/deepseek-v3.1-terminus": { "cost": [ @@ -8913,7 +11162,9 @@ 0.0, 0.0 ], - "limit": 163840 + "limit": 163840, + "max_output": 65536, + "released": "2025-09-29" }, "siliconflow/deepseek-v3.2": { "cost": [ @@ -8922,7 +11173,9 @@ 0.0, 0.0 ], - "limit": 163840 + "limit": 163840, + "max_output": 65536, + "released": "2025-12-03" }, "tongyi-intent-detect-v3": { "cost": [ @@ -8931,7 +11184,10 @@ 0.0, 0.0 ], - "limit": 8192 + "knowledge": "2024-04", + "limit": 8192, + "max_output": 1024, + "released": "2024-01" } }, "name": "Alibaba (China)" @@ -8945,7 +11201,10 @@ 0.0, 0.0 ], - "limit": 196608 + "limit": 196608, + "max_output": 24576, + "open": true, + "released": "2026-02-12" }, "glm-4.7": { "cost": [ @@ -8954,7 +11213,11 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 202752, + "max_output": 16384, + "open": true, + "released": "2025-12-22", "status": "deprecated" }, "glm-5": { @@ -8964,7 +11227,9 @@ 0.0, 0.0 ], - "limit": 202752 + "limit": 202752, + "max_output": 16384, + "released": "2026-02-11" }, "kimi-k2.5": { "cost": [ @@ -8973,7 +11238,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-01-27" }, "qwen3-coder-next": { "cost": [ @@ -8983,6 +11252,9 @@ 0.0 ], "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-03", "status": "deprecated" }, "qwen3-coder-plus": { @@ -8992,7 +11264,11 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 1000000, + "max_output": 65536, + "open": true, + "released": "2025-07-23", "status": "deprecated" }, "qwen3-max-2026-01-23": { @@ -9002,7 +11278,10 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 262144, + "max_output": 32768, + "released": "2026-01-23", "status": "deprecated" }, "qwen3.5-plus": { @@ -9012,7 +11291,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-04", + "limit": 1000000, + "max_output": 65536, + "released": "2026-02-16" }, "qwen3.6-plus": { "cost": [ @@ -9021,7 +11303,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-04", + "limit": 1000000, + "max_output": 65536, + "released": "2026-04-02" }, "qwen3.7-plus": { "cost": [ @@ -9030,7 +11315,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-04", + "limit": 1000000, + "max_output": 64000, + "released": "2026-06-02" } }, "name": "Alibaba Coding Plan" @@ -9044,7 +11332,10 @@ 0.0, 0.0 ], - "limit": 196608 + "limit": 196608, + "max_output": 24576, + "open": true, + "released": "2026-02-12" }, "glm-4.7": { "cost": [ @@ -9053,7 +11344,11 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 202752, + "max_output": 16384, + "open": true, + "released": "2025-12-22", "status": "deprecated" }, "glm-5": { @@ -9063,7 +11358,9 @@ 0.0, 0.0 ], - "limit": 202752 + "limit": 202752, + "max_output": 16384, + "released": "2026-02-11" }, "kimi-k2.5": { "cost": [ @@ -9072,7 +11369,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-01-27" }, "qwen3-coder-next": { "cost": [ @@ -9082,6 +11383,9 @@ 0.0 ], "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-03", "status": "deprecated" }, "qwen3-coder-plus": { @@ -9091,7 +11395,11 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 1000000, + "max_output": 65536, + "open": true, + "released": "2025-07-23", "status": "deprecated" }, "qwen3-max-2026-01-23": { @@ -9101,7 +11409,10 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 262144, + "max_output": 32768, + "released": "2026-01-23", "status": "deprecated" }, "qwen3.5-plus": { @@ -9111,7 +11422,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-04", + "limit": 1000000, + "max_output": 65536, + "released": "2026-02-16" }, "qwen3.6-plus": { "cost": [ @@ -9120,7 +11434,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-04", + "limit": 1000000, + "max_output": 65536, + "released": "2026-04-02" }, "qwen3.7-plus": { "cost": [ @@ -9129,7 +11446,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-04", + "limit": 1000000, + "max_output": 64000, + "released": "2026-06-02" } }, "name": "Alibaba Coding Plan (China)" @@ -9143,7 +11463,10 @@ 0.0, 0.0 ], - "limit": 196608 + "limit": 196608, + "max_output": 32768, + "open": true, + "released": "2026-02-12" }, "deepseek-v3.2": { "cost": [ @@ -9152,7 +11475,11 @@ 0.0, 0.0 ], + "knowledge": "2025-01", "limit": 131072, + "max_output": 65536, + "open": true, + "released": "2025-12-03", "status": "deprecated" }, "deepseek-v4-flash": { @@ -9162,7 +11489,11 @@ 0.0, 0.0 ], + "knowledge": "2025-05", "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24", "status": "deprecated" }, "deepseek-v4-flash-0731": { @@ -9172,7 +11503,11 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-07-31" }, "deepseek-v4-pro": { "cost": [ @@ -9181,7 +11516,11 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "deepseek-v4-pro-0813": { "cost": [ @@ -9190,7 +11529,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-08-13" }, "deepseek-v4.1-flash": { "cost": [ @@ -9199,7 +11541,11 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-09-10" }, "deepseek-v4.1-flash-1017": { "cost": [ @@ -9208,7 +11554,11 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-10-17" }, "glm-5": { "cost": [ @@ -9217,7 +11567,9 @@ 0.0, 0.0 ], - "limit": 202752 + "limit": 202752, + "max_output": 16384, + "released": "2026-02-12" }, "glm-5.1": { "cost": [ @@ -9226,7 +11578,10 @@ 0.0, 0.0 ], - "limit": 202752 + "limit": 202752, + "max_output": 128000, + "open": true, + "released": "2026-04-07" }, "glm-5.2": { "cost": [ @@ -9235,7 +11590,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "glm-5.3": { "cost": [ @@ -9244,7 +11602,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "happyhorse-1.1-i2v": { "cost": [ @@ -9252,7 +11613,9 @@ 0.0, 0.0, 0.0 - ] + ], + "released": "2026-07-17", + "type": "video" }, "happyhorse-1.1-r2v": { "cost": [ @@ -9260,7 +11623,9 @@ 0.0, 0.0, 0.0 - ] + ], + "released": "2026-07-17", + "type": "video" }, "happyhorse-1.1-t2v": { "cost": [ @@ -9268,7 +11633,9 @@ 0.0, 0.0, 0.0 - ] + ], + "released": "2026-07-17", + "type": "video" }, "kimi-k2.5": { "cost": [ @@ -9277,7 +11644,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 98304, + "open": true, + "released": "2026-01-27" }, "kimi-k2.6": { "cost": [ @@ -9286,7 +11657,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-20" }, "kimi-k2.7-code": { "cost": [ @@ -9295,7 +11670,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-06-12" }, "qwen-image-2.0": { "cost": [ @@ -9304,7 +11683,9 @@ 0.0, 0.0 ], - "limit": 8192 + "limit": 8192, + "released": "2026-03-03", + "type": "image" }, "qwen-image-2.0-pro": { "cost": [ @@ -9313,7 +11694,9 @@ 0.0, 0.0 ], - "limit": 8192 + "limit": 8192, + "released": "2026-03-03", + "type": "image" }, "qwen3.6-flash": { "cost": [ @@ -9322,7 +11705,9 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 65536, + "released": "2026-04-27" }, "qwen3.6-plus": { "cost": [ @@ -9331,7 +11716,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-04", + "limit": 1000000, + "max_output": 65536, + "released": "2026-04-02" }, "qwen3.7-max": { "cost": [ @@ -9340,7 +11728,9 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-05-21" }, "qwen3.7-plus": { "cost": [ @@ -9349,7 +11739,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-04", + "limit": 1000000, + "max_output": 65536, + "released": "2026-06-02" }, "qwen3.8-flash": { "cost": [ @@ -9358,7 +11751,9 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-08-26" }, "qwen3.8-max": { "cost": [ @@ -9367,7 +11762,9 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-08-03" }, "qwen3.8-max-preview": { "cost": [ @@ -9377,6 +11774,8 @@ 0.0 ], "limit": 1000000, + "max_output": 131072, + "released": "2026-07-19", "status": "deprecated" }, "wan2.7-image": { @@ -9386,7 +11785,9 @@ 0.0, 0.0 ], - "limit": 8192 + "limit": 8192, + "released": "2026-05-29", + "type": "image" }, "wan2.7-image-pro": { "cost": [ @@ -9395,7 +11796,9 @@ 0.0, 0.0 ], - "limit": 8192 + "limit": 8192, + "released": "2026-05-29", + "type": "image" } }, "name": "Alibaba Token Plan" @@ -9409,7 +11812,10 @@ 0.0, 0.0 ], - "limit": 196608 + "limit": 196608, + "max_output": 32768, + "open": true, + "released": "2026-02-12" }, "deepseek-v3.2": { "cost": [ @@ -9418,7 +11824,11 @@ 0.0, 0.0 ], + "knowledge": "2025-01", "limit": 131072, + "max_output": 65536, + "open": true, + "released": "2025-12-03", "status": "deprecated" }, "deepseek-v4-flash": { @@ -9428,7 +11838,11 @@ 0.0, 0.0 ], + "knowledge": "2025-05", "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24", "status": "deprecated" }, "deepseek-v4-flash-0731": { @@ -9438,7 +11852,11 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-07-31" }, "deepseek-v4-pro": { "cost": [ @@ -9447,7 +11865,11 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "deepseek-v4-pro-0813": { "cost": [ @@ -9456,7 +11878,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-08-13" }, "deepseek-v4.1-flash": { "cost": [ @@ -9465,7 +11890,11 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-09-10" }, "deepseek-v4.1-flash-1017": { "cost": [ @@ -9474,7 +11903,11 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-10-17" }, "glm-5": { "cost": [ @@ -9483,7 +11916,9 @@ 0.0, 0.0 ], - "limit": 202752 + "limit": 202752, + "max_output": 16384, + "released": "2026-02-12" }, "glm-5.1": { "cost": [ @@ -9492,7 +11927,10 @@ 0.0, 0.0 ], - "limit": 202752 + "limit": 202752, + "max_output": 128000, + "open": true, + "released": "2026-04-07" }, "glm-5.2": { "cost": [ @@ -9501,7 +11939,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "glm-5.3": { "cost": [ @@ -9510,7 +11951,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "happyhorse-1.1-i2v": { "cost": [ @@ -9518,7 +11962,9 @@ 0.0, 0.0, 0.0 - ] + ], + "released": "2026-07-17", + "type": "video" }, "happyhorse-1.1-r2v": { "cost": [ @@ -9526,7 +11972,9 @@ 0.0, 0.0, 0.0 - ] + ], + "released": "2026-07-17", + "type": "video" }, "happyhorse-1.1-t2v": { "cost": [ @@ -9534,7 +11982,9 @@ 0.0, 0.0, 0.0 - ] + ], + "released": "2026-07-17", + "type": "video" }, "kimi-k2.5": { "cost": [ @@ -9543,7 +11993,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 98304, + "open": true, + "released": "2026-01-27" }, "kimi-k2.6": { "cost": [ @@ -9552,7 +12006,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-20" }, "kimi-k2.7-code": { "cost": [ @@ -9561,7 +12019,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-06-12" }, "qwen-image-2.0": { "cost": [ @@ -9570,7 +12032,9 @@ 0.0, 0.0 ], - "limit": 8192 + "limit": 8192, + "released": "2026-03-03", + "type": "image" }, "qwen-image-2.0-pro": { "cost": [ @@ -9579,7 +12043,9 @@ 0.0, 0.0 ], - "limit": 8192 + "limit": 8192, + "released": "2026-03-03", + "type": "image" }, "qwen3.6-flash": { "cost": [ @@ -9588,7 +12054,9 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 65536, + "released": "2026-04-27" }, "qwen3.6-plus": { "cost": [ @@ -9597,7 +12065,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-04", + "limit": 1000000, + "max_output": 65536, + "released": "2026-04-02" }, "qwen3.7-max": { "cost": [ @@ -9606,7 +12077,9 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-05-21" }, "qwen3.7-plus": { "cost": [ @@ -9615,7 +12088,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-04", + "limit": 1000000, + "max_output": 65536, + "released": "2026-06-02" }, "qwen3.8-flash": { "cost": [ @@ -9624,7 +12100,9 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-08-26" }, "qwen3.8-max": { "cost": [ @@ -9633,7 +12111,9 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-08-03" }, "qwen3.8-max-preview": { "cost": [ @@ -9643,6 +12123,8 @@ 0.0 ], "limit": 1000000, + "max_output": 131072, + "released": "2026-07-19", "status": "deprecated" }, "wan2.7-image": { @@ -9652,7 +12134,9 @@ 0.0, 0.0 ], - "limit": 8192 + "limit": 8192, + "released": "2026-05-29", + "type": "image" }, "wan2.7-image-pro": { "cost": [ @@ -9661,7 +12145,9 @@ 0.0, 0.0 ], - "limit": 8192 + "limit": 8192, + "released": "2026-05-29", + "type": "image" } }, "name": "Alibaba Token Plan (China)" @@ -9675,7 +12161,10 @@ 0.0825, 0.33 ], - "limit": 1000000 + "knowledge": "2025-10", + "limit": 1000000, + "max_output": 65535, + "released": "2025-12-02" }, "amazon.nova-lite-v1:0": { "cost": [ @@ -9684,7 +12173,10 @@ 0.015, 0.06 ], - "limit": 300000 + "knowledge": "2024-10", + "limit": 300000, + "max_output": 10000, + "released": "2024-12-03" }, "amazon.nova-micro-v1:0": { "cost": [ @@ -9693,7 +12185,10 @@ 0.00875, 0.035 ], - "limit": 128000 + "knowledge": "2024-10", + "limit": 128000, + "max_output": 10000, + "released": "2024-12-03" }, "amazon.nova-pro-v1:0": { "cost": [ @@ -9702,7 +12197,10 @@ 0.2, 0.8 ], - "limit": 300000 + "knowledge": "2024-10", + "limit": 300000, + "max_output": 10000, + "released": "2024-12-03" }, "anthropic.claude-fable-5": { "cost": [ @@ -9711,7 +12209,10 @@ 1.0, 12.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-09" }, "anthropic.claude-fable-5-1": { "cost": [ @@ -9720,7 +12221,10 @@ 0.25, 12.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-01" }, "anthropic.claude-haiku-4-5-20251001-v1:0": { "cost": [ @@ -9729,7 +12233,10 @@ 0.1, 1.25 ], - "limit": 200000 + "knowledge": "2025-02-28", + "limit": 200000, + "max_output": 64000, + "released": "2025-10-15" }, "anthropic.claude-haiku-5-5": { "cost": [ @@ -9738,7 +12245,10 @@ 0.01, 0.125 ], + "knowledge": "2026-06", "limit": 1000000, + "max_output": 128000, + "released": "2026-10-07", "tiers": [ { "cost": [ @@ -9761,7 +12271,10 @@ 1.5, 18.75 ], + "knowledge": "2025-03-31", "limit": 200000, + "max_output": 32000, + "released": "2025-08-05", "status": "deprecated" }, "anthropic.claude-opus-4-5-20251101-v1:0": { @@ -9771,7 +12284,10 @@ 0.5, 6.25 ], - "limit": 200000 + "knowledge": "2025-05", + "limit": 200000, + "max_output": 64000, + "released": "2025-11-24" }, "anthropic.claude-opus-4-6-v1": { "cost": [ @@ -9780,7 +12296,10 @@ 0.55, 6.875 ], - "limit": 1000000 + "knowledge": "2025-05-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-05" }, "anthropic.claude-opus-4-7": { "cost": [ @@ -9789,7 +12308,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-16" }, "anthropic.claude-opus-4-8": { "cost": [ @@ -9798,7 +12320,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-28" }, "anthropic.claude-opus-5": { "cost": [ @@ -9807,7 +12332,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-05", + "limit": 1000000, + "max_output": 128000, + "released": "2026-07-24" }, "anthropic.claude-opus-5-5": { "cost": [ @@ -9816,7 +12344,10 @@ 0.2, 5.0 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-22" }, "anthropic.claude-sonnet-4-5-20250929-v1:0": { "cost": [ @@ -9825,7 +12356,10 @@ 0.3, 3.75 ], + "knowledge": "2025-07-31", "limit": 200000, + "max_output": 64000, + "released": "2025-09-29", "status": "deprecated" }, "anthropic.claude-sonnet-4-6": { @@ -9835,7 +12369,10 @@ 0.33, 4.125 ], - "limit": 1000000 + "knowledge": "2025-08-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-17" }, "anthropic.claude-sonnet-5": { "cost": [ @@ -9844,7 +12381,10 @@ 0.2, 2.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-30" }, "anthropic.claude-sonnet-5-5": { "cost": [ @@ -9853,7 +12393,10 @@ 0.1, 2.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-28" }, "apac.amazon.nova-lite-v1:0": { "cost": [ @@ -9862,7 +12405,10 @@ 0.01575, 0.063 ], - "limit": 300000 + "knowledge": "2024-10", + "limit": 300000, + "max_output": 10000, + "released": "2024-12-03" }, "apac.amazon.nova-micro-v1:0": { "cost": [ @@ -9871,7 +12417,10 @@ 0.00925, 0.037 ], - "limit": 128000 + "knowledge": "2024-10", + "limit": 128000, + "max_output": 10000, + "released": "2024-12-03" }, "apac.amazon.nova-pro-v1:0": { "cost": [ @@ -9880,7 +12429,10 @@ 0.21, 0.84 ], - "limit": 300000 + "knowledge": "2024-10", + "limit": 300000, + "max_output": 10000, + "released": "2024-12-03" }, "apac.anthropic.claude-sonnet-4-20250514-v1:0": { "cost": [ @@ -9889,7 +12441,10 @@ 0.3, 3.75 ], + "knowledge": "2025-03-31", "limit": 200000, + "max_output": 64000, + "released": "2025-05-22", "status": "deprecated" }, "au.anthropic.claude-haiku-4-5-20251001-v1:0": { @@ -9899,7 +12454,10 @@ 0.11, 1.375 ], - "limit": 200000 + "knowledge": "2025-02-28", + "limit": 200000, + "max_output": 64000, + "released": "2025-10-15" }, "au.anthropic.claude-haiku-5-5": { "cost": [ @@ -9908,7 +12466,10 @@ 0.011, 0.1375 ], + "knowledge": "2026-06", "limit": 1000000, + "max_output": 128000, + "released": "2026-10-07", "tiers": [ { "cost": [ @@ -9931,7 +12492,10 @@ 0.55, 6.875 ], - "limit": 1000000 + "knowledge": "2025-05-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-05" }, "au.anthropic.claude-opus-4-7": { "cost": [ @@ -9940,7 +12504,10 @@ 0.55, 6.875 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-16" }, "au.anthropic.claude-opus-4-8": { "cost": [ @@ -9949,7 +12516,10 @@ 0.55, 6.875 ], - "limit": 1000000 + "knowledge": "2026-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-28" }, "au.anthropic.claude-opus-5": { "cost": [ @@ -9958,7 +12528,10 @@ 0.55, 6.875 ], - "limit": 1000000 + "knowledge": "2026-05", + "limit": 1000000, + "max_output": 128000, + "released": "2026-07-24" }, "au.anthropic.claude-opus-5-5": { "cost": [ @@ -9967,7 +12540,10 @@ 0.22, 5.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-22" }, "au.anthropic.claude-sonnet-4-5-20250929-v1:0": { "cost": [ @@ -9976,7 +12552,10 @@ 0.33, 4.125 ], + "knowledge": "2025-07-31", "limit": 200000, + "max_output": 64000, + "released": "2025-09-29", "status": "deprecated" }, "au.anthropic.claude-sonnet-4-6": { @@ -9986,7 +12565,10 @@ 0.33, 4.125 ], - "limit": 1000000 + "knowledge": "2025-08-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-17" }, "au.anthropic.claude-sonnet-5": { "cost": [ @@ -9995,7 +12577,22 @@ 0.22, 2.75 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-30" + }, + "au.anthropic.claude-sonnet-5-5": { + "cost": [ + 2.2, + 11.0, + 0.11, + 2.75 + ], + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-28" }, "ca.amazon.nova-lite-v1:0": { "cost": [ @@ -10004,7 +12601,10 @@ 0.016, 0.064 ], - "limit": 300000 + "knowledge": "2024-10", + "limit": 300000, + "max_output": 10000, + "released": "2024-12-03" }, "deepseek.r1-v1:0": { "cost": [ @@ -10013,7 +12613,11 @@ 0.0, 0.0 ], + "knowledge": "2024-07", "limit": 128000, + "max_output": 32768, + "open": true, + "released": "2025-01-20", "status": "deprecated" }, "deepseek.v3-v1:0": { @@ -10024,6 +12628,9 @@ 0.0 ], "limit": 163840, + "max_output": 81920, + "open": true, + "released": "2025-08-21", "status": "deprecated" }, "deepseek.v3.2": { @@ -10033,7 +12640,11 @@ 0.0, 0.0 ], - "limit": 163840 + "knowledge": "2024-07", + "limit": 163840, + "max_output": 81920, + "open": true, + "released": "2025-12-01" }, "eu.amazon.nova-2-lite-v1:0": { "cost": [ @@ -10042,7 +12653,10 @@ 0.0935, 0.374 ], - "limit": 1000000 + "knowledge": "2025-10", + "limit": 1000000, + "max_output": 65535, + "released": "2025-12-02" }, "eu.amazon.nova-lite-v1:0": { "cost": [ @@ -10051,7 +12665,10 @@ 0.01725, 0.069 ], - "limit": 300000 + "knowledge": "2024-10", + "limit": 300000, + "max_output": 10000, + "released": "2024-12-03" }, "eu.amazon.nova-micro-v1:0": { "cost": [ @@ -10060,7 +12677,10 @@ 0.01, 0.04 ], - "limit": 128000 + "knowledge": "2024-10", + "limit": 128000, + "max_output": 10000, + "released": "2024-12-03" }, "eu.amazon.nova-pro-v1:0": { "cost": [ @@ -10069,7 +12689,10 @@ 0.23, 0.92 ], - "limit": 300000 + "knowledge": "2024-10", + "limit": 300000, + "max_output": 10000, + "released": "2024-12-03" }, "eu.anthropic.claude-fable-5": { "cost": [ @@ -10078,7 +12701,10 @@ 1.1, 13.75 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-09" }, "eu.anthropic.claude-haiku-4-5-20251001-v1:0": { "cost": [ @@ -10087,7 +12713,10 @@ 0.11, 1.375 ], - "limit": 200000 + "knowledge": "2025-02-28", + "limit": 200000, + "max_output": 64000, + "released": "2025-10-15" }, "eu.anthropic.claude-haiku-5-5": { "cost": [ @@ -10096,7 +12725,10 @@ 0.011, 0.1375 ], + "knowledge": "2026-06", "limit": 1000000, + "max_output": 128000, + "released": "2026-10-07", "tiers": [ { "cost": [ @@ -10119,7 +12751,10 @@ 0.55, 6.875 ], - "limit": 200000 + "knowledge": "2025-05", + "limit": 200000, + "max_output": 64000, + "released": "2025-11-24" }, "eu.anthropic.claude-opus-4-6-v1": { "cost": [ @@ -10128,7 +12763,10 @@ 0.55, 6.875 ], - "limit": 1000000 + "knowledge": "2025-05-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-05" }, "eu.anthropic.claude-opus-4-7": { "cost": [ @@ -10137,7 +12775,10 @@ 0.55, 6.875 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-16" }, "eu.anthropic.claude-opus-4-8": { "cost": [ @@ -10146,7 +12787,10 @@ 0.55, 6.875 ], - "limit": 1000000 + "knowledge": "2026-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-28" }, "eu.anthropic.claude-opus-5": { "cost": [ @@ -10155,7 +12799,10 @@ 0.55, 6.875 ], - "limit": 1000000 + "knowledge": "2026-05", + "limit": 1000000, + "max_output": 128000, + "released": "2026-07-24" }, "eu.anthropic.claude-opus-5-5": { "cost": [ @@ -10164,7 +12811,10 @@ 0.22, 5.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-22" }, "eu.anthropic.claude-sonnet-4-20250514-v1:0": { "cost": [ @@ -10173,7 +12823,10 @@ 0.3, 3.75 ], + "knowledge": "2025-03-31", "limit": 200000, + "max_output": 64000, + "released": "2025-05-22", "status": "deprecated" }, "eu.anthropic.claude-sonnet-4-5-20250929-v1:0": { @@ -10183,7 +12836,10 @@ 0.33, 4.125 ], + "knowledge": "2025-07-31", "limit": 200000, + "max_output": 64000, + "released": "2025-09-29", "status": "deprecated" }, "eu.anthropic.claude-sonnet-4-6": { @@ -10193,7 +12849,10 @@ 0.33, 4.125 ], - "limit": 1000000 + "knowledge": "2025-08-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-17" }, "eu.anthropic.claude-sonnet-5": { "cost": [ @@ -10202,7 +12861,10 @@ 0.22, 2.75 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-30" }, "eu.anthropic.claude-sonnet-5-5": { "cost": [ @@ -10211,7 +12873,10 @@ 0.11, 2.75 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-28" }, "eu.mistral.pixtral-large-2502-v1:0": { "cost": [ @@ -10220,7 +12885,9 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 8192, + "released": "2025-04-08" }, "global.amazon.nova-2-lite-v1:0": { "cost": [ @@ -10229,7 +12896,10 @@ 0.075, 0.3 ], - "limit": 1000000 + "knowledge": "2025-10", + "limit": 1000000, + "max_output": 65535, + "released": "2025-12-02" }, "global.anthropic.claude-fable-5": { "cost": [ @@ -10238,7 +12908,10 @@ 1.0, 12.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-09" }, "global.anthropic.claude-fable-5-1": { "cost": [ @@ -10247,7 +12920,10 @@ 0.25, 12.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-01" }, "global.anthropic.claude-haiku-4-5-20251001-v1:0": { "cost": [ @@ -10256,7 +12932,10 @@ 0.1, 1.25 ], - "limit": 200000 + "knowledge": "2025-02-28", + "limit": 200000, + "max_output": 64000, + "released": "2025-10-15" }, "global.anthropic.claude-haiku-5-5": { "cost": [ @@ -10265,7 +12944,10 @@ 0.01, 0.125 ], + "knowledge": "2026-06", "limit": 1000000, + "max_output": 128000, + "released": "2026-10-07", "tiers": [ { "cost": [ @@ -10288,7 +12970,10 @@ 0.5, 6.25 ], - "limit": 200000 + "knowledge": "2025-05", + "limit": 200000, + "max_output": 64000, + "released": "2025-11-24" }, "global.anthropic.claude-opus-4-6-v1": { "cost": [ @@ -10297,7 +12982,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2025-05-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-05" }, "global.anthropic.claude-opus-4-7": { "cost": [ @@ -10306,7 +12994,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-16" }, "global.anthropic.claude-opus-4-8": { "cost": [ @@ -10315,7 +13006,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-28" }, "global.anthropic.claude-opus-5": { "cost": [ @@ -10324,7 +13018,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-05", + "limit": 1000000, + "max_output": 128000, + "released": "2026-07-24" }, "global.anthropic.claude-opus-5-5": { "cost": [ @@ -10333,7 +13030,10 @@ 0.2, 5.0 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-22" }, "global.anthropic.claude-sonnet-4-20250514-v1:0": { "cost": [ @@ -10342,7 +13042,10 @@ 0.3, 3.75 ], + "knowledge": "2025-03-31", "limit": 200000, + "max_output": 64000, + "released": "2025-05-22", "status": "deprecated" }, "global.anthropic.claude-sonnet-4-5-20250929-v1:0": { @@ -10352,7 +13055,10 @@ 0.3, 3.75 ], + "knowledge": "2025-07-31", "limit": 200000, + "max_output": 64000, + "released": "2025-09-29", "status": "deprecated" }, "global.anthropic.claude-sonnet-4-6": { @@ -10362,7 +13068,10 @@ 0.3, 3.75 ], - "limit": 1000000 + "knowledge": "2025-08-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-17" }, "global.anthropic.claude-sonnet-5": { "cost": [ @@ -10371,7 +13080,10 @@ 0.2, 2.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-30" }, "global.anthropic.claude-sonnet-5-5": { "cost": [ @@ -10380,7 +13092,10 @@ 0.1, 2.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-28" }, "global.moonshotai.kimi-k3": { "cost": [ @@ -10389,7 +13104,10 @@ 0.3, 3.75 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 128000, + "open": true, + "released": "2026-07-16" }, "global.openai.gpt-5.6-luna": { "cost": [ @@ -10398,7 +13116,10 @@ 0.02, 0.25 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -10421,7 +13142,10 @@ 0.4, 5.0 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -10444,7 +13168,10 @@ 0.2, 2.5 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -10467,7 +13194,10 @@ 1.0, 12.5 ], + "knowledge": "2026-04-30", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-04", "tiers": [ { "cost": [ @@ -10490,7 +13220,10 @@ 6.0, 75.0 ], - "limit": 1050000 + "knowledge": "2026-04-30", + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-04" }, "global.openai.gpt-6-luna": { "cost": [ @@ -10499,7 +13232,10 @@ 0.01, 0.125 ], + "knowledge": "2026-05-18", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -10522,7 +13258,10 @@ 0.2, 2.5 ], + "knowledge": "2026-04-20", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -10545,7 +13284,10 @@ 0.1, 2.5 ], + "knowledge": "2026-04-30", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-29", "tiers": [ { "cost": [ @@ -10568,7 +13310,36 @@ 0.6, 15.0 ], - "limit": 1050000 + "knowledge": "2026-04-30", + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-29" + }, + "global.openai.gpt-6.1-terra": { + "cost": [ + 1.0, + 5.0, + 0.05, + 1.25 + ], + "knowledge": "2026-06-01", + "limit": 1050000, + "max_output": 128000, + "released": "2026-10-26", + "tiers": [ + { + "cost": [ + 2.0, + 7.5, + 0.1, + 2.5 + ], + "tier": { + "size": 272000, + "type": "context" + } + } + ] }, "global.xai.grok-4.6": { "cost": [ @@ -10577,7 +13348,10 @@ 0.5, 0.0 ], - "limit": 500000 + "knowledge": "2026-02-01", + "limit": 500000, + "max_output": 500000, + "released": "2026-08-12" }, "global.xai.grok-4.7": { "cost": [ @@ -10586,7 +13360,10 @@ 0.5, 0.0 ], - "limit": 500000 + "knowledge": "2026-05", + "limit": 500000, + "max_output": 500000, + "released": "2026-09-21" }, "global.zai.glm-5.3": { "cost": [ @@ -10595,7 +13372,10 @@ 0.312, 2.1 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 128000, + "open": true, + "released": "2026-08-14" }, "google.gemma-3-12b-it": { "cost": [ @@ -10604,7 +13384,11 @@ 0.0, 0.0 ], + "knowledge": "2024-08", "limit": 131072, + "max_output": 8192, + "open": true, + "released": "2025-03-12", "status": "deprecated" }, "google.gemma-3-27b-it": { @@ -10614,7 +13398,11 @@ 0.0, 0.0 ], + "knowledge": "2024-08", "limit": 131072, + "max_output": 8192, + "open": true, + "released": "2025-03-12", "status": "deprecated" }, "google.gemma-3-4b-it": { @@ -10624,7 +13412,11 @@ 0.0, 0.0 ], + "knowledge": "2024-08", "limit": 131072, + "max_output": 4096, + "open": true, + "released": "2025-03-12", "status": "deprecated" }, "google.gemma-4-26b-a4b": { @@ -10634,7 +13426,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-04-02" }, "google.gemma-4-31b": { "cost": [ @@ -10643,7 +13438,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-04-02" }, "google.gemma-4-e2b": { "cost": [ @@ -10652,7 +13451,10 @@ 0.0, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 8192, + "open": true, + "released": "2026-04-02" }, "in.anthropic.claude-haiku-4-5-20251001-v1:0": { "cost": [ @@ -10661,7 +13463,10 @@ 0.11, 1.375 ], - "limit": 200000 + "knowledge": "2025-02-28", + "limit": 200000, + "max_output": 64000, + "released": "2025-10-15" }, "in.anthropic.claude-opus-5": { "cost": [ @@ -10670,7 +13475,10 @@ 0.55, 6.875 ], - "limit": 1000000 + "knowledge": "2026-05", + "limit": 1000000, + "max_output": 128000, + "released": "2026-07-24" }, "in.anthropic.claude-sonnet-5": { "cost": [ @@ -10679,7 +13487,10 @@ 0.22, 2.75 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-30" }, "in.openai.gpt-5.6-luna": { "cost": [ @@ -10688,7 +13499,10 @@ 0.022, 0.275 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -10711,7 +13525,10 @@ 0.22, 2.75 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -10734,7 +13551,10 @@ 0.099, 0.396 ], - "limit": 1000000 + "knowledge": "2025-10", + "limit": 1000000, + "max_output": 65535, + "released": "2025-12-02" }, "jp.anthropic.claude-haiku-4-5-20251001-v1:0": { "cost": [ @@ -10743,7 +13563,10 @@ 0.11, 1.375 ], - "limit": 200000 + "knowledge": "2025-02-28", + "limit": 200000, + "max_output": 64000, + "released": "2025-10-15" }, "jp.anthropic.claude-haiku-5-5": { "cost": [ @@ -10752,7 +13575,10 @@ 0.011, 0.1375 ], + "knowledge": "2026-06", "limit": 1000000, + "max_output": 128000, + "released": "2026-10-07", "tiers": [ { "cost": [ @@ -10775,7 +13601,10 @@ 0.55, 6.875 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-16" }, "jp.anthropic.claude-opus-4-8": { "cost": [ @@ -10784,7 +13613,10 @@ 0.55, 6.875 ], - "limit": 1000000 + "knowledge": "2026-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-28" }, "jp.anthropic.claude-opus-5": { "cost": [ @@ -10793,7 +13625,10 @@ 0.55, 6.875 ], - "limit": 1000000 + "knowledge": "2026-05", + "limit": 1000000, + "max_output": 128000, + "released": "2026-07-24" }, "jp.anthropic.claude-opus-5-5": { "cost": [ @@ -10802,7 +13637,10 @@ 0.22, 5.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-22" }, "jp.anthropic.claude-sonnet-4-5-20250929-v1:0": { "cost": [ @@ -10811,7 +13649,10 @@ 0.33, 4.125 ], + "knowledge": "2025-07-31", "limit": 200000, + "max_output": 64000, + "released": "2025-09-29", "status": "deprecated" }, "jp.anthropic.claude-sonnet-4-6": { @@ -10821,7 +13662,10 @@ 0.33, 4.125 ], - "limit": 1000000 + "knowledge": "2025-08-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-17" }, "jp.anthropic.claude-sonnet-5": { "cost": [ @@ -10830,7 +13674,10 @@ 0.22, 2.75 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-30" }, "meta.llama3-1-70b-instruct-v1:0": { "cost": [ @@ -10839,7 +13686,11 @@ 0.0, 0.0 ], + "knowledge": "2023-12", "limit": 128000, + "max_output": 4096, + "open": true, + "released": "2024-07-23", "status": "deprecated" }, "meta.llama3-1-8b-instruct-v1:0": { @@ -10849,7 +13700,11 @@ 0.0, 0.0 ], + "knowledge": "2023-12", "limit": 128000, + "max_output": 4096, + "open": true, + "released": "2024-07-23", "status": "deprecated" }, "meta.llama3-3-70b-instruct-v1:0": { @@ -10859,7 +13714,11 @@ 0.0, 0.0 ], + "knowledge": "2023-12", "limit": 128000, + "max_output": 4096, + "open": true, + "released": "2024-12-06", "status": "deprecated" }, "meta.llama4-maverick-17b-instruct-v1:0": { @@ -10869,7 +13728,11 @@ 0.0, 0.0 ], + "knowledge": "2024-08", "limit": 1000000, + "max_output": 8192, + "open": true, + "released": "2025-04-05", "status": "deprecated" }, "meta.llama4-scout-17b-instruct-v1:0": { @@ -10879,7 +13742,11 @@ 0.0, 0.0 ], + "knowledge": "2024-08", "limit": 10000000, + "max_output": 8192, + "open": true, + "released": "2025-04-05", "status": "deprecated" }, "minimax.minimax-m2": { @@ -10890,6 +13757,9 @@ 0.0 ], "limit": 204608, + "max_output": 128000, + "open": true, + "released": "2025-10-27", "status": "deprecated" }, "minimax.minimax-m2.1": { @@ -10900,6 +13770,9 @@ 0.0 ], "limit": 196608, + "max_output": 131072, + "open": true, + "released": "2025-12-23", "status": "deprecated" }, "minimax.minimax-m2.5": { @@ -10909,7 +13782,10 @@ 0.0, 0.0 ], - "limit": 196608 + "limit": 196608, + "max_output": 98304, + "open": true, + "released": "2026-02-12" }, "mistral.devstral-2-123b": { "cost": [ @@ -10918,7 +13794,11 @@ 0.0, 0.0 ], + "knowledge": "2025-12", "limit": 262144, + "max_output": 8192, + "open": true, + "released": "2025-12-09", "status": "deprecated" }, "mistral.magistral-small-2509": { @@ -10928,7 +13808,10 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 40000, + "open": true, + "released": "2025-09-18" }, "mistral.ministral-3-14b-instruct": { "cost": [ @@ -10937,7 +13820,10 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 4096, + "open": true, + "released": "2025-12-02" }, "mistral.ministral-3-3b-instruct": { "cost": [ @@ -10946,7 +13832,10 @@ 0.0, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 8192, + "open": true, + "released": "2025-12-02" }, "mistral.ministral-3-8b-instruct": { "cost": [ @@ -10955,7 +13844,10 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 4096, + "open": true, + "released": "2025-12-02" }, "mistral.mistral-large-3-675b-instruct": { "cost": [ @@ -10964,7 +13856,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2024-11", + "limit": 262144, + "max_output": 8192, + "open": true, + "released": "2025-12-02" }, "mistral.pixtral-large-2502-v1:0": { "cost": [ @@ -10973,7 +13869,9 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 8192, + "released": "2025-04-08" }, "mistral.voxtral-mini-3b-2507": { "cost": [ @@ -10983,6 +13881,9 @@ 0.0 ], "limit": 32768, + "max_output": 4096, + "open": true, + "released": "2025-07-15", "status": "deprecated" }, "mistral.voxtral-small-24b-2507": { @@ -10993,6 +13894,9 @@ 0.0 ], "limit": 32768, + "max_output": 8192, + "open": true, + "released": "2025-07-15", "status": "deprecated" }, "moonshot.kimi-k2-thinking": { @@ -11002,7 +13906,11 @@ 0.0, 0.0 ], + "knowledge": "2024-08", "limit": 262144, + "max_output": 16000, + "open": true, + "released": "2025-11-06", "status": "deprecated" }, "moonshotai.kimi-k2.5": { @@ -11012,7 +13920,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 16384, + "open": true, + "released": "2026-01-27" }, "nvidia.nemotron-nano-12b-v2": { "cost": [ @@ -11022,6 +13934,9 @@ 0.0 ], "limit": 131072, + "max_output": 8192, + "open": true, + "released": "2025-10-28", "status": "deprecated" }, "nvidia.nemotron-nano-3-30b": { @@ -11031,7 +13946,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-06-25", + "limit": 262144, + "max_output": 8192, + "open": true, + "released": "2025-12-15" }, "nvidia.nemotron-nano-9b-v2": { "cost": [ @@ -11040,7 +13959,11 @@ 0.0, 0.0 ], + "knowledge": "2024-09", "limit": 131072, + "max_output": 8192, + "open": true, + "released": "2025-08-18", "status": "deprecated" }, "nvidia.nemotron-super-3-120b": { @@ -11050,7 +13973,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-06", + "limit": 262144, + "max_output": 131072, + "open": true, + "released": "2026-03-11" }, "openai.gpt-5.4": { "cost": [ @@ -11059,7 +13986,10 @@ 0.275, 0.0 ], - "limit": 1000000 + "knowledge": "2025-08-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-03-05" }, "openai.gpt-5.5": { "cost": [ @@ -11068,7 +13998,10 @@ 0.55, 0.0 ], - "limit": 1000000 + "knowledge": "2025-12-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-23" }, "openai.gpt-5.6-luna": { "cost": [ @@ -11077,7 +14010,10 @@ 0.022, 0.275 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -11100,7 +14036,10 @@ 0.44, 5.5 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -11123,7 +14062,10 @@ 0.22, 2.75 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -11146,7 +14088,10 @@ 1.1, 13.75 ], + "knowledge": "2026-04-30", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-04", "tiers": [ { "cost": [ @@ -11169,7 +14114,10 @@ 6.6, 82.5 ], - "limit": 1050000 + "knowledge": "2026-04-30", + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-04" }, "openai.gpt-6-luna": { "cost": [ @@ -11178,7 +14126,10 @@ 0.011, 0.1375 ], + "knowledge": "2026-05-18", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -11201,7 +14152,10 @@ 0.22, 2.75 ], + "knowledge": "2026-04-20", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -11224,7 +14178,10 @@ 0.11, 2.75 ], + "knowledge": "2026-04-30", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-29", "tiers": [ { "cost": [ @@ -11247,7 +14204,36 @@ 0.66, 16.5 ], - "limit": 1050000 + "knowledge": "2026-04-30", + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-29" + }, + "openai.gpt-6.1-terra": { + "cost": [ + 1.1, + 5.5, + 0.055, + 1.375 + ], + "knowledge": "2026-06-01", + "limit": 1050000, + "max_output": 128000, + "released": "2026-10-26", + "tiers": [ + { + "cost": [ + 2.2, + 8.25, + 0.11, + 2.75 + ], + "tier": { + "size": 272000, + "type": "context" + } + } + ] }, "openai.gpt-oss-120b": { "cost": [ @@ -11256,7 +14242,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2025-08-05" }, "openai.gpt-oss-120b-1:0": { "cost": [ @@ -11265,7 +14255,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 128000, + "open": true, + "released": "2025-08-05" }, "openai.gpt-oss-20b": { "cost": [ @@ -11274,7 +14268,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2025-08-05" }, "openai.gpt-oss-20b-1:0": { "cost": [ @@ -11283,7 +14281,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 128000, + "open": true, + "released": "2025-08-05" }, "openai.gpt-oss-safeguard-120b": { "cost": [ @@ -11292,7 +14294,10 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 16384, + "open": true, + "released": "2025-10-29" }, "openai.gpt-oss-safeguard-20b": { "cost": [ @@ -11301,7 +14306,10 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 16384, + "open": true, + "released": "2025-10-29" }, "qwen.qwen3-235b-a22b-2507-v1:0": { "cost": [ @@ -11310,7 +14318,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 131072, + "open": true, + "released": "2025-07-21" }, "qwen.qwen3-32b-v1:0": { "cost": [ @@ -11319,7 +14330,11 @@ 0.0, 0.0 ], - "limit": 32768 + "knowledge": "2025-04", + "limit": 32768, + "max_output": 16384, + "open": true, + "released": "2025-04-28" }, "qwen.qwen3-coder-30b-a3b-v1:0": { "cost": [ @@ -11328,7 +14343,11 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 262144, + "max_output": 131072, + "open": true, + "released": "2025-07-31", "status": "deprecated" }, "qwen.qwen3-coder-480b-a35b-v1:0": { @@ -11338,7 +14357,11 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 131072, + "max_output": 65536, + "open": true, + "released": "2025-07-23", "status": "deprecated" }, "qwen.qwen3-coder-next": { @@ -11348,7 +14371,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-09", + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-03" }, "qwen.qwen3-next-80b-a3b": { "cost": [ @@ -11357,7 +14384,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-04", + "limit": 262144, + "max_output": 262000, + "open": true, + "released": "2025-09-11" }, "qwen.qwen3-vl-235b-a22b": { "cost": [ @@ -11366,7 +14397,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-03-31", + "limit": 262144, + "max_output": 262000, + "open": true, + "released": "2025-09-23" }, "us-gov.openai.gpt-oss-120b-1:0": { "cost": [ @@ -11375,7 +14410,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-06", + "limit": 128000, + "max_output": 16384, + "open": true, + "released": "2025-08-05" }, "us-gov.openai.gpt-oss-20b-1:0": { "cost": [ @@ -11384,7 +14423,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-06", + "limit": 128000, + "max_output": 16384, + "open": true, + "released": "2025-08-05" }, "us.amazon.nova-2-lite-v1:0": { "cost": [ @@ -11393,7 +14436,10 @@ 0.0825, 0.33 ], - "limit": 1000000 + "knowledge": "2025-10", + "limit": 1000000, + "max_output": 65535, + "released": "2025-12-02" }, "us.amazon.nova-lite-v1:0": { "cost": [ @@ -11402,7 +14448,10 @@ 0.015, 0.06 ], - "limit": 300000 + "knowledge": "2024-10", + "limit": 300000, + "max_output": 10000, + "released": "2024-12-03" }, "us.amazon.nova-micro-v1:0": { "cost": [ @@ -11411,7 +14460,10 @@ 0.00875, 0.035 ], - "limit": 128000 + "knowledge": "2024-10", + "limit": 128000, + "max_output": 10000, + "released": "2024-12-03" }, "us.amazon.nova-premier-v1:0": { "cost": [ @@ -11420,7 +14472,10 @@ 0.625, 2.5 ], + "knowledge": "2024-10", "limit": 1000000, + "max_output": 10000, + "released": "2025-04-30", "status": "deprecated" }, "us.amazon.nova-pro-v1:0": { @@ -11430,7 +14485,10 @@ 0.2, 0.8 ], - "limit": 300000 + "knowledge": "2024-10", + "limit": 300000, + "max_output": 10000, + "released": "2024-12-03" }, "us.anthropic.claude-fable-5": { "cost": [ @@ -11439,7 +14497,10 @@ 1.1, 13.75 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-09" }, "us.anthropic.claude-fable-5-1": { "cost": [ @@ -11448,7 +14509,10 @@ 0.275, 13.75 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-01" }, "us.anthropic.claude-haiku-4-5-20251001-v1:0": { "cost": [ @@ -11457,7 +14521,10 @@ 0.11, 1.375 ], - "limit": 200000 + "knowledge": "2025-02-28", + "limit": 200000, + "max_output": 64000, + "released": "2025-10-15" }, "us.anthropic.claude-haiku-5-5": { "cost": [ @@ -11466,7 +14533,10 @@ 0.011, 0.1375 ], + "knowledge": "2026-06", "limit": 1000000, + "max_output": 128000, + "released": "2026-10-07", "tiers": [ { "cost": [ @@ -11489,7 +14559,10 @@ 1.5, 18.75 ], + "knowledge": "2025-03-31", "limit": 200000, + "max_output": 32000, + "released": "2025-08-05", "status": "deprecated" }, "us.anthropic.claude-opus-4-5-20251101-v1:0": { @@ -11499,7 +14572,10 @@ 0.55, 6.875 ], - "limit": 200000 + "knowledge": "2025-05", + "limit": 200000, + "max_output": 64000, + "released": "2025-11-24" }, "us.anthropic.claude-opus-4-6-v1": { "cost": [ @@ -11508,7 +14584,10 @@ 0.55, 6.875 ], - "limit": 1000000 + "knowledge": "2025-05-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-05" }, "us.anthropic.claude-opus-4-7": { "cost": [ @@ -11517,7 +14596,10 @@ 0.55, 6.875 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-16" }, "us.anthropic.claude-opus-4-8": { "cost": [ @@ -11526,7 +14608,10 @@ 0.55, 6.875 ], - "limit": 1000000 + "knowledge": "2026-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-28" }, "us.anthropic.claude-opus-5": { "cost": [ @@ -11535,7 +14620,10 @@ 0.55, 6.875 ], - "limit": 1000000 + "knowledge": "2026-05", + "limit": 1000000, + "max_output": 128000, + "released": "2026-07-24" }, "us.anthropic.claude-opus-5-5": { "cost": [ @@ -11544,7 +14632,10 @@ 0.22, 5.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-22" }, "us.anthropic.claude-sonnet-4-20250514-v1:0": { "cost": [ @@ -11553,7 +14644,10 @@ 0.3, 3.75 ], + "knowledge": "2025-03-31", "limit": 200000, + "max_output": 64000, + "released": "2025-05-22", "status": "deprecated" }, "us.anthropic.claude-sonnet-4-5-20250929-v1:0": { @@ -11563,7 +14657,10 @@ 0.33, 4.125 ], + "knowledge": "2025-07-31", "limit": 200000, + "max_output": 64000, + "released": "2025-09-29", "status": "deprecated" }, "us.anthropic.claude-sonnet-4-6": { @@ -11573,7 +14670,10 @@ 0.33, 4.125 ], - "limit": 1000000 + "knowledge": "2025-08-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-17" }, "us.anthropic.claude-sonnet-5": { "cost": [ @@ -11582,7 +14682,10 @@ 0.22, 2.75 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-30" }, "us.anthropic.claude-sonnet-5-5": { "cost": [ @@ -11591,7 +14694,10 @@ 0.11, 2.75 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-28" }, "us.deepseek.r1-v1:0": { "cost": [ @@ -11600,7 +14706,11 @@ 0.0, 0.0 ], + "knowledge": "2024-07", "limit": 128000, + "max_output": 32768, + "open": true, + "released": "2025-01-20", "status": "deprecated" }, "us.meta.llama3-1-70b-instruct-v1:0": { @@ -11610,7 +14720,11 @@ 0.0, 0.0 ], + "knowledge": "2023-12", "limit": 128000, + "max_output": 4096, + "open": true, + "released": "2024-07-23", "status": "deprecated" }, "us.meta.llama3-1-8b-instruct-v1:0": { @@ -11620,7 +14734,11 @@ 0.0, 0.0 ], + "knowledge": "2023-12", "limit": 128000, + "max_output": 4096, + "open": true, + "released": "2024-07-23", "status": "deprecated" }, "us.meta.llama3-3-70b-instruct-v1:0": { @@ -11630,7 +14748,11 @@ 0.0, 0.0 ], + "knowledge": "2023-12", "limit": 128000, + "max_output": 4096, + "open": true, + "released": "2024-12-06", "status": "deprecated" }, "us.meta.llama4-maverick-17b-instruct-v1:0": { @@ -11640,7 +14762,11 @@ 0.0, 0.0 ], + "knowledge": "2024-08", "limit": 1000000, + "max_output": 8192, + "open": true, + "released": "2025-04-05", "status": "deprecated" }, "us.meta.llama4-scout-17b-instruct-v1:0": { @@ -11650,7 +14776,11 @@ 0.0, 0.0 ], + "knowledge": "2024-08", "limit": 10000000, + "max_output": 8192, + "open": true, + "released": "2025-04-05", "status": "deprecated" }, "us.mistral.pixtral-large-2502-v1:0": { @@ -11660,7 +14790,9 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 8192, + "released": "2025-04-08" }, "us.moonshotai.kimi-k3": { "cost": [ @@ -11669,7 +14801,10 @@ 0.33, 4.125 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 128000, + "open": true, + "released": "2026-07-16" }, "us.openai.gpt-5.6-luna": { "cost": [ @@ -11678,7 +14813,10 @@ 0.022, 0.275 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -11701,7 +14839,10 @@ 0.44, 5.5 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -11724,7 +14865,10 @@ 0.22, 2.75 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -11747,7 +14891,10 @@ 1.1, 13.75 ], + "knowledge": "2026-04-30", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-04", "tiers": [ { "cost": [ @@ -11770,7 +14917,10 @@ 6.6, 82.5 ], - "limit": 1050000 + "knowledge": "2026-04-30", + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-04" }, "us.openai.gpt-6-luna": { "cost": [ @@ -11779,7 +14929,10 @@ 0.011, 0.1375 ], + "knowledge": "2026-05-18", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -11802,7 +14955,10 @@ 0.22, 2.75 ], + "knowledge": "2026-04-20", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -11825,7 +14981,10 @@ 0.11, 2.75 ], + "knowledge": "2026-04-30", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-29", "tiers": [ { "cost": [ @@ -11848,7 +15007,36 @@ 0.66, 16.5 ], - "limit": 1050000 + "knowledge": "2026-04-30", + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-29" + }, + "us.openai.gpt-6.1-terra": { + "cost": [ + 1.1, + 5.5, + 0.055, + 1.375 + ], + "knowledge": "2026-06-01", + "limit": 1050000, + "max_output": 128000, + "released": "2026-10-26", + "tiers": [ + { + "cost": [ + 2.2, + 8.25, + 0.11, + 2.75 + ], + "tier": { + "size": 272000, + "type": "context" + } + } + ] }, "us.writer.palmyra-x4-v1:0": { "cost": [ @@ -11858,6 +15046,8 @@ 0.0 ], "limit": 122880, + "max_output": 8192, + "released": "2024-10-09", "status": "deprecated" }, "us.writer.palmyra-x5-v1:0": { @@ -11868,6 +15058,8 @@ 0.0 ], "limit": 1040000, + "max_output": 8192, + "released": "2025-04-28", "status": "deprecated" }, "us.xai.grok-4.6": { @@ -11877,7 +15069,10 @@ 0.55, 0.0 ], - "limit": 500000 + "knowledge": "2026-02-01", + "limit": 500000, + "max_output": 500000, + "released": "2026-08-12" }, "us.xai.grok-4.7": { "cost": [ @@ -11886,7 +15081,10 @@ 0.55, 0.0 ], - "limit": 500000 + "knowledge": "2026-05", + "limit": 500000, + "max_output": 500000, + "released": "2026-09-21" }, "us.zai.glm-5.3": { "cost": [ @@ -11895,7 +15093,10 @@ 0.3432, 2.31 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 128000, + "open": true, + "released": "2026-08-14" }, "writer.palmyra-x4-v1:0": { "cost": [ @@ -11905,6 +15106,8 @@ 0.0 ], "limit": 122880, + "max_output": 8192, + "released": "2024-10-09", "status": "deprecated" }, "writer.palmyra-x5-v1:0": { @@ -11915,6 +15118,8 @@ 0.0 ], "limit": 1040000, + "max_output": 8192, + "released": "2025-04-28", "status": "deprecated" }, "xai.grok-4.3": { @@ -11924,7 +15129,9 @@ 0.2, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-04-17" }, "xai.grok-4.6": { "cost": [ @@ -11933,7 +15140,10 @@ 0.55, 0.0 ], - "limit": 500000 + "knowledge": "2026-02-01", + "limit": 500000, + "max_output": 500000, + "released": "2026-08-12" }, "zai.glm-4.7": { "cost": [ @@ -11942,7 +15152,11 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 202752, + "max_output": 131072, + "open": true, + "released": "2025-12-22", "status": "deprecated" }, "zai.glm-4.7-flash": { @@ -11952,7 +15166,11 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 202752, + "max_output": 131072, + "open": true, + "released": "2026-01-19", "status": "deprecated" }, "zai.glm-5": { @@ -11962,7 +15180,10 @@ 0.0, 0.0 ], - "limit": 202752 + "limit": 202752, + "max_output": 131072, + "open": true, + "released": "2026-02-12" } }, "name": "Amazon Bedrock" @@ -11976,7 +15197,10 @@ 0.15, 0.0 ], - "limit": 202752 + "limit": 202752, + "max_output": 202752, + "open": true, + "released": "2026-06-13" }, "ambient/small": { "cost": [ @@ -11985,7 +15209,10 @@ 0.0, 0.0 ], - "limit": 101072 + "limit": 101072, + "max_output": 101072, + "open": true, + "released": "2026-10-13" }, "minimax/minimax-m3": { "cost": [ @@ -11994,7 +15221,10 @@ 0.05, 0.0 ], - "limit": 262144 + "limit": 131072, + "max_output": 131702, + "open": true, + "released": "2026-06-01" }, "qwen/qwen3-30b-a3b-instruct-2507": { "cost": [ @@ -12003,7 +15233,10 @@ 0.09, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-07-28" }, "qwen/qwen3.6-27b": { "cost": [ @@ -12012,7 +15245,10 @@ 0.16, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 8192, + "open": true, + "released": "2026-04-22" }, "qwen/qwen3.6-35b-a3b": { "cost": [ @@ -12021,7 +15257,10 @@ 0.15, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-17" }, "qwen/qwen3.8-27b": { "cost": [ @@ -12030,7 +15269,10 @@ 0.16, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 8192, + "open": true, + "released": "2026-08-14" }, "unsloth/qwen3.8-27b-gguf": { "cost": [ @@ -12039,7 +15281,10 @@ 0.0, 0.0 ], - "limit": 101072 + "limit": 101072, + "max_output": 101072, + "open": true, + "released": "2026-10-13" }, "z-ai/glm-5.2": { "cost": [ @@ -12048,7 +15293,10 @@ 0.15, 0.0 ], - "limit": 202752 + "limit": 202752, + "max_output": 202752, + "open": true, + "released": "2026-06-13" }, "zai-org/GLM-5.2-FP8": { "cost": [ @@ -12058,6 +15306,9 @@ 0.0 ], "limit": 202752, + "max_output": 202752, + "open": true, + "released": "2026-06-13", "status": "deprecated" } }, @@ -12072,7 +15323,11 @@ 0.0, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-07-31" }, "DeepSeek-V4-Flash-Vision-Exp": { "cost": [ @@ -12082,6 +15337,9 @@ 0.0 ], "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-08-21", "status": "deprecated" }, "DeepSeek-V4.1-Flash": { @@ -12091,7 +15349,11 @@ 0.0, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-10-17" }, "GLM-5.3-Flash": { "cost": [ @@ -12100,7 +15362,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 131072, + "open": true, + "released": "2026-08-26" }, "Gemma-4-31B-IT": { "cost": [ @@ -12109,7 +15374,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-04-02" }, "MiMo-V2.6-Flash": { "cost": [ @@ -12118,7 +15387,10 @@ 0.0, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-09-22" }, "MiniCPM-V-4.7-1B": { "cost": [ @@ -12127,7 +15399,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-10-06" }, "MiniCPM-V-4.7-35B-A3B": { "cost": [ @@ -12136,7 +15411,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-10-07" }, "MiniCPM5-2B": { "cost": [ @@ -12145,7 +15423,10 @@ 0.0, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2026-09-06" }, "Qwen3.8-27B": { "cost": [ @@ -12154,7 +15435,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-08-14" }, "Qwen3.8-Flash-Next": { "cost": [ @@ -12163,7 +15447,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 131072, + "open": true, + "released": "2026-08-27" } }, "name": "AMD" @@ -12177,7 +15464,9 @@ 1.0, 12.5 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-07" }, "claude-fable-5-1": { "cost": [ @@ -12186,7 +15475,10 @@ 0.25, 12.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-01" }, "claude-haiku-4-5": { "cost": [ @@ -12195,7 +15487,10 @@ 0.1, 1.25 ], - "limit": 200000 + "knowledge": "2025-02-28", + "limit": 200000, + "max_output": 64000, + "released": "2025-10-15" }, "claude-haiku-4-5-20251001": { "cost": [ @@ -12204,7 +15499,10 @@ 0.1, 1.25 ], - "limit": 200000 + "knowledge": "2025-02-28", + "limit": 200000, + "max_output": 64000, + "released": "2025-10-15" }, "claude-haiku-5-5": { "cost": [ @@ -12213,7 +15511,10 @@ 0.01, 0.125 ], + "knowledge": "2026-06", "limit": 1000000, + "max_output": 128000, + "released": "2026-10-07", "tiers": [ { "cost": [ @@ -12236,7 +15537,10 @@ 0.5, 6.25 ], - "limit": 200000 + "knowledge": "2025-05", + "limit": 200000, + "max_output": 64000, + "released": "2025-11-24" }, "claude-opus-4-5-20251101": { "cost": [ @@ -12245,7 +15549,10 @@ 0.5, 6.25 ], - "limit": 200000 + "knowledge": "2025-05", + "limit": 200000, + "max_output": 64000, + "released": "2025-11-24" }, "claude-opus-4-6": { "cost": [ @@ -12254,7 +15561,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2025-05-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-04" }, "claude-opus-4-7": { "cost": [ @@ -12263,7 +15573,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-14" }, "claude-opus-4-8": { "cost": [ @@ -12272,7 +15585,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-28" }, "claude-opus-4-8-fast": { "cost": [ @@ -12281,7 +15597,10 @@ 1.0, 12.5 ], - "limit": 1000000 + "knowledge": "2026-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-28" }, "claude-opus-5": { "cost": [ @@ -12290,7 +15609,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-05", + "limit": 1000000, + "max_output": 128000, + "released": "2026-07-24" }, "claude-opus-5-5": { "cost": [ @@ -12299,7 +15621,10 @@ 0.2, 5.0 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-22" }, "claude-opus-5-5-fast": { "cost": [ @@ -12308,7 +15633,10 @@ 0.4, 10.0 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-22" }, "claude-opus-5-fast": { "cost": [ @@ -12317,7 +15645,10 @@ 1.0, 12.5 ], - "limit": 1000000 + "knowledge": "2026-05", + "limit": 1000000, + "max_output": 128000, + "released": "2026-07-24" }, "claude-sonnet-4-5": { "cost": [ @@ -12326,7 +15657,10 @@ 0.3, 3.75 ], - "limit": 200000 + "knowledge": "2025-07-31", + "limit": 200000, + "max_output": 64000, + "released": "2025-09-29" }, "claude-sonnet-4-5-20250929": { "cost": [ @@ -12335,7 +15669,10 @@ 0.3, 3.75 ], - "limit": 200000 + "knowledge": "2025-07-31", + "limit": 200000, + "max_output": 64000, + "released": "2025-09-29" }, "claude-sonnet-4-6": { "cost": [ @@ -12344,7 +15681,10 @@ 0.3, 3.75 ], - "limit": 1000000 + "knowledge": "2025-08-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-17" }, "claude-sonnet-5": { "cost": [ @@ -12353,7 +15693,10 @@ 0.2, 2.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-29" }, "claude-sonnet-5-5": { "cost": [ @@ -12362,7 +15705,10 @@ 0.1, 2.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-28" } }, "name": "Anthropic" @@ -12376,7 +15722,10 @@ 3.0, 37.5 ], - "limit": 1000000 + "knowledge": "2025-05-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-05" }, "anthropic/claude-opus-4-7-fast": { "cost": [ @@ -12385,7 +15734,10 @@ 3.0, 37.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-16" }, "openai/gpt-5.4-fast": { "cost": [ @@ -12394,7 +15746,10 @@ 0.5, 0.0 ], - "limit": 1050000 + "knowledge": "2025-08-31", + "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05" } }, "name": "AnyAPI" @@ -12408,7 +15763,11 @@ 0.028, 0.0 ], + "knowledge": "2025-05", "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-07-31", "status": "beta" }, "deepseek/deepseek-v4-pro": { @@ -12418,7 +15777,11 @@ 0.2, 0.0 ], + "knowledge": "2025-05", "limit": 512000, + "max_output": 384000, + "open": true, + "released": "2026-04-24", "status": "deprecated" }, "deepseek/deepseek-v4-pro-0813": { @@ -12429,6 +15792,9 @@ 0.0 ], "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-08-13", "status": "beta" }, "deepseek/deepseek-v4.1-flash": { @@ -12438,7 +15804,11 @@ 0.007, 0.0 ], + "knowledge": "2025-05", "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-09-10", "status": "beta" }, "deepseek/deepseek-v4.1-flash-1017": { @@ -12448,7 +15818,11 @@ 0.006, 0.0 ], + "knowledge": "2025-05", "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-10-17", "status": "beta" }, "moonshotai/kimi-k3": { @@ -12459,6 +15833,9 @@ 0.0 ], "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-16", "status": "beta" }, "thinkingmachines/inkling-small": { @@ -12469,6 +15846,9 @@ 0.0 ], "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-07-30", "status": "deprecated" }, "trinity-large-thinking": { @@ -12479,6 +15859,9 @@ 0.0 ], "limit": 262144, + "max_output": 80000, + "open": true, + "released": "2026-04-01", "status": "beta" }, "zai-org/glm-5.2": { @@ -12489,6 +15872,9 @@ 0.0 ], "limit": 262144, + "max_output": 131072, + "open": true, + "released": "2026-06-13", "status": "beta" }, "zai-org/glm-5.3": { @@ -12499,6 +15885,9 @@ 0.0 ], "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-14", "status": "beta" }, "zai-org/glm-5.3-flash": { @@ -12509,6 +15898,9 @@ 0.0 ], "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-26", "status": "beta" } }, @@ -12523,7 +15915,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2023-12", + "limit": 131072, + "max_output": 4096, + "open": true, + "released": "2024-07-23" }, "Qwen3_5-9B-MLX-4bit": { "cost": [ @@ -12532,7 +15928,10 @@ 0.0, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 8192, + "open": true, + "released": "2026-02-23" }, "Qwen3_5-9B-Q4_K_M": { "cost": [ @@ -12541,7 +15940,10 @@ 0.0, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 8192, + "open": true, + "released": "2026-02-23" }, "gemma-4-E4B-it-IQ4_XS": { "cost": [ @@ -12550,7 +15952,10 @@ 0.0, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 8192, + "open": true, + "released": "2026-04-02" }, "gemma-4-E4B-it-MLX-4bit": { "cost": [ @@ -12559,7 +15964,10 @@ 0.0, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 8192, + "open": true, + "released": "2026-04-02" } }, "name": "Atomic Chat" @@ -12573,7 +15981,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2025-05-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-05" }, "claude-opus-4-7": { "cost": [ @@ -12582,7 +15993,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-16" }, "claude-opus-4-7-fast": { "cost": [ @@ -12591,7 +16005,10 @@ 3.0, 37.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-16" }, "claude-sonnet-4-6": { "cost": [ @@ -12600,7 +16017,10 @@ 0.3, 3.75 ], - "limit": 1000000 + "knowledge": "2025-08-31", + "limit": 1000000, + "max_output": 64000, + "released": "2026-02-17" }, "deepseek-v4-flash": { "cost": [ @@ -12609,7 +16029,11 @@ 0.0028, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "deepseek-v4-pro": { "cost": [ @@ -12618,7 +16042,11 @@ 0.044, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "gemini-2.5-flash": { "cost": [ @@ -12627,7 +16055,10 @@ 0.03, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2025-06-17" }, "gemini-2.5-pro": { "cost": [ @@ -12636,7 +16067,10 @@ 0.125, 0.0 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2025-06-17", "tiers": [ { "cost": [ @@ -12659,7 +16093,10 @@ 0.2, 0.0 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2026-02-19", "tiers": [ { "cost": [ @@ -12682,7 +16119,10 @@ 0.26, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 131072, + "open": true, + "released": "2026-04-07" }, "grok-4.3": { "cost": [ @@ -12692,6 +16132,8 @@ 0.0 ], "limit": 1000000, + "max_output": 30000, + "released": "2026-04-17", "tiers": [ { "cost": [ @@ -12714,7 +16156,11 @@ 0.07, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-01-27" }, "kimi-k2.6": { "cost": [ @@ -12723,7 +16169,11 @@ 0.16, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-20" }, "minimax-m2-7": { "cost": [ @@ -12732,7 +16182,10 @@ 0.06, 0.375 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-03-18" }, "minimax-m2-7-highspeed": { "cost": [ @@ -12741,7 +16194,10 @@ 0.06, 0.375 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-03-18" }, "qwen-3.6-plus": { "cost": [ @@ -12750,7 +16206,10 @@ 0.1, 0.0 ], + "knowledge": "2025-04", "limit": 1000000, + "max_output": 65536, + "released": "2026-04-02", "tiers": [ { "cost": [ @@ -12778,7 +16237,10 @@ 1.0, 12.5 ], + "knowledge": "2026-01-31", "limit": 1000000, + "max_output": 128000, + "released": "2026-06-09", "status": "beta" }, "claude-fable-5-1": { @@ -12788,7 +16250,10 @@ 0.25, 12.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-01" }, "claude-haiku-4-5": { "cost": [ @@ -12797,7 +16262,10 @@ 0.1, 1.25 ], - "limit": 200000 + "knowledge": "2025-02-28", + "limit": 200000, + "max_output": 64000, + "released": "2025-11-18" }, "claude-haiku-5-5": { "cost": [ @@ -12806,7 +16274,10 @@ 0.01, 0.125 ], + "knowledge": "2026-06", "limit": 1000000, + "max_output": 128000, + "released": "2026-10-07", "tiers": [ { "cost": [ @@ -12829,7 +16300,10 @@ 1.0, 12.5 ], + "knowledge": "2026-01-31", "limit": 1000000, + "max_output": 128000, + "released": "2026-06-09", "status": "beta" }, "claude-opus-4-5": { @@ -12839,7 +16313,10 @@ 0.5, 6.25 ], - "limit": 200000 + "knowledge": "2025-03-31", + "limit": 200000, + "max_output": 64000, + "released": "2025-11-24" }, "claude-opus-4-6": { "cost": [ @@ -12848,7 +16325,10 @@ 0.5, 6.25 ], + "knowledge": "2025-05-31", "limit": 1000000, + "max_output": 128000, + "released": "2026-02-05", "tiers": [ { "cost": [ @@ -12871,7 +16351,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-16" }, "claude-opus-4-8": { "cost": [ @@ -12880,7 +16363,10 @@ 0.5, 6.25 ], + "knowledge": "2025-12-31", "limit": 1000000, + "max_output": 128000, + "released": "2026-05-28", "tiers": [ { "cost": [ @@ -12903,7 +16389,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-05", + "limit": 1000000, + "max_output": 128000, + "released": "2026-07-24" }, "claude-opus-5-5": { "cost": [ @@ -12912,7 +16401,10 @@ 0.2, 5.0 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-22" }, "claude-sonnet-4-5": { "cost": [ @@ -12921,7 +16413,10 @@ 0.3, 3.75 ], - "limit": 200000 + "knowledge": "2025-07-31", + "limit": 200000, + "max_output": 64000, + "released": "2025-11-18" }, "claude-sonnet-4-6": { "cost": [ @@ -12930,7 +16425,10 @@ 0.3, 3.75 ], - "limit": 1000000 + "knowledge": "2025-08-31", + "limit": 1000000, + "max_output": 64000, + "released": "2026-02-17" }, "claude-sonnet-5": { "cost": [ @@ -12939,7 +16437,10 @@ 0.2, 2.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-30" }, "claude-sonnet-5-5": { "cost": [ @@ -12948,7 +16449,10 @@ 0.2, 2.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-28" }, "codestral-2501": { "cost": [ @@ -12957,7 +16461,10 @@ 0.0, 0.0 ], - "limit": 256000 + "knowledge": "2024-03", + "limit": 256000, + "max_output": 256000, + "released": "2025-01-01" }, "codex-mini": { "cost": [ @@ -12966,7 +16473,10 @@ 0.375, 0.0 ], + "knowledge": "2024-04", "limit": 200000, + "max_output": 100000, + "released": "2025-05-16", "status": "deprecated" }, "cohere-command-a": { @@ -12976,7 +16486,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06-01", + "limit": 131072, + "max_output": 8192, + "open": true, + "released": "2025-03-13" }, "cohere-embed-v-4-0": { "cost": [ @@ -12985,7 +16499,11 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 1536, + "open": true, + "released": "2025-04-15", + "type": "embedding" }, "cohere-embed-v3-english": { "cost": [ @@ -12994,7 +16512,11 @@ 0.0, 0.0 ], - "limit": 512 + "limit": 512, + "max_output": 1024, + "open": true, + "released": "2023-11-07", + "type": "embedding" }, "cohere-embed-v3-multilingual": { "cost": [ @@ -13003,7 +16525,11 @@ 0.0, 0.0 ], - "limit": 512 + "limit": 512, + "max_output": 1024, + "open": true, + "released": "2023-11-07", + "type": "embedding" }, "deepseek-v3.2": { "cost": [ @@ -13012,7 +16538,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-07", + "limit": 128000, + "max_output": 128000, + "open": true, + "released": "2025-12-01" }, "deepseek-v3.2-speciale": { "cost": [ @@ -13021,7 +16551,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-07", + "limit": 128000, + "max_output": 128000, + "open": true, + "released": "2025-12-01" }, "deepseek-v4-flash": { "cost": [ @@ -13030,7 +16564,11 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "deepseek-v4-pro": { "cost": [ @@ -13039,7 +16577,11 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "deepseek-v4.1-flash": { "cost": [ @@ -13048,7 +16590,11 @@ 0.006, 0.0 ], + "knowledge": "2025-05", "limit": 1000000, + "max_output": 128000, + "open": true, + "released": "2026-09-10", "status": "beta" }, "gpt-3.5-turbo-0125": { @@ -13058,7 +16604,10 @@ 0.0, 0.0 ], + "knowledge": "2021-08", "limit": 16384, + "max_output": 4096, + "released": "2024-01-25", "status": "deprecated" }, "gpt-3.5-turbo-1106": { @@ -13068,7 +16617,10 @@ 0.0, 0.0 ], + "knowledge": "2021-08", "limit": 16384, + "max_output": 4096, + "released": "2023-11-06", "status": "deprecated" }, "gpt-3.5-turbo-instruct": { @@ -13078,7 +16630,10 @@ 0.0, 0.0 ], + "knowledge": "2021-08", "limit": 4096, + "max_output": 4096, + "released": "2023-09-21", "status": "deprecated" }, "gpt-4-turbo": { @@ -13088,7 +16643,10 @@ 0.0, 0.0 ], + "knowledge": "2023-12", "limit": 128000, + "max_output": 4096, + "released": "2023-11-06", "status": "deprecated" }, "gpt-4-turbo-vision": { @@ -13098,7 +16656,10 @@ 0.0, 0.0 ], + "knowledge": "2023-11", "limit": 128000, + "max_output": 4096, + "released": "2023-11-06", "status": "deprecated" }, "gpt-4.1": { @@ -13108,7 +16669,10 @@ 0.5, 0.0 ], + "knowledge": "2024-04", "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14", "status": "deprecated" }, "gpt-4.1-mini": { @@ -13118,7 +16682,10 @@ 0.1, 0.0 ], + "knowledge": "2024-04", "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14", "status": "deprecated" }, "gpt-4.1-nano": { @@ -13128,7 +16695,10 @@ 0.025, 0.0 ], + "knowledge": "2024-04", "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14", "status": "deprecated" }, "gpt-4o": { @@ -13138,7 +16708,10 @@ 1.25, 0.0 ], + "knowledge": "2023-09", "limit": 128000, + "max_output": 16384, + "released": "2024-05-13", "status": "deprecated" }, "gpt-4o-mini": { @@ -13148,7 +16721,10 @@ 0.075, 0.0 ], + "knowledge": "2023-09", "limit": 128000, + "max_output": 16384, + "released": "2024-07-18", "status": "deprecated" }, "gpt-5": { @@ -13158,7 +16734,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "gpt-5-codex": { "cost": [ @@ -13167,7 +16746,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-09-15" }, "gpt-5-mini": { "cost": [ @@ -13176,7 +16758,10 @@ 0.025, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "gpt-5-nano": { "cost": [ @@ -13185,7 +16770,10 @@ 0.005, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "gpt-5-pro": { "cost": [ @@ -13194,7 +16782,10 @@ 0.0, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-10-06" }, "gpt-5.1": { "cost": [ @@ -13203,7 +16794,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-14" }, "gpt-5.1-codex": { "cost": [ @@ -13212,7 +16806,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-14" }, "gpt-5.1-codex-max": { "cost": [ @@ -13221,7 +16818,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "gpt-5.1-codex-mini": { "cost": [ @@ -13230,7 +16830,10 @@ 0.025, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-14" }, "gpt-5.1-fast": { "cost": [ @@ -13239,7 +16842,10 @@ 0.25, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-14" }, "gpt-5.2": { "cost": [ @@ -13248,7 +16854,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "gpt-5.2-codex": { "cost": [ @@ -13257,7 +16866,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-01-14" }, "gpt-5.2-fast": { "cost": [ @@ -13266,7 +16878,10 @@ 0.35, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "gpt-5.3-codex": { "cost": [ @@ -13275,7 +16890,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-02-24" }, "gpt-5.4": { "cost": [ @@ -13284,7 +16902,10 @@ 0.25, 0.0 ], + "knowledge": "2025-08-31", "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05", "tiers": [ { "cost": [ @@ -13307,7 +16928,10 @@ 0.5, 0.0 ], - "limit": 1050000 + "knowledge": "2025-08-31", + "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05" }, "gpt-5.4-mini": { "cost": [ @@ -13316,7 +16940,10 @@ 0.075, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "gpt-5.4-mini-fast": { "cost": [ @@ -13325,7 +16952,10 @@ 0.15, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "gpt-5.4-nano": { "cost": [ @@ -13334,7 +16964,10 @@ 0.02, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "gpt-5.4-pro": { "cost": [ @@ -13343,7 +16976,10 @@ 0.0, 0.0 ], + "knowledge": "2025-08-31", "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05", "tiers": [ { "cost": [ @@ -13366,7 +17002,10 @@ 0.5, 0.0 ], + "knowledge": "2025-12-01", "limit": 1050000, + "max_output": 128000, + "released": "2026-04-24", "tiers": [ { "cost": [ @@ -13389,7 +17028,10 @@ 1.25, 0.0 ], - "limit": 1050000 + "knowledge": "2025-12-01", + "limit": 1050000, + "max_output": 128000, + "released": "2026-04-24" }, "gpt-5.6-luna": { "cost": [ @@ -13398,7 +17040,10 @@ 0.02, 0.25 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -13421,7 +17066,10 @@ 0.4, 5.0 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -13444,7 +17092,10 @@ 0.8, 10.0 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "gpt-5.6-terra": { "cost": [ @@ -13453,7 +17104,10 @@ 0.2, 2.5 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -13476,7 +17130,10 @@ 0.4, 5.0 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "gpt-6-astra": { "cost": [ @@ -13485,7 +17142,10 @@ 1.0, 12.5 ], + "knowledge": "2026-04-30", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-04", "tiers": [ { "cost": [ @@ -13508,7 +17168,10 @@ 0.01, 0.125 ], + "knowledge": "2026-05-18", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -13531,7 +17194,10 @@ 0.2, 2.5 ], + "knowledge": "2026-04-20", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -13554,7 +17220,10 @@ 0.1, 2.5 ], + "knowledge": "2026-04-30", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-29", "tiers": [ { "cost": [ @@ -13570,6 +17239,32 @@ } ] }, + "gpt-6.1-terra": { + "cost": [ + 1.0, + 5.0, + 0.05, + 1.25 + ], + "knowledge": "2026-06-01", + "limit": 1050000, + "max_output": 128000, + "released": "2026-10-26", + "tiers": [ + { + "cost": [ + 2.0, + 7.5, + 0.1, + 2.5 + ], + "tier": { + "size": 272000, + "type": "context" + } + } + ] + }, "gpt-chat-latest": { "cost": [ 5.0, @@ -13577,7 +17272,10 @@ 0.5, 0.0 ], + "knowledge": "2025-12-01", "limit": 400000, + "max_output": 128000, + "released": "2026-05-05", "status": "beta" }, "gpt-image-1": { @@ -13586,7 +17284,9 @@ 40.0, 1.25, 0.0 - ] + ], + "released": "2025-04-24", + "type": "image" }, "gpt-image-1.5": { "cost": [ @@ -13594,7 +17294,9 @@ 32.0, 1.25, 0.0 - ] + ], + "released": "2025-11-25", + "type": "image" }, "gpt-image-2": { "cost": [ @@ -13602,7 +17304,9 @@ 30.0, 1.25, 0.0 - ] + ], + "released": "2026-04-21", + "type": "image" }, "gpt-image-2.5-flare": { "cost": [ @@ -13610,7 +17314,9 @@ 30.0, 1.25, 0.0 - ] + ], + "released": "2026-09-08", + "type": "image" }, "gpt-image-2.5-sunburst": { "cost": [ @@ -13618,7 +17324,9 @@ 30.0, 1.25, 0.0 - ] + ], + "released": "2026-09-08", + "type": "image" }, "grok-4-1-fast-non-reasoning": { "cost": [ @@ -13627,7 +17335,9 @@ 0.05, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 8192, + "released": "2025-06-27" }, "grok-4-1-fast-reasoning": { "cost": [ @@ -13636,7 +17346,9 @@ 0.05, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 8192, + "released": "2025-06-27" }, "grok-4-20-non-reasoning": { "cost": [ @@ -13645,7 +17357,10 @@ 0.0, 0.0 ], + "knowledge": "2025-09", "limit": 262000, + "max_output": 8192, + "released": "2026-04-08", "status": "beta" }, "grok-4-20-reasoning": { @@ -13655,7 +17370,10 @@ 0.0, 0.0 ], + "knowledge": "2025-09", "limit": 262000, + "max_output": 8192, + "released": "2026-04-08", "status": "beta" }, "grok-4.6": { @@ -13665,7 +17383,10 @@ 0.5, 0.0 ], + "knowledge": "2026-02-01", "limit": 200000, + "max_output": 128000, + "released": "2026-08-12", "status": "beta" }, "kimi-k2.5": { @@ -13675,7 +17396,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-01-27" }, "kimi-k2.6": { "cost": [ @@ -13684,7 +17409,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-20" }, "kimi-k2.7-code": { "cost": [ @@ -13693,7 +17422,11 @@ 0.19, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-06-12" }, "llama-3.3-70b-instruct": { "cost": [ @@ -13702,7 +17435,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2023-12", + "limit": 128000, + "max_output": 32768, + "open": true, + "released": "2024-12-06" }, "llama-4-maverick-17b-128e-instruct-fp8": { "cost": [ @@ -13711,7 +17448,11 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2024-08", + "limit": 1000000, + "max_output": 16384, + "open": true, + "released": "2025-04-05" }, "llama-4-scout-17b-16e-instruct": { "cost": [ @@ -13720,7 +17461,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-08", + "limit": 128000, + "max_output": 8192, + "open": true, + "released": "2025-04-05" }, "ministral-3b": { "cost": [ @@ -13729,7 +17474,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-03", + "limit": 128000, + "max_output": 8192, + "open": true, + "released": "2024-10-22" }, "mistral-medium-2505": { "cost": [ @@ -13738,7 +17487,10 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2025-05", + "limit": 128000, + "max_output": 128000, + "released": "2025-05-07" }, "mistral-small-2503": { "cost": [ @@ -13747,7 +17499,10 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-09", + "limit": 128000, + "max_output": 32768, + "released": "2025-03-01" }, "model-router": { "cost": [ @@ -13756,7 +17511,9 @@ 0.0, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 16384, + "released": "2025-05-19" }, "o1": { "cost": [ @@ -13765,7 +17522,10 @@ 7.5, 0.0 ], + "knowledge": "2023-09", "limit": 200000, + "max_output": 100000, + "released": "2024-12-05", "status": "deprecated" }, "o3": { @@ -13775,7 +17535,10 @@ 0.5, 0.0 ], - "limit": 200000 + "knowledge": "2024-05", + "limit": 200000, + "max_output": 100000, + "released": "2025-04-16" }, "o3-mini": { "cost": [ @@ -13784,7 +17547,10 @@ 0.55, 0.0 ], + "knowledge": "2024-05", "limit": 200000, + "max_output": 100000, + "released": "2024-12-20", "status": "deprecated" }, "o4-mini": { @@ -13794,7 +17560,10 @@ 0.275, 0.0 ], + "knowledge": "2024-05", "limit": 200000, + "max_output": 100000, + "released": "2025-04-16", "status": "deprecated" }, "phi-4": { @@ -13804,7 +17573,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2023-10", + "limit": 128000, + "max_output": 4096, + "open": true, + "released": "2024-12-11" }, "phi-4-mini": { "cost": [ @@ -13813,7 +17586,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2023-10", + "limit": 128000, + "max_output": 4096, + "open": true, + "released": "2024-12-11" }, "phi-4-mini-reasoning": { "cost": [ @@ -13822,7 +17599,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2023-10", + "limit": 128000, + "max_output": 4096, + "open": true, + "released": "2024-12-11" }, "phi-4-multimodal": { "cost": [ @@ -13831,7 +17612,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2023-10", + "limit": 128000, + "max_output": 4096, + "open": true, + "released": "2024-12-11" }, "phi-4-reasoning": { "cost": [ @@ -13840,7 +17625,11 @@ 0.0, 0.0 ], - "limit": 32000 + "knowledge": "2023-10", + "limit": 32000, + "max_output": 4096, + "open": true, + "released": "2024-12-11" }, "phi-4-reasoning-plus": { "cost": [ @@ -13849,7 +17638,11 @@ 0.0, 0.0 ], - "limit": 32000 + "knowledge": "2023-10", + "limit": 32000, + "max_output": 4096, + "open": true, + "released": "2024-12-11" }, "text-embedding-3-large": { "cost": [ @@ -13858,7 +17651,10 @@ 0.0, 0.0 ], - "limit": 8192 + "limit": 8192, + "max_output": 3072, + "released": "2024-01-25", + "type": "embedding" }, "text-embedding-3-small": { "cost": [ @@ -13867,7 +17663,10 @@ 0.0, 0.0 ], - "limit": 8192 + "limit": 8192, + "max_output": 1536, + "released": "2024-01-25", + "type": "embedding" }, "text-embedding-ada-002": { "cost": [ @@ -13876,7 +17675,10 @@ 0.0, 0.0 ], - "limit": 8192 + "limit": 8192, + "max_output": 1536, + "released": "2022-12-15", + "type": "embedding" } }, "name": "Azure" @@ -13890,7 +17692,10 @@ 1.0, 12.5 ], + "knowledge": "2026-01-31", "limit": 1000000, + "max_output": 128000, + "released": "2026-06-09", "status": "beta" }, "claude-fable-5-1": { @@ -13900,7 +17705,10 @@ 0.25, 12.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-01" }, "claude-haiku-4-5": { "cost": [ @@ -13909,7 +17717,10 @@ 0.1, 1.25 ], - "limit": 200000 + "knowledge": "2025-02-28", + "limit": 200000, + "max_output": 64000, + "released": "2025-11-18" }, "claude-haiku-5-5": { "cost": [ @@ -13918,7 +17729,10 @@ 0.01, 0.125 ], + "knowledge": "2026-06", "limit": 1000000, + "max_output": 128000, + "released": "2026-10-07", "tiers": [ { "cost": [ @@ -13941,7 +17755,10 @@ 1.0, 12.5 ], + "knowledge": "2026-01-31", "limit": 1000000, + "max_output": 128000, + "released": "2026-06-09", "status": "beta" }, "claude-opus-4-5": { @@ -13951,7 +17768,10 @@ 0.5, 6.25 ], - "limit": 200000 + "knowledge": "2025-03-31", + "limit": 200000, + "max_output": 64000, + "released": "2025-11-24" }, "claude-opus-4-6": { "cost": [ @@ -13960,7 +17780,10 @@ 0.5, 6.25 ], + "knowledge": "2025-05-31", "limit": 1000000, + "max_output": 128000, + "released": "2026-02-05", "tiers": [ { "cost": [ @@ -13983,7 +17806,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-16" }, "claude-opus-4-8": { "cost": [ @@ -13992,7 +17818,10 @@ 0.5, 6.25 ], + "knowledge": "2025-12-31", "limit": 1000000, + "max_output": 128000, + "released": "2026-05-28", "tiers": [ { "cost": [ @@ -14015,7 +17844,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-05", + "limit": 1000000, + "max_output": 128000, + "released": "2026-07-24" }, "claude-opus-5-5": { "cost": [ @@ -14024,7 +17856,10 @@ 0.2, 5.0 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-22" }, "claude-sonnet-4-5": { "cost": [ @@ -14033,7 +17868,10 @@ 0.3, 3.75 ], - "limit": 200000 + "knowledge": "2025-07-31", + "limit": 200000, + "max_output": 64000, + "released": "2025-11-18" }, "claude-sonnet-4-6": { "cost": [ @@ -14042,7 +17880,10 @@ 0.3, 3.75 ], - "limit": 1000000 + "knowledge": "2025-08-31", + "limit": 1000000, + "max_output": 64000, + "released": "2026-02-17" }, "claude-sonnet-5": { "cost": [ @@ -14051,7 +17892,10 @@ 0.2, 2.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-30" }, "claude-sonnet-5-5": { "cost": [ @@ -14060,7 +17904,10 @@ 0.2, 2.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-28" }, "codestral-2501": { "cost": [ @@ -14069,7 +17916,10 @@ 0.0, 0.0 ], - "limit": 256000 + "knowledge": "2024-03", + "limit": 256000, + "max_output": 256000, + "released": "2025-01-01" }, "codex-mini": { "cost": [ @@ -14078,7 +17928,10 @@ 0.375, 0.0 ], + "knowledge": "2024-04", "limit": 200000, + "max_output": 100000, + "released": "2025-05-16", "status": "deprecated" }, "cohere-command-a": { @@ -14088,7 +17941,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06-01", + "limit": 131072, + "max_output": 8192, + "open": true, + "released": "2025-03-13" }, "cohere-embed-v-4-0": { "cost": [ @@ -14097,7 +17954,11 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 1536, + "open": true, + "released": "2025-04-15", + "type": "embedding" }, "cohere-embed-v3-english": { "cost": [ @@ -14106,7 +17967,11 @@ 0.0, 0.0 ], - "limit": 512 + "limit": 512, + "max_output": 1024, + "open": true, + "released": "2023-11-07", + "type": "embedding" }, "cohere-embed-v3-multilingual": { "cost": [ @@ -14115,7 +17980,11 @@ 0.0, 0.0 ], - "limit": 512 + "limit": 512, + "max_output": 1024, + "open": true, + "released": "2023-11-07", + "type": "embedding" }, "deepseek-v3.2": { "cost": [ @@ -14124,7 +17993,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-07", + "limit": 128000, + "max_output": 128000, + "open": true, + "released": "2025-12-01" }, "deepseek-v3.2-speciale": { "cost": [ @@ -14133,7 +18006,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-07", + "limit": 128000, + "max_output": 128000, + "open": true, + "released": "2025-12-01" }, "deepseek-v4-flash": { "cost": [ @@ -14142,7 +18019,11 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "deepseek-v4-pro": { "cost": [ @@ -14151,7 +18032,11 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "deepseek-v4.1-flash": { "cost": [ @@ -14160,7 +18045,11 @@ 0.006, 0.0 ], + "knowledge": "2025-05", "limit": 1000000, + "max_output": 128000, + "open": true, + "released": "2026-09-10", "status": "beta" }, "gpt-3.5-turbo-0125": { @@ -14170,7 +18059,10 @@ 0.0, 0.0 ], + "knowledge": "2021-08", "limit": 16384, + "max_output": 4096, + "released": "2024-01-25", "status": "deprecated" }, "gpt-3.5-turbo-1106": { @@ -14180,7 +18072,10 @@ 0.0, 0.0 ], + "knowledge": "2021-08", "limit": 16384, + "max_output": 4096, + "released": "2023-11-06", "status": "deprecated" }, "gpt-3.5-turbo-instruct": { @@ -14190,7 +18085,10 @@ 0.0, 0.0 ], + "knowledge": "2021-08", "limit": 4096, + "max_output": 4096, + "released": "2023-09-21", "status": "deprecated" }, "gpt-4-turbo": { @@ -14200,7 +18098,10 @@ 0.0, 0.0 ], + "knowledge": "2023-12", "limit": 128000, + "max_output": 4096, + "released": "2023-11-06", "status": "deprecated" }, "gpt-4-turbo-vision": { @@ -14210,7 +18111,10 @@ 0.0, 0.0 ], + "knowledge": "2023-11", "limit": 128000, + "max_output": 4096, + "released": "2023-11-06", "status": "deprecated" }, "gpt-4.1": { @@ -14220,7 +18124,10 @@ 0.5, 0.0 ], + "knowledge": "2024-04", "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14", "status": "deprecated" }, "gpt-4.1-mini": { @@ -14230,7 +18137,10 @@ 0.1, 0.0 ], + "knowledge": "2024-04", "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14", "status": "deprecated" }, "gpt-4.1-nano": { @@ -14240,7 +18150,10 @@ 0.025, 0.0 ], + "knowledge": "2024-04", "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14", "status": "deprecated" }, "gpt-4o": { @@ -14250,7 +18163,10 @@ 1.25, 0.0 ], + "knowledge": "2023-09", "limit": 128000, + "max_output": 16384, + "released": "2024-05-13", "status": "deprecated" }, "gpt-4o-mini": { @@ -14260,7 +18176,10 @@ 0.075, 0.0 ], + "knowledge": "2023-09", "limit": 128000, + "max_output": 16384, + "released": "2024-07-18", "status": "deprecated" }, "gpt-5": { @@ -14270,7 +18189,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "gpt-5-codex": { "cost": [ @@ -14279,7 +18201,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-09-15" }, "gpt-5-mini": { "cost": [ @@ -14288,7 +18213,10 @@ 0.025, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "gpt-5-nano": { "cost": [ @@ -14297,7 +18225,10 @@ 0.005, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "gpt-5-pro": { "cost": [ @@ -14306,7 +18237,10 @@ 0.0, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-10-06" }, "gpt-5.1": { "cost": [ @@ -14315,7 +18249,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-14" }, "gpt-5.1-codex": { "cost": [ @@ -14324,7 +18261,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-14" }, "gpt-5.1-codex-max": { "cost": [ @@ -14333,7 +18273,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "gpt-5.1-codex-mini": { "cost": [ @@ -14342,7 +18285,10 @@ 0.025, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-14" }, "gpt-5.1-fast": { "cost": [ @@ -14351,7 +18297,10 @@ 0.25, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-14" }, "gpt-5.2": { "cost": [ @@ -14360,7 +18309,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "gpt-5.2-codex": { "cost": [ @@ -14369,7 +18321,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-01-14" }, "gpt-5.2-fast": { "cost": [ @@ -14378,7 +18333,10 @@ 0.35, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "gpt-5.3-codex": { "cost": [ @@ -14387,7 +18345,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-02-24" }, "gpt-5.4": { "cost": [ @@ -14396,7 +18357,10 @@ 0.25, 0.0 ], + "knowledge": "2025-08-31", "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05", "tiers": [ { "cost": [ @@ -14419,7 +18383,10 @@ 0.5, 0.0 ], - "limit": 1050000 + "knowledge": "2025-08-31", + "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05" }, "gpt-5.4-mini": { "cost": [ @@ -14428,7 +18395,10 @@ 0.075, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "gpt-5.4-mini-fast": { "cost": [ @@ -14437,7 +18407,10 @@ 0.15, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "gpt-5.4-nano": { "cost": [ @@ -14446,7 +18419,10 @@ 0.02, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "gpt-5.4-pro": { "cost": [ @@ -14455,7 +18431,10 @@ 0.0, 0.0 ], + "knowledge": "2025-08-31", "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05", "tiers": [ { "cost": [ @@ -14478,7 +18457,10 @@ 0.5, 0.0 ], + "knowledge": "2025-12-01", "limit": 1050000, + "max_output": 128000, + "released": "2026-04-24", "tiers": [ { "cost": [ @@ -14501,7 +18483,10 @@ 1.25, 0.0 ], - "limit": 1050000 + "knowledge": "2025-12-01", + "limit": 1050000, + "max_output": 128000, + "released": "2026-04-24" }, "gpt-5.6-luna": { "cost": [ @@ -14510,7 +18495,10 @@ 0.02, 0.25 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -14533,7 +18521,10 @@ 0.4, 5.0 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -14556,7 +18547,10 @@ 0.8, 10.0 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "gpt-5.6-terra": { "cost": [ @@ -14565,7 +18559,10 @@ 0.2, 2.5 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -14588,7 +18585,10 @@ 0.4, 5.0 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "gpt-6-astra": { "cost": [ @@ -14597,7 +18597,10 @@ 1.0, 12.5 ], + "knowledge": "2026-04-30", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-04", "tiers": [ { "cost": [ @@ -14620,7 +18623,10 @@ 0.01, 0.125 ], + "knowledge": "2026-05-18", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -14643,7 +18649,10 @@ 0.2, 2.5 ], + "knowledge": "2026-04-20", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -14666,7 +18675,10 @@ 0.1, 2.5 ], + "knowledge": "2026-04-30", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-29", "tiers": [ { "cost": [ @@ -14682,6 +18694,32 @@ } ] }, + "gpt-6.1-terra": { + "cost": [ + 1.0, + 5.0, + 0.05, + 1.25 + ], + "knowledge": "2026-06-01", + "limit": 1050000, + "max_output": 128000, + "released": "2026-10-26", + "tiers": [ + { + "cost": [ + 2.0, + 7.5, + 0.1, + 2.5 + ], + "tier": { + "size": 272000, + "type": "context" + } + } + ] + }, "gpt-chat-latest": { "cost": [ 5.0, @@ -14689,7 +18727,10 @@ 0.5, 0.0 ], + "knowledge": "2025-12-01", "limit": 400000, + "max_output": 128000, + "released": "2026-05-05", "status": "beta" }, "gpt-image-1": { @@ -14698,7 +18739,9 @@ 40.0, 1.25, 0.0 - ] + ], + "released": "2025-04-24", + "type": "image" }, "gpt-image-1.5": { "cost": [ @@ -14706,7 +18749,9 @@ 32.0, 1.25, 0.0 - ] + ], + "released": "2025-11-25", + "type": "image" }, "gpt-image-2": { "cost": [ @@ -14714,7 +18759,9 @@ 30.0, 1.25, 0.0 - ] + ], + "released": "2026-04-21", + "type": "image" }, "gpt-image-2.5-flare": { "cost": [ @@ -14722,7 +18769,9 @@ 30.0, 1.25, 0.0 - ] + ], + "released": "2026-09-08", + "type": "image" }, "gpt-image-2.5-sunburst": { "cost": [ @@ -14730,7 +18779,9 @@ 30.0, 1.25, 0.0 - ] + ], + "released": "2026-09-08", + "type": "image" }, "grok-4-1-fast-non-reasoning": { "cost": [ @@ -14739,7 +18790,9 @@ 0.05, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 8192, + "released": "2025-06-27" }, "grok-4-1-fast-reasoning": { "cost": [ @@ -14748,7 +18801,9 @@ 0.05, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 8192, + "released": "2025-06-27" }, "grok-4-20-non-reasoning": { "cost": [ @@ -14757,7 +18812,10 @@ 0.0, 0.0 ], + "knowledge": "2025-09", "limit": 262000, + "max_output": 8192, + "released": "2026-04-08", "status": "beta" }, "grok-4-20-reasoning": { @@ -14767,7 +18825,10 @@ 0.0, 0.0 ], + "knowledge": "2025-09", "limit": 262000, + "max_output": 8192, + "released": "2026-04-08", "status": "beta" }, "grok-4.6": { @@ -14777,7 +18838,10 @@ 0.5, 0.0 ], + "knowledge": "2026-02-01", "limit": 200000, + "max_output": 128000, + "released": "2026-08-12", "status": "beta" }, "kimi-k2.5": { @@ -14787,7 +18851,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-01-27" }, "kimi-k2.6": { "cost": [ @@ -14796,7 +18864,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-20" }, "kimi-k2.7-code": { "cost": [ @@ -14805,7 +18877,11 @@ 0.19, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-06-12" }, "llama-3.3-70b-instruct": { "cost": [ @@ -14814,7 +18890,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2023-12", + "limit": 128000, + "max_output": 32768, + "open": true, + "released": "2024-12-06" }, "llama-4-maverick-17b-128e-instruct-fp8": { "cost": [ @@ -14823,7 +18903,11 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2024-08", + "limit": 1000000, + "max_output": 16384, + "open": true, + "released": "2025-04-05" }, "llama-4-scout-17b-16e-instruct": { "cost": [ @@ -14832,7 +18916,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-08", + "limit": 128000, + "max_output": 8192, + "open": true, + "released": "2025-04-05" }, "ministral-3b": { "cost": [ @@ -14841,7 +18929,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-03", + "limit": 128000, + "max_output": 8192, + "open": true, + "released": "2024-10-22" }, "mistral-medium-2505": { "cost": [ @@ -14850,7 +18942,10 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2025-05", + "limit": 128000, + "max_output": 128000, + "released": "2025-05-07" }, "mistral-small-2503": { "cost": [ @@ -14859,7 +18954,10 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-09", + "limit": 128000, + "max_output": 32768, + "released": "2025-03-01" }, "model-router": { "cost": [ @@ -14868,7 +18966,9 @@ 0.0, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 16384, + "released": "2025-05-19" }, "o1": { "cost": [ @@ -14877,7 +18977,10 @@ 7.5, 0.0 ], + "knowledge": "2023-09", "limit": 200000, + "max_output": 100000, + "released": "2024-12-05", "status": "deprecated" }, "o3": { @@ -14887,7 +18990,10 @@ 0.5, 0.0 ], - "limit": 200000 + "knowledge": "2024-05", + "limit": 200000, + "max_output": 100000, + "released": "2025-04-16" }, "o3-mini": { "cost": [ @@ -14896,7 +19002,10 @@ 0.55, 0.0 ], + "knowledge": "2024-05", "limit": 200000, + "max_output": 100000, + "released": "2024-12-20", "status": "deprecated" }, "o4-mini": { @@ -14906,7 +19015,10 @@ 0.275, 0.0 ], + "knowledge": "2024-05", "limit": 200000, + "max_output": 100000, + "released": "2025-04-16", "status": "deprecated" }, "phi-4": { @@ -14916,7 +19028,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2023-10", + "limit": 128000, + "max_output": 4096, + "open": true, + "released": "2024-12-11" }, "phi-4-mini": { "cost": [ @@ -14925,7 +19041,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2023-10", + "limit": 128000, + "max_output": 4096, + "open": true, + "released": "2024-12-11" }, "phi-4-mini-reasoning": { "cost": [ @@ -14934,7 +19054,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2023-10", + "limit": 128000, + "max_output": 4096, + "open": true, + "released": "2024-12-11" }, "phi-4-multimodal": { "cost": [ @@ -14943,7 +19067,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2023-10", + "limit": 128000, + "max_output": 4096, + "open": true, + "released": "2024-12-11" }, "phi-4-reasoning": { "cost": [ @@ -14952,7 +19080,11 @@ 0.0, 0.0 ], - "limit": 32000 + "knowledge": "2023-10", + "limit": 32000, + "max_output": 4096, + "open": true, + "released": "2024-12-11" }, "phi-4-reasoning-plus": { "cost": [ @@ -14961,7 +19093,11 @@ 0.0, 0.0 ], - "limit": 32000 + "knowledge": "2023-10", + "limit": 32000, + "max_output": 4096, + "open": true, + "released": "2024-12-11" }, "text-embedding-3-large": { "cost": [ @@ -14970,7 +19106,10 @@ 0.0, 0.0 ], - "limit": 8192 + "limit": 8192, + "max_output": 3072, + "released": "2024-01-25", + "type": "embedding" }, "text-embedding-3-small": { "cost": [ @@ -14979,7 +19118,10 @@ 0.0, 0.0 ], - "limit": 8192 + "limit": 8192, + "max_output": 1536, + "released": "2024-01-25", + "type": "embedding" }, "text-embedding-ada-002": { "cost": [ @@ -14988,7 +19130,10 @@ 0.0, 0.0 ], - "limit": 8192 + "limit": 8192, + "max_output": 1536, + "released": "2022-12-15", + "type": "embedding" } }, "name": "Azure Cognitive Services" @@ -15002,7 +19147,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-06", + "limit": 128000, + "max_output": 32000, + "open": true, + "released": "2025-10" }, "Ring-1T": { "cost": [ @@ -15011,7 +19160,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-06", + "limit": 128000, + "max_output": 32000, + "open": true, + "released": "2025-10" } }, "name": "Bailing" @@ -15025,7 +19178,11 @@ 0.028, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-07-31" }, "deepseek-ai/DeepSeek-V4-Pro-0813": { "cost": [ @@ -15034,7 +19191,10 @@ 0.132, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 262144, + "open": true, + "released": "2026-08-13" }, "deepseek-ai/DeepSeek-V4.1-Flash": { "cost": [ @@ -15043,7 +19203,11 @@ 0.007, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 32768, + "open": true, + "released": "2026-09-10" }, "deepseek-ai/DeepSeek-V4.1-Flash-1017": { "cost": [ @@ -15052,7 +19216,11 @@ 0.007, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 262144, + "open": true, + "released": "2026-10-17" }, "deepseek-ai/DeepSeek-V4.1-Flash-1017-Fast": { "cost": [ @@ -15061,7 +19229,11 @@ 0.014, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 262144, + "open": true, + "released": "2026-10-17" }, "deepseek-ai/DeepSeek-V4.1-Flash-Fast": { "cost": [ @@ -15070,7 +19242,11 @@ 0.014, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 32768, + "open": true, + "released": "2026-09-10" }, "moonshotai/Kimi-K3": { "cost": [ @@ -15079,7 +19255,10 @@ 0.3, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 262144, + "open": true, + "released": "2026-07-16" }, "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B": { "cost": [ @@ -15088,7 +19267,11 @@ 0.12, 0.0 ], - "limit": 202800 + "knowledge": "2025-09", + "limit": 202800, + "max_output": 202800, + "open": true, + "released": "2026-06-04" }, "openai/gpt-oss-120b": { "cost": [ @@ -15097,7 +19280,11 @@ 0.1, 0.0 ], - "limit": 128072 + "knowledge": "2024-06", + "limit": 128072, + "max_output": 128072, + "open": true, + "released": "2025-08-05" }, "zai-org/GLM-5.2": { "cost": [ @@ -15106,7 +19293,10 @@ 0.14, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 262144, + "open": true, + "released": "2026-06-13" }, "zai-org/GLM-5.2-Fast": { "cost": [ @@ -15115,7 +19305,10 @@ 0.21, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 262144, + "open": true, + "released": "2026-06-13" }, "zai-org/GLM-5.3": { "cost": [ @@ -15124,7 +19317,10 @@ 0.14, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 262144, + "open": true, + "released": "2026-08-14" }, "zai-org/GLM-5.3-Fast": { "cost": [ @@ -15133,7 +19329,10 @@ 0.21, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 262144, + "open": true, + "released": "2026-08-14" }, "zai-org/GLM-5.3-Flash": { "cost": [ @@ -15142,7 +19341,10 @@ 0.03, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-08-26" } }, "name": "Baseten" @@ -15156,7 +19358,9 @@ 0.06, 0.72 ], - "limit": 262144 + "limit": 262144, + "max_output": 16384, + "released": "2026-07-10" }, "bee-buzz": { "cost": [ @@ -15165,7 +19369,9 @@ 0.25, 3.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 24576, + "released": "2026-07-10" }, "bee-cell": { "cost": [ @@ -15174,7 +19380,9 @@ 0.03, 0.36 ], - "limit": 131072 + "limit": 131072, + "max_output": 8192, + "released": "2026-07-10" }, "bee-comb": { "cost": [ @@ -15183,7 +19391,9 @@ 0.125, 1.5 ], - "limit": 262144 + "limit": 262144, + "max_output": 16384, + "released": "2026-07-10" }, "bee-hive": { "cost": [ @@ -15192,7 +19402,9 @@ 0.5, 6.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "released": "2026-07-10" }, "bee-swarm": { "cost": [ @@ -15201,7 +19413,9 @@ 2.5, 30.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 64000, + "released": "2026-07-10" } }, "name": "Bee by HEOSSI" @@ -15215,7 +19429,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-08-14" }, "google/gemma-4-31B-it": { "cost": [ @@ -15224,7 +19441,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2025-12", + "limit": 128000, + "max_output": 8192, + "open": true, + "released": "2026-04-02" }, "mistralai/Mistral-Small-3.2-24B-Instruct-2506": { "cost": [ @@ -15233,7 +19454,11 @@ 0.0, 0.0 ], - "limit": 32000 + "knowledge": "2025-09", + "limit": 32000, + "max_output": 8192, + "open": true, + "released": "2025-06-20" }, "moonshotai/Kimi-K3": { "cost": [ @@ -15242,7 +19467,10 @@ 1.00935, 0.0 ], - "limit": 327680 + "limit": 327680, + "max_output": 32768, + "open": true, + "released": "2026-07-16" }, "zai-org/GLM-5.2": { "cost": [ @@ -15252,6 +19480,9 @@ 0.0 ], "limit": 524288, + "max_output": 32768, + "open": true, + "released": "2026-06-13", "status": "deprecated" }, "zai-org/GLM-5.3-Flash": { @@ -15261,7 +19492,10 @@ 0.0, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 16384, + "open": true, + "released": "2026-08-26" } }, "name": "Berget.AI" @@ -15275,7 +19509,11 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-07-31" }, "deepseek-v4-pro-0813": { "cost": [ @@ -15284,7 +19522,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-08-13" }, "gemma-4-31b-it:free": { "cost": [ @@ -15293,7 +19534,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-04-02" }, "glm-5.3": { "cost": [ @@ -15302,7 +19547,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "glm-5.3-flash": { "cost": [ @@ -15311,7 +19559,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-26" }, "gpt-5.6-luna": { "cost": [ @@ -15320,7 +19571,10 @@ 0.0, 0.0 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "muse-spark-1.3-contributor": { "cost": [ @@ -15329,7 +19583,9 @@ 0.0, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 943718, + "released": "2026-09-02" }, "nemotron-3-ultra-550b-a55b:free": { "cost": [ @@ -15338,7 +19594,11 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-09", + "limit": 1000000, + "max_output": 128000, + "open": true, + "released": "2026-06-04" } }, "name": "Bothub" @@ -15352,7 +19612,10 @@ 0.25, 0.0 ], - "limit": 262144 + "knowledge": "2026-06", + "limit": 262144, + "max_output": 128000, + "released": "2026-09-01" }, "claude-opus-5": { "cost": [ @@ -15361,7 +19624,10 @@ 0.5, 0.0 ], + "knowledge": "2026-05", "limit": 262144, + "max_output": 128000, + "released": "2026-07-24", "status": "deprecated" }, "claude-opus-5.5": { @@ -15371,7 +19637,10 @@ 0.2, 0.0 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-22" }, "deepseek-v4-pro-0813": { "cost": [ @@ -15380,7 +19649,10 @@ 0.0352, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-08-13" }, "deepseek-v4.1-flash": { "cost": [ @@ -15389,7 +19661,11 @@ 0.01, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-09-10" }, "dsv4": { "cost": [ @@ -15398,7 +19674,11 @@ 0.02, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-07-31" }, "glm-5.2": { "cost": [ @@ -15408,6 +19688,9 @@ 0.0 ], "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-06-13", "status": "deprecated" }, "glm-5.3": { @@ -15417,7 +19700,10 @@ 0.14, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "glm-5.3-flash": { "cost": [ @@ -15426,7 +19712,10 @@ 0.024, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-08-26" }, "gpt-5.6-luna": { "cost": [ @@ -15435,7 +19724,10 @@ 0.02, 0.0 ], + "knowledge": "2026-02-16", "limit": 262144, + "max_output": 128000, + "released": "2026-07-09", "status": "deprecated" }, "gpt-5.6-sol": { @@ -15445,7 +19737,10 @@ 0.2, 0.0 ], + "knowledge": "2026-02-16", "limit": 262144, + "max_output": 128000, + "released": "2026-07-09", "status": "deprecated" }, "gpt-6-luna": { @@ -15455,7 +19750,10 @@ 0.01, 0.0 ], - "limit": 1050000 + "knowledge": "2026-05-18", + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22" }, "gpt-6-sol": { "cost": [ @@ -15464,7 +19762,10 @@ 0.2, 0.0 ], - "limit": 1050000 + "knowledge": "2026-04-20", + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22" }, "kimi-k3": { "cost": [ @@ -15473,7 +19774,10 @@ 0.23, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-16" }, "mimo-v2.6-flash": { "cost": [ @@ -15482,7 +19786,10 @@ 0.0028, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-09-22" }, "mimo-v2.6-pro": { "cost": [ @@ -15491,7 +19798,10 @@ 0.0036, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-09-22" }, "minimax-m3": { "cost": [ @@ -15500,7 +19810,10 @@ 0.056, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 512000, + "open": true, + "released": "2026-06-01" }, "nemotron3-super": { "cost": [ @@ -15509,7 +19822,11 @@ 0.06, 0.0 ], - "limit": 262144 + "knowledge": "2025-06", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-03-11" }, "qwen3.6": { "cost": [ @@ -15518,7 +19835,10 @@ 0.02, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-04-17" }, "qwen3.8-flash": { "cost": [ @@ -15527,7 +19847,9 @@ 0.016, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-08-26" } }, "name": "Boundless" @@ -15541,7 +19863,11 @@ 0.35, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 40960, + "open": true, + "released": "2025-08-05" }, "qwen-3.8-27b": { "cost": [ @@ -15550,40 +19876,16 @@ 0.99, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 40960, + "open": true, + "released": "2026-08-14" } }, "name": "Cerebras" }, "chutes": { "models": { - "Nemotron-3-Nano-Omni-30B-TEE": { - "cost": [ - 0.0245, - 0.0978, - 0.0024499999999999995, - 0.0 - ], - "limit": 131072 - }, - "Qwen/Qwen3-235B-A22B-Thinking-2507-TEE": { - "cost": [ - 0.2989, - 1.1957, - 0.029889999999999993, - 0.0 - ], - "limit": 262144 - }, - "Qwen/Qwen3-32B-TEE": { - "cost": [ - 0.104, - 0.416, - 0.010399999999999998, - 0.0 - ], - "limit": 40960 - }, "Qwen/Qwen3.5-397B-A17B-TEE": { "cost": [ 0.45, @@ -15591,7 +19893,10 @@ 0.04499999999999999, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-15" }, "Qwen/Qwen3.6-27B-TEE": { "cost": [ @@ -15600,7 +19905,10 @@ 0.024999999999999994, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-04-22" }, "Qwen/Qwen3.8-27B-TEE": { "cost": [ @@ -15609,7 +19917,10 @@ 0.003899999999999999, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-08-14" }, "deepseek-ai/DeepSeek-V3.2-TEE": { "cost": [ @@ -15618,7 +19929,11 @@ 0.09999999999999998, 0.0 ], - "limit": 131072 + "knowledge": "2024-07", + "limit": 131072, + "max_output": 65536, + "open": true, + "released": "2025-12-01" }, "deepseek-ai/DeepSeek-V4-Flash-0731-TEE": { "cost": [ @@ -15627,7 +19942,11 @@ 0.04399999999999999, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-31" }, "google/gemma-4-31B-turbo-TEE": { "cost": [ @@ -15636,16 +19955,24 @@ 0.011999999999999997, 0.0 ], - "limit": 131072 + "knowledge": "2025-01", + "limit": 131072, + "max_output": 65536, + "open": true, + "released": "2026-04-02" }, "moonshotai/Kimi-K2.6-TEE": { "cost": [ - 0.45, - 1.95, - 0.04499999999999999, + 0.39, + 1.8, + 0.03899999999999999, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 65535, + "open": true, + "released": "2026-04-20" }, "moonshotai/Kimi-K3-TEE": { "cost": [ @@ -15654,25 +19981,22 @@ 0.18499999999999997, 0.0 ], - "limit": 1048576 - }, - "unsloth/Mistral-Nemo-Instruct-2407-TEE": { - "cost": [ - 0.0245, - 0.0978, - 0.0024499999999999995, - 0.0 - ], - "limit": 131072 + "limit": 1048576, + "max_output": 65535, + "open": true, + "released": "2026-07-16" }, "zai-org/GLM-5.1-TEE": { "cost": [ - 0.98, - 3.08, - 0.09799999999999998, + 0.9, + 2.9, + 0.08999999999999998, 0.0 ], - "limit": 202752 + "limit": 202752, + "max_output": 65535, + "open": true, + "released": "2026-04-07" }, "zai-org/GLM-5.2-TEE": { "cost": [ @@ -15681,7 +20005,10 @@ 0.12499999999999997, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65535, + "open": true, + "released": "2026-06-13" } }, "name": "Chutes" @@ -15695,7 +20022,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-10", + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2025-12-01" }, "clarifai/main/models/mm-poly-8b": { "cost": [ @@ -15704,7 +20035,9 @@ 0.0, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 4096, + "released": "2025-06" }, "deepseek-ai/deepseek-ocr/models/DeepSeek-OCR": { "cost": [ @@ -15713,7 +20046,10 @@ 0.0, 0.0 ], - "limit": 8192 + "limit": 8192, + "max_output": 8192, + "open": true, + "released": "2025-10-20" }, "minimaxai/chat-completion/models/MiniMax-M2_5-high-throughput": { "cost": [ @@ -15722,7 +20058,10 @@ 0.0, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-02-12" }, "mistralai/completion/models/Ministral-3-14B-Reasoning-2512": { "cost": [ @@ -15731,7 +20070,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-12", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2025-12-01" }, "mistralai/completion/models/Ministral-3-3B-Reasoning-2512": { "cost": [ @@ -15740,7 +20083,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2025-12" }, "moonshotai/chat-completion/models/Kimi-K2_6": { "cost": [ @@ -15749,7 +20095,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-20" }, "openai/chat-completion/models/gpt-oss-120b-high-throughput": { "cost": [ @@ -15758,7 +20108,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 16384, + "open": true, + "released": "2025-08-05" }, "openai/chat-completion/models/gpt-oss-20b": { "cost": [ @@ -15767,7 +20121,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 16384, + "open": true, + "released": "2025-08-05" }, "qwen/qwenCoder/models/Qwen3-Coder-30B-A3B-Instruct": { "cost": [ @@ -15776,7 +20134,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-04", + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2025-07-31" }, "qwen/qwenLM/models/Qwen3-30B-A3B-Instruct-2507": { "cost": [ @@ -15785,7 +20147,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2025-07-28" }, "qwen/qwenLM/models/Qwen3-30B-A3B-Thinking-2507": { "cost": [ @@ -15794,7 +20159,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 131072, + "open": true, + "released": "2025-07-31" } }, "name": "Clarifai" @@ -15808,7 +20176,10 @@ 0.15, 0.0 ], - "limit": 256000 + "knowledge": "2026-05", + "limit": 256000, + "max_output": 64000, + "released": "2026-05-12" }, "claudius": { "cost": [ @@ -15817,7 +20188,10 @@ 0.9, 0.0 ], - "limit": 256000 + "knowledge": "2026-05", + "limit": 256000, + "max_output": 64000, + "released": "2026-05-12" } }, "name": "Claudinio" @@ -15831,7 +20205,11 @@ 0.0028, 0.0 ], + "knowledge": "2025-05", "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24", "status": "deprecated" }, "cline-pass/deepseek-v4-pro": { @@ -15841,7 +20219,11 @@ 0.022, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "cline-pass/deepseek-v4.1-flash": { "cost": [ @@ -15850,7 +20232,11 @@ 0.003, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-09-10" }, "cline-pass/glm-5.2": { "cost": [ @@ -15860,6 +20246,9 @@ 0.0 ], "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-13", "status": "deprecated" }, "cline-pass/glm-5.3": { @@ -15869,7 +20258,10 @@ 0.26, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "cline-pass/glm-5.3-flash": { "cost": [ @@ -15878,7 +20270,10 @@ 0.03, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-26" }, "cline-pass/kimi-k2.6": { "cost": [ @@ -15887,7 +20282,11 @@ 0.16, 0.0 ], + "knowledge": "2025-01", "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-20", "status": "deprecated" }, "cline-pass/kimi-k2.7-code": { @@ -15897,7 +20296,11 @@ 0.19, 0.0 ], + "knowledge": "2025-01", "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-06-12", "status": "deprecated" }, "cline-pass/kimi-k3": { @@ -15907,7 +20310,10 @@ 0.3, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-16" }, "cline-pass/mimo-v2.5": { "cost": [ @@ -15916,7 +20322,11 @@ 0.0028, 0.0 ], - "limit": 1048576 + "knowledge": "2024-12", + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-04-22" }, "cline-pass/mimo-v2.5-pro": { "cost": [ @@ -15925,7 +20335,11 @@ 0.0145, 0.0 ], - "limit": 1048576 + "knowledge": "2024-12", + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-04-22" }, "cline-pass/mimo-v2.6-flash": { "cost": [ @@ -15935,7 +20349,9 @@ 0.0 ], "limit": 1048576, - "status": "deprecated" + "max_output": 131072, + "open": true, + "released": "2026-09-22" }, "cline-pass/mimo-v2.6-pro": { "cost": [ @@ -15945,7 +20361,9 @@ 0.0 ], "limit": 1048576, - "status": "deprecated" + "max_output": 131072, + "open": true, + "released": "2026-09-22" }, "cline-pass/minimax-m3": { "cost": [ @@ -15954,7 +20372,10 @@ 0.06, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 512000, + "open": true, + "released": "2026-06-01" }, "cline-pass/muse-spark-1.3-contributor": { "cost": [ @@ -15963,7 +20384,9 @@ 0.002, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-09-02" }, "cline-pass/qwen3.7-max": { "cost": [ @@ -15972,7 +20395,9 @@ 0.5, 3.125 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-05-21" }, "cline-pass/qwen3.7-plus": { "cost": [ @@ -15981,7 +20406,10 @@ 0.04, 0.5 ], + "knowledge": "2025-04", "limit": 1000000, + "max_output": 64000, + "released": "2026-06-02", "tiers": [ { "cost": [ @@ -16004,7 +20432,9 @@ 0.25, 2.5 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-08-03" } }, "name": "ClinePass" @@ -16018,7 +20448,11 @@ 0.0, 0.0 ], - "limit": 196000 + "knowledge": "2026-01", + "limit": 196000, + "max_output": 16000, + "open": true, + "released": "2026-02-12" }, "meta-llama/Llama-3.3-70B-Instruct": { "cost": [ @@ -16027,7 +20461,11 @@ 0.0, 0.0 ], - "limit": 70000 + "knowledge": "2024-10-09", + "limit": 70000, + "max_output": 70000, + "open": true, + "released": "2024-12-06" }, "openai/gpt-oss-120b": { "cost": [ @@ -16036,7 +20474,11 @@ 0.0, 0.0 ], - "limit": 131000 + "knowledge": "2024-06", + "limit": 131000, + "max_output": 131000, + "open": true, + "released": "2025-08-05" }, "speakleash/Bielik-11B-v3.0-Instruct": { "cost": [ @@ -16045,7 +20487,11 @@ 0.0, 0.0 ], - "limit": 32000 + "knowledge": "2025-03", + "limit": 32000, + "max_output": 32000, + "open": true, + "released": "2025-03-13" }, "zai-org/GLM-5.3": { "cost": [ @@ -16054,7 +20500,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 131072, + "open": true, + "released": "2026-08-14" } }, "name": "CloudFerro Sherlock" @@ -16068,7 +20517,10 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-04", + "limit": 262144, + "max_output": 65536, + "released": "2025-09-23" }, "alibaba/qwen3.5-397b-a17b": { "cost": [ @@ -16077,7 +20529,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-15" }, "alibaba/qwen3.7-max": { "cost": [ @@ -16086,7 +20541,9 @@ 0.25, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-05-21" }, "alibaba/qwen3.7-plus": { "cost": [ @@ -16095,7 +20552,10 @@ 0.064, 0.0 ], - "limit": 1000000 + "knowledge": "2025-04", + "limit": 1000000, + "max_output": 64000, + "released": "2026-06-02" }, "alibaba/qwen3.8-max": { "cost": [ @@ -16104,7 +20564,9 @@ 0.25, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-08-03" }, "anthropic/claude-fable-5": { "cost": [ @@ -16113,7 +20575,10 @@ 1.0, 12.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-09" }, "anthropic/claude-fable-5.1": { "cost": [ @@ -16122,7 +20587,10 @@ 0.25, 12.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-01" }, "anthropic/claude-haiku-4.5": { "cost": [ @@ -16131,7 +20599,10 @@ 0.1, 1.25 ], - "limit": 200000 + "knowledge": "2025-02-28", + "limit": 200000, + "max_output": 64000, + "released": "2025-10-15" }, "anthropic/claude-haiku-5.5": { "cost": [ @@ -16140,7 +20611,10 @@ 0.01, 0.125 ], + "knowledge": "2026-06", "limit": 1000000, + "max_output": 128000, + "released": "2026-10-07", "tiers": [ { "cost": [ @@ -16163,7 +20637,10 @@ 0.5, 6.25 ], - "limit": 200000 + "knowledge": "2025-05", + "limit": 200000, + "max_output": 64000, + "released": "2025-11-24" }, "anthropic/claude-opus-4.6": { "cost": [ @@ -16172,7 +20649,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2025-05-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-05" }, "anthropic/claude-opus-4.7": { "cost": [ @@ -16181,7 +20661,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-16" }, "anthropic/claude-opus-4.8": { "cost": [ @@ -16190,7 +20673,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-28" }, "anthropic/claude-opus-5": { "cost": [ @@ -16199,7 +20685,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-05", + "limit": 1000000, + "max_output": 128000, + "released": "2026-07-24" }, "anthropic/claude-opus-5.5": { "cost": [ @@ -16208,7 +20697,10 @@ 0.2, 5.0 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-22" }, "anthropic/claude-sonnet-4.5": { "cost": [ @@ -16217,7 +20709,10 @@ 0.3, 3.75 ], - "limit": 200000 + "knowledge": "2025-07-31", + "limit": 200000, + "max_output": 64000, + "released": "2025-09-29" }, "anthropic/claude-sonnet-4.6": { "cost": [ @@ -16226,7 +20721,10 @@ 0.3, 3.75 ], - "limit": 1000000 + "knowledge": "2025-08-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-17" }, "anthropic/claude-sonnet-5": { "cost": [ @@ -16235,7 +20733,10 @@ 0.2, 2.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-30" }, "anthropic/claude-sonnet-5.5": { "cost": [ @@ -16244,7 +20745,10 @@ 0.2, 2.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-28" }, "deepseek/deepseek-v4-pro": { "cost": [ @@ -16253,7 +20757,11 @@ 0.145, 0.0 ], - "limit": 131072 + "knowledge": "2025-05", + "limit": 131072, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "fireworks/ember-1": { "cost": [ @@ -16262,7 +20770,9 @@ 0.3, 0.0 ], - "limit": 1040000 + "limit": 1040000, + "max_output": 131072, + "released": "2026-09-22" }, "google/gemini-2.5-flash": { "cost": [ @@ -16271,7 +20781,10 @@ 0.03, 0.0 ], - "limit": 1000000 + "knowledge": "2025-01", + "limit": 1000000, + "max_output": 65536, + "released": "2025-06-17" }, "google/gemini-2.5-flash-lite": { "cost": [ @@ -16280,7 +20793,10 @@ 0.01, 0.0 ], - "limit": 1000000 + "knowledge": "2025-01", + "limit": 1000000, + "max_output": 65536, + "released": "2025-06-17" }, "google/gemini-2.5-pro": { "cost": [ @@ -16289,7 +20805,10 @@ 0.125, 0.0 ], - "limit": 1000000 + "knowledge": "2025-01", + "limit": 1000000, + "max_output": 65536, + "released": "2025-06-17" }, "google/gemini-3-flash": { "cost": [ @@ -16298,7 +20817,10 @@ 0.05, 0.0 ], - "limit": 1000000 + "knowledge": "2025-01", + "limit": 1000000, + "max_output": 65536, + "released": "2025-12-17" }, "google/gemini-3.1-flash-lite": { "cost": [ @@ -16307,7 +20829,10 @@ 0.03, 0.0 ], - "limit": 1000000 + "knowledge": "2025-01", + "limit": 1000000, + "max_output": 65536, + "released": "2026-05-07" }, "google/gemini-3.1-pro": { "cost": [ @@ -16316,7 +20841,10 @@ 0.2, 0.0 ], + "knowledge": "2025-01", "limit": 1000000, + "max_output": 65536, + "released": "2026-02-19", "tiers": [ { "cost": [ @@ -16339,7 +20867,10 @@ 0.15, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-05-19" }, "google/gemini-3.5-flash-lite": { "cost": [ @@ -16348,7 +20879,10 @@ 0.03, 0.03 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-07-21" }, "google/gemini-3.6-flash": { "cost": [ @@ -16357,7 +20891,10 @@ 0.15, 1.5 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-07-21" }, "google/gemini-3.7-flash": { "cost": [ @@ -16366,7 +20903,10 @@ 0.075, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-08-13" }, "google/gemini-3.8-flash": { "cost": [ @@ -16375,7 +20915,9 @@ 0.075, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65536, + "released": "2026-09-02" }, "google/gemini-4-argon": { "cost": [ @@ -16384,7 +20926,10 @@ 0.1, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-10-13" }, "meta/muse-spark-1.1": { "cost": [ @@ -16393,7 +20938,9 @@ 0.16, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-04-08" }, "meta/muse-spark-1.2": { "cost": [ @@ -16402,7 +20949,9 @@ 0.16, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-08-05" }, "meta/muse-spark-1.3": { "cost": [ @@ -16411,7 +20960,9 @@ 0.16, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-09-02" }, "meta/muse-spark-open": { "cost": [ @@ -16420,7 +20971,11 @@ 0.15, 0.0 ], - "limit": 1040000 + "knowledge": "2026-01-04", + "limit": 1040000, + "max_output": 131072, + "open": true, + "released": "2026-10-15" }, "meta/muse-wonder-1.0": { "cost": [ @@ -16429,7 +20984,9 @@ 0.2, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-10-12" }, "minimax/m3.1-flash": { "cost": [ @@ -16438,7 +20995,9 @@ 0.015, 0.15 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 512000, + "released": "2026-10-19" }, "moonshotai/kimi-k3": { "cost": [ @@ -16447,7 +21006,10 @@ 0.3, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-16" }, "openai/gpt-4.1": { "cost": [ @@ -16456,7 +21018,10 @@ 0.5, 0.0 ], - "limit": 1047576 + "knowledge": "2024-04", + "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14" }, "openai/gpt-4.1-mini": { "cost": [ @@ -16465,7 +21030,10 @@ 0.1, 0.0 ], - "limit": 1047576 + "knowledge": "2024-04", + "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14" }, "openai/gpt-4.1-nano": { "cost": [ @@ -16474,7 +21042,10 @@ 0.025, 0.0 ], - "limit": 1000000 + "knowledge": "2024-04", + "limit": 1000000, + "max_output": 32768, + "released": "2025-04-14" }, "openai/gpt-4o": { "cost": [ @@ -16483,7 +21054,10 @@ 0.625, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-05-13" }, "openai/gpt-4o-mini": { "cost": [ @@ -16492,7 +21066,10 @@ 0.0375, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-07-18" }, "openai/gpt-5": { "cost": [ @@ -16501,7 +21078,10 @@ 0.125, 0.0 ], - "limit": 128000 + "knowledge": "2024-09-30", + "limit": 128000, + "max_output": 128000, + "released": "2025-08-07" }, "openai/gpt-5-mini": { "cost": [ @@ -16510,7 +21090,10 @@ 0.025, 0.0 ], - "limit": 128000 + "knowledge": "2024-05-30", + "limit": 128000, + "max_output": 128000, + "released": "2025-08-07" }, "openai/gpt-5-nano": { "cost": [ @@ -16519,7 +21102,10 @@ 0.005, 0.0 ], - "limit": 128000 + "knowledge": "2024-05-30", + "limit": 128000, + "max_output": 128000, + "released": "2025-08-07" }, "openai/gpt-5.1": { "cost": [ @@ -16528,7 +21114,10 @@ 0.125, 0.0 ], - "limit": 128000 + "knowledge": "2024-09-30", + "limit": 128000, + "max_output": 128000, + "released": "2025-11-13" }, "openai/gpt-5.4": { "cost": [ @@ -16537,7 +21126,10 @@ 0.25, 0.0 ], - "limit": 1000000 + "knowledge": "2025-08-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-03-05" }, "openai/gpt-5.4-mini": { "cost": [ @@ -16546,7 +21138,10 @@ 0.075, 0.0 ], - "limit": 128000 + "knowledge": "2025-08-31", + "limit": 128000, + "max_output": 128000, + "released": "2026-03-17" }, "openai/gpt-5.4-nano": { "cost": [ @@ -16555,7 +21150,10 @@ 0.02, 0.0 ], - "limit": 128000 + "knowledge": "2025-08-31", + "limit": 128000, + "max_output": 128000, + "released": "2026-03-17" }, "openai/gpt-5.4-pro": { "cost": [ @@ -16564,7 +21162,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-08-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-03-05" }, "openai/gpt-5.5": { "cost": [ @@ -16573,7 +21174,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-12-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-23" }, "openai/gpt-5.5-pro": { "cost": [ @@ -16582,7 +21186,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-12-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-23" }, "openai/gpt-5.6-luna": { "cost": [ @@ -16591,16 +21198,22 @@ 0.02, 0.25 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "openai/gpt-5.6-sol": { "cost": [ - 2.0, - 10.0, - 0.25, - 3.125 + 4.0, + 20.0, + 0.4, + 5.0 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "openai/gpt-5.6-terra": { "cost": [ @@ -16609,7 +21222,10 @@ 0.2, 2.5 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "openai/gpt-6-astra": { "cost": [ @@ -16618,7 +21234,10 @@ 1.0, 12.0 ], + "knowledge": "2026-04-30", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-04", "tiers": [ { "cost": [ @@ -16641,7 +21260,10 @@ 0.01, 0.125 ], + "knowledge": "2026-05-18", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -16664,7 +21286,10 @@ 0.2, 2.5 ], + "knowledge": "2026-04-20", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -16687,7 +21312,10 @@ 0.1, 2.5 ], + "knowledge": "2026-04-30", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-29", "tiers": [ { "cost": [ @@ -16703,6 +21331,32 @@ } ] }, + "openai/gpt-6.1-terra": { + "cost": [ + 1.0, + 5.0, + 0.05, + 1.25 + ], + "knowledge": "2026-06-01", + "limit": 1050000, + "max_output": 128000, + "released": "2026-10-26", + "tiers": [ + { + "cost": [ + 2.0, + 7.5, + 0.1, + 2.5 + ], + "tier": { + "size": 272000, + "type": "context" + } + } + ] + }, "openai/o3": { "cost": [ 2.0, @@ -16710,7 +21364,10 @@ 0.5, 0.0 ], - "limit": 200000 + "knowledge": "2024-05", + "limit": 200000, + "max_output": 100000, + "released": "2025-04-16" }, "openai/o3-mini": { "cost": [ @@ -16719,7 +21376,10 @@ 0.55, 0.0 ], - "limit": 200000 + "knowledge": "2024-05", + "limit": 200000, + "max_output": 100000, + "released": "2024-12-20" }, "openai/o4-mini": { "cost": [ @@ -16728,7 +21388,10 @@ 0.275, 0.0 ], - "limit": 200000 + "knowledge": "2024-05", + "limit": 200000, + "max_output": 100000, + "released": "2025-04-16" }, "reflection-ai/beam-1.0-501b-a23b": { "cost": [ @@ -16737,7 +21400,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2026-06-30", + "limit": 262144, + "max_output": 131072, + "open": true, + "released": "2026-10-05" }, "unbiased/pareto": { "cost": [ @@ -16746,7 +21413,9 @@ 0.25, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 131072, + "released": "2026-09-17" }, "xai/grok-4.20-0309-non-reasoning": { "cost": [ @@ -16755,7 +21424,9 @@ 0.2, 0.0 ], - "limit": 2000000 + "limit": 2000000, + "max_output": 30000, + "released": "2026-03-09" }, "xai/grok-4.20-0309-reasoning": { "cost": [ @@ -16764,7 +21435,9 @@ 0.2, 0.0 ], - "limit": 2000000 + "limit": 2000000, + "max_output": 30000, + "released": "2026-03-09" }, "xai/grok-4.3": { "cost": [ @@ -16773,7 +21446,9 @@ 0.2, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 30000, + "released": "2026-04-17" }, "xai/grok-4.5": { "cost": [ @@ -16783,6 +21458,8 @@ 0.0 ], "limit": 500000, + "max_output": 500000, + "released": "2026-07-08", "tiers": [ { "cost": [ @@ -16805,7 +21482,10 @@ 0.5, 0.0 ], + "knowledge": "2026-02-01", "limit": 500000, + "max_output": 500000, + "released": "2026-08-12", "tiers": [ { "cost": [ @@ -16828,7 +21508,10 @@ 0.5, 0.0 ], + "knowledge": "2026-05", "limit": 500000, + "max_output": 500000, + "released": "2026-09-21", "tiers": [ { "cost": [ @@ -16856,7 +21539,10 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 128000, + "open": true, + "released": "2025-09-23" }, "@cf/deepseek-ai/deepseek-r1-distill-qwen-32b": { "cost": [ @@ -16865,7 +21551,11 @@ 0.0, 0.0 ], - "limit": 80000 + "knowledge": "2024-07", + "limit": 80000, + "max_output": 80000, + "open": true, + "released": "2025-01-20" }, "@cf/deepseek-ai/deepseek-v4-flash-0731": { "cost": [ @@ -16874,7 +21564,11 @@ 0.014, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-07-31" }, "@cf/deepseek-ai/deepseek-v4-pro-0813": { "cost": [ @@ -16883,7 +21577,10 @@ 0.044, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-08-13" }, "@cf/deepseek-ai/deepseek-v4.1-flash-1017": { "cost": [ @@ -16892,7 +21589,11 @@ 0.006, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-10-17" }, "@cf/google/gemma-4-26b-a4b-it": { "cost": [ @@ -16901,7 +21602,10 @@ 0.05, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 16384, + "open": true, + "released": "2026-04-02" }, "@cf/ibm-granite/granite-4.0-h-micro": { "cost": [ @@ -16910,7 +21614,10 @@ 0.0, 0.0 ], - "limit": 131000 + "limit": 131000, + "max_output": 131000, + "open": true, + "released": "2025-10-02" }, "@cf/meta/llama-3.1-8b-instruct-fp8": { "cost": [ @@ -16919,7 +21626,11 @@ 0.0, 0.0 ], - "limit": 32000 + "knowledge": "2023-12", + "limit": 32000, + "max_output": 32000, + "open": true, + "released": "2024-07-23" }, "@cf/meta/llama-3.2-11b-vision-instruct": { "cost": [ @@ -16928,7 +21639,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2023-12", + "limit": 128000, + "max_output": 128000, + "open": true, + "released": "2024-09-25" }, "@cf/meta/llama-3.2-1b-instruct": { "cost": [ @@ -16937,7 +21652,11 @@ 0.0, 0.0 ], - "limit": 60000 + "knowledge": "2023-12", + "limit": 60000, + "max_output": 60000, + "open": true, + "released": "2024-09-25" }, "@cf/meta/llama-3.2-3b-instruct": { "cost": [ @@ -16946,7 +21665,11 @@ 0.0, 0.0 ], - "limit": 80000 + "knowledge": "2023-12", + "limit": 80000, + "max_output": 80000, + "open": true, + "released": "2024-09-25" }, "@cf/meta/llama-3.3-70b-instruct-fp8-fast": { "cost": [ @@ -16955,7 +21678,11 @@ 0.0, 0.0 ], - "limit": 24000 + "knowledge": "2023-12", + "limit": 24000, + "max_output": 24000, + "open": true, + "released": "2024-12-06" }, "@cf/meta/llama-4-scout-17b-16e-instruct": { "cost": [ @@ -16964,7 +21691,11 @@ 0.0, 0.0 ], - "limit": 131000 + "knowledge": "2024-08", + "limit": 131000, + "max_output": 16384, + "open": true, + "released": "2025-04-05" }, "@cf/meta/llama-guard-3-8b": { "cost": [ @@ -16973,7 +21704,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2023-12", + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2024-07-23" }, "@cf/mistralai/mistral-small-3.1-24b-instruct": { "cost": [ @@ -16982,7 +21717,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-06", + "limit": 128000, + "max_output": 128000, + "open": true, + "released": "2025-03-17" }, "@cf/moonshotai/kimi-k2.6": { "cost": [ @@ -16991,7 +21730,11 @@ 0.16, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 256000, + "open": true, + "released": "2026-04-20" }, "@cf/moonshotai/kimi-k2.7-code": { "cost": [ @@ -17000,7 +21743,11 @@ 0.19, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-06-12" }, "@cf/nvidia/nemotron-3-120b-a12b": { "cost": [ @@ -17009,7 +21756,11 @@ 0.0, 0.0 ], - "limit": 256000 + "knowledge": "2025-06", + "limit": 256000, + "max_output": 256000, + "open": true, + "released": "2026-03-11" }, "@cf/openai/gpt-oss-120b": { "cost": [ @@ -17018,7 +21769,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-06", + "limit": 128000, + "max_output": 16384, + "open": true, + "released": "2025-08-05" }, "@cf/openai/gpt-oss-20b": { "cost": [ @@ -17027,7 +21782,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-06", + "limit": 128000, + "max_output": 16384, + "open": true, + "released": "2025-08-05" }, "@cf/qwen/qwen2.5-coder-32b-instruct": { "cost": [ @@ -17036,7 +21795,10 @@ 0.0, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 32768, + "open": true, + "released": "2024-11-12" }, "@cf/qwen/qwen3-30b-a3b-fp8": { "cost": [ @@ -17045,7 +21807,10 @@ 0.0, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 32768, + "open": true, + "released": "2025-04-28" }, "@cf/qwen/qwen3.8-27b": { "cost": [ @@ -17054,7 +21819,10 @@ 0.05, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-08-14" }, "@cf/qwen/qwq-32b": { "cost": [ @@ -17063,7 +21831,11 @@ 0.0, 0.0 ], - "limit": 24000 + "knowledge": "2024-04", + "limit": 24000, + "max_output": 24000, + "open": true, + "released": "2025-03-05" }, "@cf/zai-org/glm-4.7-flash": { "cost": [ @@ -17072,7 +21844,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2025-04", + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2026-01-19" }, "@cf/zai-org/glm-5.2": { "cost": [ @@ -17081,7 +21857,10 @@ 0.26, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 256000, + "open": true, + "released": "2026-06-13" }, "@cf/zai-org/glm-5.3": { "cost": [ @@ -17090,7 +21869,10 @@ 0.26, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-08-14" }, "@cf/zai-org/glm-5.3-flash": { "cost": [ @@ -17099,7 +21881,10 @@ 0.03, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-08-26" } }, "name": "Cloudflare Workers AI" @@ -17113,7 +21898,10 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 4000, + "open": true, + "released": "2024-10-24" }, "command-a-03-2025": { "cost": [ @@ -17122,7 +21910,11 @@ 0.0, 0.0 ], - "limit": 256000 + "knowledge": "2024-06-01", + "limit": 256000, + "max_output": 8000, + "open": true, + "released": "2025-03-13" }, "command-a-plus-05-2026": { "cost": [ @@ -17131,7 +21923,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2025-04-01", + "limit": 128000, + "max_output": 64000, + "open": true, + "released": "2026-05-20" }, "command-a-reasoning-08-2025": { "cost": [ @@ -17140,7 +21936,11 @@ 0.0, 0.0 ], - "limit": 256000 + "knowledge": "2024-06-01", + "limit": 256000, + "max_output": 32000, + "open": true, + "released": "2025-08-21" }, "command-a-translate-08-2025": { "cost": [ @@ -17149,7 +21949,11 @@ 0.0, 0.0 ], - "limit": 8000 + "knowledge": "2024-06-01", + "limit": 8000, + "max_output": 8000, + "open": true, + "released": "2025-08-28" }, "command-a-vision-07-2025": { "cost": [ @@ -17158,7 +21962,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-06-01", + "limit": 128000, + "max_output": 8000, + "open": true, + "released": "2025-07-31" }, "command-r-08-2024": { "cost": [ @@ -17167,7 +21975,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-06-01", + "limit": 128000, + "max_output": 4000, + "open": true, + "released": "2024-08-30" }, "command-r-plus-08-2024": { "cost": [ @@ -17176,7 +21988,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-06-01", + "limit": 128000, + "max_output": 4000, + "open": true, + "released": "2024-08-30" }, "command-r7b-12-2024": { "cost": [ @@ -17185,7 +22001,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-06-01", + "limit": 128000, + "max_output": 4000, + "open": true, + "released": "2024-12-13" }, "command-r7b-arabic-02-2025": { "cost": [ @@ -17194,7 +22014,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-06-01", + "limit": 128000, + "max_output": 4000, + "open": true, + "released": "2025-02-27" }, "north-mini-code-1-0": { "cost": [ @@ -17203,7 +22027,11 @@ 0.0, 0.0 ], - "limit": 256000 + "knowledge": "2025-09-23", + "limit": 256000, + "max_output": 64000, + "open": true, + "released": "2026-06-09" }, "north-small-translate-09-2026": { "cost": [ @@ -17212,7 +22040,10 @@ 0.0, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 16000, + "open": true, + "released": "2026-09-09" } }, "name": "Cohere" @@ -17226,7 +22057,10 @@ 0.03, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 131072, + "open": true, + "released": "2026-02-12" }, "MiniMaxAI/MiniMax-M2.7": { "cost": [ @@ -17235,7 +22069,10 @@ 0.06, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 131072, + "open": true, + "released": "2026-03-18" }, "MiniMaxAI/MiniMax-M3": { "cost": [ @@ -17244,7 +22081,10 @@ 0.06, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 512000, + "open": true, + "released": "2026-06-01" }, "Qwen/Qwen3.8-27B": { "cost": [ @@ -17253,7 +22093,10 @@ 0.04, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-08-14" }, "Qwen/Qwen3.8-Flash": { "cost": [ @@ -17262,7 +22105,9 @@ 0.016, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-08-26" }, "Qwen/Qwen3.8-Max": { "cost": [ @@ -17271,7 +22116,9 @@ 0.25, 2.5 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-08-03" }, "Qwen/Qwen3.8-Max-0902": { "cost": [ @@ -17280,7 +22127,9 @@ 0.25, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-09-02" }, "Qwen/Qwen3.8-Omni-Flash": { "cost": [ @@ -17289,7 +22138,9 @@ 0.016, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-09-17" }, "claude-fable-5": { "cost": [ @@ -17298,7 +22149,10 @@ 1.0, 12.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-09" }, "claude-fable-5-1": { "cost": [ @@ -17307,7 +22161,10 @@ 0.25, 12.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-01" }, "claude-haiku-4-5-20251001": { "cost": [ @@ -17316,7 +22173,10 @@ 0.1, 1.25 ], - "limit": 200000 + "knowledge": "2025-02-28", + "limit": 200000, + "max_output": 64000, + "released": "2025-10-15" }, "claude-haiku-5-5": { "cost": [ @@ -17325,7 +22185,10 @@ 0.01, 0.125 ], + "knowledge": "2026-06", "limit": 1000000, + "max_output": 128000, + "released": "2026-10-07", "tiers": [ { "cost": [ @@ -17348,7 +22211,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-16" }, "claude-opus-4-8": { "cost": [ @@ -17357,7 +22223,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-28" }, "claude-opus-5": { "cost": [ @@ -17366,7 +22235,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-05", + "limit": 1000000, + "max_output": 128000, + "released": "2026-07-24" }, "claude-opus-5-5": { "cost": [ @@ -17375,7 +22247,10 @@ 0.2, 5.0 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-22" }, "claude-sonnet-4-6": { "cost": [ @@ -17384,7 +22259,10 @@ 0.3, 3.75 ], - "limit": 1000000 + "knowledge": "2025-08-31", + "limit": 1000000, + "max_output": 64000, + "released": "2026-02-17" }, "claude-sonnet-5": { "cost": [ @@ -17393,7 +22271,10 @@ 0.2, 2.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-30" }, "claude-sonnet-5-5": { "cost": [ @@ -17402,7 +22283,10 @@ 0.1, 2.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-28" }, "deepseek/deepseek-v4-flash": { "cost": [ @@ -17411,7 +22295,11 @@ 0.003, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "deepseek/deepseek-v4-flash-fast": { "cost": [ @@ -17420,7 +22308,11 @@ 0.07, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "deepseek/deepseek-v4-flash-vision-exp": { "cost": [ @@ -17429,7 +22321,10 @@ 0.003, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-08-21" }, "deepseek/deepseek-v4-pro": { "cost": [ @@ -17438,7 +22333,11 @@ 0.022, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "deepseek/deepseek-v4.1-flash": { "cost": [ @@ -17447,7 +22346,11 @@ 0.003, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-09-10" }, "deepseek/deepseek-v4.1-flash-fast": { "cost": [ @@ -17456,7 +22359,11 @@ 0.016, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-09-10" }, "google/gemini-3.1-flash-lite": { "cost": [ @@ -17465,7 +22372,10 @@ 0.03, 0.0 ], - "limit": 1000000 + "knowledge": "2025-01", + "limit": 1000000, + "max_output": 65536, + "released": "2026-05-07" }, "google/gemini-3.5-flash": { "cost": [ @@ -17474,7 +22384,10 @@ 0.15, 0.0 ], - "limit": 1000000 + "knowledge": "2025-01", + "limit": 1000000, + "max_output": 65536, + "released": "2026-05-19" }, "google/gemini-3.5-flash-lite": { "cost": [ @@ -17483,7 +22396,10 @@ 0.03, 0.0 ], - "limit": 1000000 + "knowledge": "2026-03", + "limit": 1000000, + "max_output": 65536, + "released": "2026-07-21" }, "google/gemini-3.6-flash": { "cost": [ @@ -17492,7 +22408,10 @@ 0.15, 0.0 ], - "limit": 1000000 + "knowledge": "2026-03", + "limit": 1000000, + "max_output": 65536, + "released": "2026-07-21" }, "google/gemini-3.7-flash": { "cost": [ @@ -17501,7 +22420,10 @@ 0.15, 0.08334 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-08-13" }, "google/gemini-3.8-flash": { "cost": [ @@ -17510,7 +22432,9 @@ 0.15, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 65536, + "released": "2026-09-02" }, "google/gemini-4-argon": { "cost": [ @@ -17519,7 +22443,10 @@ 0.1, 0.0 ], - "limit": 1000000 + "knowledge": "2026-03", + "limit": 1000000, + "max_output": 65536, + "released": "2026-10-13" }, "gpt-5.3-codex": { "cost": [ @@ -17528,7 +22455,10 @@ 0.5, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-02-05" }, "gpt-5.4": { "cost": [ @@ -17537,7 +22467,10 @@ 0.25, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-05" }, "gpt-5.4-mini": { "cost": [ @@ -17546,7 +22479,10 @@ 0.075, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "gpt-5.5": { "cost": [ @@ -17555,7 +22491,10 @@ 0.5, 0.0 ], - "limit": 400000 + "knowledge": "2025-12-01", + "limit": 400000, + "max_output": 128000, + "released": "2026-04-23" }, "gpt-5.6-luna": { "cost": [ @@ -17564,7 +22503,10 @@ 0.02, 0.25 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -17587,7 +22529,10 @@ 0.5, 6.25 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -17610,7 +22555,10 @@ 0.2, 2.5 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -17633,7 +22581,10 @@ 1.0, 12.5 ], + "knowledge": "2026-04-30", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-04", "tiers": [ { "cost": [ @@ -17656,7 +22607,10 @@ 0.01, 0.125 ], + "knowledge": "2026-05-18", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -17679,7 +22633,10 @@ 0.2, 2.5 ], + "knowledge": "2026-04-20", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -17702,7 +22659,10 @@ 0.1, 2.5 ], + "knowledge": "2026-04-30", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-29", "tiers": [ { "cost": [ @@ -17718,6 +22678,32 @@ } ] }, + "gpt-6.1-terra": { + "cost": [ + 1.0, + 5.0, + 0.05, + 1.25 + ], + "knowledge": "2026-06-01", + "limit": 1050000, + "max_output": 128000, + "released": "2026-10-26", + "tiers": [ + { + "cost": [ + 2.0, + 7.5, + 0.1, + 2.5 + ], + "tier": { + "size": 272000, + "type": "context" + } + } + ] + }, "inclusionai/ling-3.1-flash:free": { "cost": [ 0.0, @@ -17726,6 +22712,9 @@ 0.0 ], "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-09-29", "status": "deprecated" }, "meta/muse-spark-1.1": { @@ -17735,7 +22724,9 @@ 0.15, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-04-08" }, "meta/muse-spark-1.2": { "cost": [ @@ -17744,7 +22735,9 @@ 0.15, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-08-05" }, "meta/muse-spark-1.2-contributor": { "cost": [ @@ -17753,7 +22746,9 @@ 0.002, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-08-05" }, "meta/muse-spark-1.3": { "cost": [ @@ -17762,7 +22757,9 @@ 0.15, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-09-02" }, "meta/muse-spark-1.3-contributor": { "cost": [ @@ -17771,7 +22768,9 @@ 0.002, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-09-02" }, "meta/muse-wonder-1.0": { "cost": [ @@ -17780,7 +22779,9 @@ 0.2, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-10-12" }, "mistral/mistral-large-4": { "cost": [ @@ -17789,7 +22790,9 @@ 0.14, 0.0 ], - "limit": 524288 + "limit": 524288, + "max_output": 262144, + "released": "2026-10-06" }, "moonshotai/Kimi-K2.7-Code": { "cost": [ @@ -17798,7 +22801,11 @@ 0.19, 0.0 ], - "limit": 256000 + "knowledge": "2025-01", + "limit": 256000, + "max_output": 256000, + "open": true, + "released": "2026-06-12" }, "moonshotai/Kimi-K2.7-Code-Highspeed": { "cost": [ @@ -17807,7 +22814,11 @@ 0.38, 0.0 ], - "limit": 262000 + "knowledge": "2025-01", + "limit": 262000, + "max_output": 262000, + "open": true, + "released": "2026-06-12" }, "moonshotai/Kimi-K3": { "cost": [ @@ -17816,7 +22827,10 @@ 0.3, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-07-16" }, "nvidia/nemotron-3-ultra-550b-a55b": { "cost": [ @@ -17825,7 +22839,11 @@ 0.12, 0.0 ], - "limit": 1000000 + "knowledge": "2025-09", + "limit": 1000000, + "max_output": 128000, + "open": true, + "released": "2026-06-04" }, "sakana/fugu-ultra": { "cost": [ @@ -17834,7 +22852,9 @@ 0.5, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-15" }, "stepfun/Step-3.5-Flash": { "cost": [ @@ -17843,7 +22863,11 @@ 0.02, 0.0 ], - "limit": 256000 + "knowledge": "2025-01", + "limit": 256000, + "max_output": 256000, + "open": true, + "released": "2026-01-29" }, "stepfun/Step-3.7-Flash": { "cost": [ @@ -17852,7 +22876,11 @@ 0.04, 0.0 ], - "limit": 256000 + "knowledge": "2026-03-01", + "limit": 256000, + "max_output": 256000, + "open": true, + "released": "2026-05-29" }, "stepfun/Step-5-Preview": { "cost": [ @@ -17861,7 +22889,10 @@ 0.05, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 1000000, + "open": true, + "released": "2026-09-16" }, "tencent/hy3-paid": { "cost": [ @@ -17870,7 +22901,10 @@ 0.035, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 128000, + "open": true, + "released": "2026-07-06" }, "tencent/hy4-preview": { "cost": [ @@ -17879,7 +22913,10 @@ 0.042, 0.0 ], - "limit": 1024000 + "limit": 1024000, + "max_output": 64000, + "open": true, + "released": "2026-08-28" }, "thinkingmachines/inkling": { "cost": [ @@ -17888,7 +22925,10 @@ 0.17, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 256000, + "open": true, + "released": "2026-07-15" }, "thinkingmachines/inkling-small": { "cost": [ @@ -17897,7 +22937,10 @@ 0.1, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 1000000, + "open": true, + "released": "2026-07-30" }, "xai/grok-4.5": { "cost": [ @@ -17906,7 +22949,9 @@ 0.5, 0.0 ], - "limit": 500000 + "limit": 500000, + "max_output": 500000, + "released": "2026-07-08" }, "xai/grok-4.6": { "cost": [ @@ -17915,7 +22960,10 @@ 0.5, 0.0 ], + "knowledge": "2026-02-01", "limit": 500000, + "max_output": 500000, + "released": "2026-08-12", "tiers": [ { "cost": [ @@ -17938,7 +22986,10 @@ 0.5, 0.0 ], + "knowledge": "2026-05", "limit": 500000, + "max_output": 500000, + "released": "2026-09-21", "tiers": [ { "cost": [ @@ -17961,7 +23012,10 @@ 0.03, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-26" }, "z-ai/glm-5.3-flashx": { "cost": [ @@ -17970,7 +23024,10 @@ 0.075, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-26" }, "zai-org/GLM-5.2": { "cost": [ @@ -17979,7 +23036,10 @@ 0.26, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "zai-org/GLM-5.2-Fast": { "cost": [ @@ -17988,7 +23048,10 @@ 0.5, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "zai-org/GLM-5.3": { "cost": [ @@ -17997,7 +23060,10 @@ 0.26, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-14" } }, "name": "CommandCode" @@ -18011,7 +23077,11 @@ 0.005, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 393216, + "open": true, + "released": "2026-09-10" } }, "name": "CoralBricks" @@ -18025,7 +23095,11 @@ 0.0, 0.0 ], - "limit": 65536 + "knowledge": "2025-09", + "limit": 65536, + "max_output": 16384, + "open": true, + "released": "2025-09-02" }, "claude-4-5-sonnet": { "cost": [ @@ -18034,7 +23108,10 @@ 0.326, 4.078 ], - "limit": 200000 + "knowledge": "2025-07-31", + "limit": 200000, + "max_output": 64000, + "released": "2025-09-29" }, "claude-4-6-sonnet": { "cost": [ @@ -18043,7 +23120,10 @@ 0.32, 3.999 ], - "limit": 1000000 + "knowledge": "2025-08-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-17" }, "claude-haiku-4-5": { "cost": [ @@ -18052,7 +23132,10 @@ 0.099, 1.186 ], - "limit": 200000 + "knowledge": "2025-02-28", + "limit": 200000, + "max_output": 64000, + "released": "2025-10-15" }, "claude-haiku-5.5": { "cost": [ @@ -18061,7 +23144,10 @@ 0.011, 0.14 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-10-07" }, "claude-opus-5": { "cost": [ @@ -18070,7 +23156,10 @@ 0.55, 6.874 ], - "limit": 1000000 + "knowledge": "2026-05", + "limit": 1000000, + "max_output": 128000, + "released": "2026-07-24" }, "claude-opus-5.5": { "cost": [ @@ -18079,7 +23168,10 @@ 0.219, 5.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-22" }, "claude-opus4-5": { "cost": [ @@ -18088,7 +23180,10 @@ 0.531, 6.645 ], - "limit": 200000 + "knowledge": "2025-05", + "limit": 200000, + "max_output": 64000, + "released": "2025-11-24" }, "claude-opus4-6": { "cost": [ @@ -18097,7 +23192,10 @@ 0.531, 6.645 ], - "limit": 1000000 + "knowledge": "2025-05-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-05" }, "claude-opus4-7": { "cost": [ @@ -18106,7 +23204,10 @@ 0.544, 6.797 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-16" }, "claude-opus4-8": { "cost": [ @@ -18115,7 +23216,10 @@ 0.544, 6.797 ], - "limit": 1000000 + "knowledge": "2026-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-28" }, "claude-sonnet-5": { "cost": [ @@ -18124,7 +23228,10 @@ 0.219, 2.749 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-30" }, "claude-sonnet-5.5": { "cost": [ @@ -18133,7 +23240,10 @@ 0.225, 2.813 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-28" }, "codestral-2508": { "cost": [ @@ -18142,7 +23252,9 @@ 0.037, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 256000, + "released": "2025-07-30" }, "deepseek-v3.2": { "cost": [ @@ -18151,7 +23263,11 @@ 0.15, 0.0 ], - "limit": 163840 + "knowledge": "2024-07", + "limit": 163840, + "max_output": 65536, + "open": true, + "released": "2025-12-01" }, "deepseek-v4-flash-0731": { "cost": [ @@ -18160,7 +23276,11 @@ 0.06, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-07-31" }, "deepseek-v4-pro": { "cost": [ @@ -18169,7 +23289,11 @@ 0.15, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "deepseek-v4-pro-0813": { "cost": [ @@ -18178,7 +23302,10 @@ 0.5, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 64000, + "open": true, + "released": "2026-08-13" }, "deepseek-v4.1-flash": { "cost": [ @@ -18187,16 +23314,24 @@ 0.004, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 393216, + "open": true, + "released": "2026-09-10" }, "deepseek-v4.1-flash-1017": { "cost": [ - 0.279, - 1.114, - 0.111, + 0.203, + 0.609, + 0.006, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-10-17" }, "devstral-2512": { "cost": [ @@ -18205,7 +23340,11 @@ 0.045, 0.0 ], - "limit": 256000 + "knowledge": "2025-12", + "limit": 256000, + "max_output": 256000, + "open": true, + "released": "2025-12-09" }, "gemini-2.5-flash": { "cost": [ @@ -18214,7 +23353,10 @@ 0.029, 0.097 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65535, + "released": "2025-06-17" }, "gemini-2.5-pro": { "cost": [ @@ -18223,7 +23365,10 @@ 0.242, 0.434 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65535, + "released": "2025-06-17" }, "gemini-3.1-flash-lite": { "cost": [ @@ -18232,7 +23377,10 @@ 0.025, 0.082 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65535, + "released": "2026-05-07" }, "gemini-3.5-flash": { "cost": [ @@ -18241,7 +23389,10 @@ 0.165, 1.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65535, + "released": "2026-05-19" }, "gemini-3.5-flash-lite": { "cost": [ @@ -18250,7 +23401,10 @@ 0.033, 0.082 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65535, + "released": "2026-07-21" }, "gemini-3.6-flash": { "cost": [ @@ -18259,7 +23413,10 @@ 0.075, 0.038 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65535, + "released": "2026-07-21" }, "gemini-3.7-flash": { "cost": [ @@ -18268,7 +23425,10 @@ 0.075, 0.038 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65535, + "released": "2026-08-13" }, "gemini-3.8-flash": { "cost": [ @@ -18277,7 +23437,9 @@ 0.082, 0.084 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65535, + "released": "2026-09-02" }, "gemini-4-argon": { "cost": [ @@ -18286,7 +23448,10 @@ 0.113, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65535, + "released": "2026-10-13" }, "gemma-3-27b-it": { "cost": [ @@ -18295,7 +23460,11 @@ 0.0, 0.0 ], - "limit": 131000 + "knowledge": "2024-08", + "limit": 131000, + "max_output": 110000, + "open": true, + "released": "2025-03-12" }, "gemma-4-26b-a4b-it": { "cost": [ @@ -18304,7 +23473,10 @@ 0.0, 0.0 ], - "limit": 262000 + "limit": 262000, + "max_output": 81920, + "open": true, + "released": "2026-04-02" }, "gemma-4-31b-it": { "cost": [ @@ -18313,7 +23485,11 @@ 0.0, 0.0 ], - "limit": 262000 + "knowledge": "2025-01", + "limit": 262000, + "max_output": 262000, + "open": true, + "released": "2026-04-02" }, "glm-4.7-flash": { "cost": [ @@ -18322,7 +23498,11 @@ 0.0, 0.0 ], - "limit": 203000 + "knowledge": "2025-04", + "limit": 203000, + "max_output": 203000, + "open": true, + "released": "2026-01-19" }, "glm-5.1": { "cost": [ @@ -18331,7 +23511,10 @@ 0.346, 0.0 ], - "limit": 202752 + "limit": 202752, + "max_output": 202752, + "open": true, + "released": "2026-04-07" }, "glm-5.2": { "cost": [ @@ -18340,7 +23523,10 @@ 0.189, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1000000, + "open": true, + "released": "2026-06-13" }, "glm-5.3": { "cost": [ @@ -18349,7 +23535,10 @@ 0.154, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-08-14" }, "glm-5.3-flash": { "cost": [ @@ -18358,7 +23547,10 @@ 0.018, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-08-26" }, "gpt-4.1": { "cost": [ @@ -18367,7 +23559,10 @@ 0.546, 0.0 ], - "limit": 1047576 + "knowledge": "2024-04", + "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14" }, "gpt-4.1-mini": { "cost": [ @@ -18376,7 +23571,10 @@ 0.134, 0.0 ], - "limit": 1047576 + "knowledge": "2024-04", + "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14" }, "gpt-4.1-nano": { "cost": [ @@ -18385,7 +23583,10 @@ 0.056, 0.0 ], - "limit": 1047576 + "knowledge": "2024-04", + "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14" }, "gpt-4o": { "cost": [ @@ -18394,7 +23595,10 @@ 1.33, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16000, + "released": "2024-05-13" }, "gpt-4o-mini": { "cost": [ @@ -18403,7 +23607,10 @@ 0.081, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16000, + "released": "2024-07-18" }, "gpt-5": { "cost": [ @@ -18412,7 +23619,10 @@ 0.156, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "gpt-5-mini": { "cost": [ @@ -18421,7 +23631,10 @@ 0.056, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "gpt-5-nano": { "cost": [ @@ -18430,7 +23643,10 @@ 0.019, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "gpt-5.1": { "cost": [ @@ -18439,7 +23655,10 @@ 0.156, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "gpt-5.4": { "cost": [ @@ -18448,7 +23667,10 @@ 0.242, 0.0 ], - "limit": 1050000 + "knowledge": "2025-08-31", + "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05" }, "gpt-5.6-luna": { "cost": [ @@ -18457,7 +23679,10 @@ 0.022, 0.275 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "gpt-5.6-sol": { "cost": [ @@ -18466,7 +23691,10 @@ 0.44, 5.5 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "gpt-5.6-terra": { "cost": [ @@ -18475,7 +23703,10 @@ 0.219, 2.749 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "gpt-6-astra": { "cost": [ @@ -18484,7 +23715,10 @@ 1.228, 15.34 ], - "limit": 1050000 + "knowledge": "2026-04-30", + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-04" }, "gpt-6-luna": { "cost": [ @@ -18493,7 +23727,10 @@ 0.012, 0.15 ], - "limit": 1050000 + "knowledge": "2026-05-18", + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22" }, "gpt-6-sol": { "cost": [ @@ -18502,7 +23739,10 @@ 0.24, 3.0 ], - "limit": 1050000 + "knowledge": "2026-04-20", + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22" }, "gpt-6.1-sol": { "cost": [ @@ -18511,7 +23751,22 @@ 0.12, 3.0 ], - "limit": 1050000 + "knowledge": "2026-04-30", + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-29" + }, + "gpt-6.1-terra": { + "cost": [ + 1.176, + 5.882, + 0.059, + 1.47 + ], + "knowledge": "2026-06-01", + "limit": 1050000, + "max_output": 128000, + "released": "2026-10-26" }, "gpt-oss-120b": { "cost": [ @@ -18520,7 +23775,11 @@ 0.01, 0.0 ], - "limit": 131000 + "knowledge": "2024-06", + "limit": 131000, + "max_output": 131000, + "open": true, + "released": "2025-08-05" }, "gpt-oss-20b": { "cost": [ @@ -18529,7 +23788,11 @@ 0.0, 0.0 ], - "limit": 131000 + "knowledge": "2024-06", + "limit": 131000, + "max_output": 131000, + "open": true, + "released": "2025-08-05" }, "gpt-oss-safeguard-120b": { "cost": [ @@ -18538,7 +23801,10 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 128000, + "open": true, + "released": "2025-10-29" }, "hermes-4-405b": { "cost": [ @@ -18547,7 +23813,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-08-31", + "limit": 128000, + "max_output": 128000, + "open": true, + "released": "2025-08-26" }, "kimi-k2.6": { "cost": [ @@ -18556,7 +23826,11 @@ 0.1, 0.0 ], - "limit": 256000 + "knowledge": "2025-01", + "limit": 256000, + "max_output": 256000, + "open": true, + "released": "2026-04-20" }, "kimi-k2.7-code": { "cost": [ @@ -18565,7 +23839,11 @@ 0.18, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-06-12" }, "kimi-k3": { "cost": [ @@ -18574,7 +23852,10 @@ 0.0, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-07-16" }, "kolibri-1": { "cost": [ @@ -18583,7 +23864,11 @@ 0.084, 0.0 ], - "limit": 262144 + "knowledge": "2026-06-18", + "limit": 262144, + "max_output": 81920, + "open": true, + "released": "2026-10-03" }, "llama-3.3-70b-instruct": { "cost": [ @@ -18592,7 +23877,11 @@ 0.0, 0.0 ], - "limit": 131000 + "knowledge": "2023-12", + "limit": 131000, + "max_output": 131000, + "open": true, + "released": "2024-12-06" }, "minicpm-v-4.5": { "cost": [ @@ -18601,7 +23890,9 @@ 0.0, 0.0 ], - "limit": 32000 + "limit": 32000, + "max_output": 32000, + "released": "2026-06-02" }, "minimax-m2": { "cost": [ @@ -18610,7 +23901,10 @@ 0.0, 0.0 ], - "limit": 400000 + "limit": 400000, + "max_output": 196000, + "open": true, + "released": "2025-10-27" }, "minimax-m2.1": { "cost": [ @@ -18619,7 +23913,10 @@ 0.0, 0.0 ], - "limit": 196000 + "limit": 196000, + "max_output": 196000, + "open": true, + "released": "2025-12-23" }, "minimax-m2.5": { "cost": [ @@ -18628,7 +23925,10 @@ 0.075, 0.0 ], - "limit": 196000 + "limit": 196000, + "max_output": 196000, + "open": true, + "released": "2026-02-12" }, "minimax-m3": { "cost": [ @@ -18637,7 +23937,21 @@ 0.06, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-06-01" + }, + "minimax-m3.1-flash": { + "cost": [ + 0.304, + 1.219, + 0.076, + 0.0 + ], + "limit": 1048576, + "max_output": 64000, + "released": "2026-10-19" }, "ministral-14b-2512": { "cost": [ @@ -18646,7 +23960,10 @@ 0.022, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 256000, + "open": true, + "released": "2025-12-02" }, "ministral-3b-2512": { "cost": [ @@ -18655,7 +23972,10 @@ 0.012, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 256000, + "open": true, + "released": "2025-12-02" }, "ministral-8b-2512": { "cost": [ @@ -18664,7 +23984,10 @@ 0.017, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 256000, + "open": true, + "released": "2025-12-02" }, "mistral-7b-instruct-v0.2": { "cost": [ @@ -18673,7 +23996,9 @@ 0.0, 0.0 ], - "limit": 32000 + "limit": 32000, + "max_output": 8192, + "released": "2025-05-26" }, "mistral-large-2402": { "cost": [ @@ -18682,7 +24007,9 @@ 0.0, 0.0 ], - "limit": 32000 + "limit": 32000, + "max_output": 8192, + "released": "2025-05-26" }, "mistral-large-2512": { "cost": [ @@ -18691,7 +24018,11 @@ 0.061, 0.0 ], - "limit": 256000 + "knowledge": "2024-11", + "limit": 256000, + "max_output": 256000, + "open": true, + "released": "2025-12-02" }, "mistral-large-4-0": { "cost": [ @@ -18700,7 +24031,9 @@ 0.079, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 262144, + "released": "2026-10-06" }, "mistral-medium-3.5": { "cost": [ @@ -18709,7 +24042,9 @@ 0.154, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 256000, + "released": "2026-04-30" }, "mistral-nemo-instruct-2407": { "cost": [ @@ -18718,7 +24053,11 @@ 0.014, 0.0 ], - "limit": 118000 + "knowledge": "2024-07", + "limit": 118000, + "max_output": 118000, + "open": true, + "released": "2024-07-18" }, "mistral-small-2503": { "cost": [ @@ -18727,7 +24066,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-06", + "limit": 128000, + "max_output": 128000, + "open": true, + "released": "2025-03-17" }, "mistral-small-2603": { "cost": [ @@ -18736,7 +24079,11 @@ 0.016, 0.0 ], - "limit": 262144 + "knowledge": "2025-06", + "limit": 262144, + "max_output": 256000, + "open": true, + "released": "2026-03-16" }, "mistral-small-3.2-24b-instruct-2506": { "cost": [ @@ -18745,7 +24092,11 @@ 0.0, 0.0 ], - "limit": 131000 + "knowledge": "2023-10-31", + "limit": 131000, + "max_output": 131000, + "open": true, + "released": "2025-06-20" }, "mixtral-8x7B-instruct-v0.1": { "cost": [ @@ -18754,7 +24105,10 @@ 0.0, 0.0 ], - "limit": 32000 + "limit": 32000, + "max_output": 4096, + "open": true, + "released": "2023-12-11" }, "nemotron-nano-v2-12b": { "cost": [ @@ -18763,7 +24117,10 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 128000, + "open": true, + "released": "2025-10-28" }, "nova-2-lite": { "cost": [ @@ -18772,7 +24129,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-10", + "limit": 1000000, + "max_output": 65535, + "released": "2025-12-02" }, "nova-lite-v1": { "cost": [ @@ -18781,7 +24141,10 @@ 0.0, 0.0 ], - "limit": 300000 + "knowledge": "2024-10-31", + "limit": 300000, + "max_output": 10000, + "released": "2024-12-05" }, "nova-micro-v1": { "cost": [ @@ -18790,7 +24153,10 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-10-31", + "limit": 128000, + "max_output": 10000, + "released": "2024-12-05" }, "nova-pro-v1": { "cost": [ @@ -18799,7 +24165,10 @@ 0.0, 0.0 ], - "limit": 300000 + "knowledge": "2024-10-31", + "limit": 300000, + "max_output": 10000, + "released": "2024-12-05" }, "nvidia-nemotron-3-nano-30b-a3b": { "cost": [ @@ -18808,7 +24177,11 @@ 0.0, 0.0 ], - "limit": 256000 + "knowledge": "2025-06-25", + "limit": 256000, + "max_output": 256000, + "open": true, + "released": "2025-12-15" }, "pixtral-large-2502": { "cost": [ @@ -18817,7 +24190,9 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 128000, + "released": "2025-04-08" }, "qwen2.5-vl-72b-instruct": { "cost": [ @@ -18826,7 +24201,11 @@ 0.0, 0.0 ], - "limit": 32000 + "knowledge": "2024-04", + "limit": 32000, + "max_output": 32000, + "open": true, + "released": "2025-01-26" }, "qwen3-235b-a22b-instruct-2507": { "cost": [ @@ -18835,7 +24214,10 @@ 0.018, 0.0 ], - "limit": 262000 + "limit": 262000, + "max_output": 262000, + "open": true, + "released": "2025-07-21" }, "qwen3-30b-a3b-instruct-2507": { "cost": [ @@ -18844,7 +24226,10 @@ 0.0, 0.0 ], - "limit": 262000 + "limit": 262000, + "max_output": 262000, + "open": true, + "released": "2025-07-28" }, "qwen3-32b": { "cost": [ @@ -18853,7 +24238,11 @@ 0.0, 0.0 ], - "limit": 16384 + "knowledge": "2025-04", + "limit": 16384, + "max_output": 16384, + "open": true, + "released": "2025-04-28" }, "qwen3-coder-30b-a3b-instruct": { "cost": [ @@ -18862,7 +24251,11 @@ 0.014, 0.0 ], - "limit": 262144 + "knowledge": "2025-04", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2025-07-31" }, "qwen3-coder-next": { "cost": [ @@ -18871,7 +24264,11 @@ 0.0, 0.0 ], - "limit": 256000 + "knowledge": "2025-09", + "limit": 256000, + "max_output": 256000, + "open": true, + "released": "2026-02-03" }, "qwen3-vl-235b-a22b": { "cost": [ @@ -18880,7 +24277,11 @@ 0.052, 0.0 ], - "limit": 256000 + "knowledge": "2025-03-31", + "limit": 256000, + "max_output": 256000, + "open": true, + "released": "2025-09-23" }, "qwen3.5-397b-a17b": { "cost": [ @@ -18889,7 +24290,10 @@ 0.0, 0.0 ], - "limit": 262000 + "limit": 262000, + "max_output": 262000, + "open": true, + "released": "2026-02-15" }, "qwen3.5-9b": { "cost": [ @@ -18898,7 +24302,10 @@ 0.0, 0.0 ], - "limit": 262000 + "limit": 262000, + "max_output": 262000, + "open": true, + "released": "2026-02-23" }, "qwen3.6-27b": { "cost": [ @@ -18907,7 +24314,10 @@ 0.0, 0.0 ], - "limit": 262000 + "limit": 262000, + "max_output": 262000, + "open": true, + "released": "2026-04-22" }, "qwen3.6-35b-a3b": { "cost": [ @@ -18916,7 +24326,10 @@ 0.0, 0.0 ], - "limit": 262000 + "limit": 262000, + "max_output": 32768, + "open": true, + "released": "2026-04-17" }, "qwen3.8-2.4t-a95b": { "cost": [ @@ -18925,7 +24338,10 @@ 0.625, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-08-12" }, "qwen3.8-27b": { "cost": [ @@ -18934,7 +24350,10 @@ 0.04, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 500000, + "open": true, + "released": "2026-08-14" }, "qwen3.8-flash-next": { "cost": [ @@ -18943,7 +24362,10 @@ 0.05, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 64000, + "open": true, + "released": "2026-08-27" }, "qwen3guard-gen-0.6b": { "cost": [ @@ -18952,7 +24374,9 @@ 0.0, 0.0 ], - "limit": 32000 + "limit": 32000, + "max_output": 32000, + "released": "2026-02-04" }, "qwen3guard-gen-8b": { "cost": [ @@ -18961,7 +24385,9 @@ 0.0, 0.0 ], - "limit": 32000 + "limit": 32000, + "max_output": 32000, + "released": "2026-02-04" }, "voxtral-small-2507": { "cost": [ @@ -18970,7 +24396,10 @@ 0.012, 0.0 ], - "limit": 32000 + "limit": 32000, + "max_output": 32000, + "open": true, + "released": "2025-07-15" } }, "name": "Cortecs" @@ -18984,7 +24413,10 @@ 1.0, 12.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-09" }, "anthropic/claude-fable-5-1": { "cost": [ @@ -18993,7 +24425,10 @@ 0.25, 12.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-01" }, "anthropic/claude-haiku-4-5": { "cost": [ @@ -19002,7 +24437,10 @@ 0.1, 1.25 ], - "limit": 200000 + "knowledge": "2025-02-28", + "limit": 200000, + "max_output": 64000, + "released": "2025-10-15" }, "anthropic/claude-haiku-5-5": { "cost": [ @@ -19011,7 +24449,10 @@ 0.01, 0.125 ], + "knowledge": "2026-06", "limit": 1000000, + "max_output": 128000, + "released": "2026-10-07", "tiers": [ { "cost": [ @@ -19034,7 +24475,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-16" }, "anthropic/claude-opus-4-8": { "cost": [ @@ -19043,7 +24487,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-28" }, "anthropic/claude-opus-5": { "cost": [ @@ -19052,7 +24499,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-05", + "limit": 1000000, + "max_output": 128000, + "released": "2026-07-24" }, "anthropic/claude-opus-5-5": { "cost": [ @@ -19061,7 +24511,10 @@ 0.2, 5.0 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-22" }, "anthropic/claude-sonnet-4-6": { "cost": [ @@ -19070,7 +24523,10 @@ 0.3, 3.75 ], - "limit": 1000000 + "knowledge": "2025-08-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-17" }, "anthropic/claude-sonnet-5": { "cost": [ @@ -19079,7 +24535,10 @@ 0.2, 2.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-30" }, "anthropic/claude-sonnet-5-5": { "cost": [ @@ -19088,7 +24547,10 @@ 0.1, 2.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-28" }, "deepseek/deepseek-v4-flash": { "cost": [ @@ -19097,7 +24559,11 @@ 0.006, 0.3 ], + "knowledge": "2025-05", "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24", "status": "deprecated" }, "deepseek/deepseek-v4-flash-vision-exp": { @@ -19108,6 +24574,9 @@ 0.3 ], "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-08-21", "status": "deprecated" }, "deepseek/deepseek-v4-pro": { @@ -19117,7 +24586,11 @@ 0.045, 1.35 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "deepseek/deepseek-v4.1-flash": { "cost": [ @@ -19126,7 +24599,11 @@ 0.006, 0.3 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-09-10" }, "gemini/gemini-2.5-flash": { "cost": [ @@ -19135,7 +24612,10 @@ 0.03, 0.3 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2025-06-17" }, "gemini/gemini-2.5-flash-lite": { "cost": [ @@ -19144,7 +24624,10 @@ 0.01, 0.1 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2025-06-17" }, "gemini/gemini-2.5-pro": { "cost": [ @@ -19153,7 +24636,10 @@ 0.125, 1.25 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2025-06-17", "tiers": [ { "cost": [ @@ -19176,7 +24662,10 @@ 0.05, 0.5 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2025-12-17" }, "gemini/gemini-3.1-pro-preview": { "cost": [ @@ -19185,7 +24674,10 @@ 0.2, 2.0 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2026-02-19", "tiers": [ { "cost": [ @@ -19208,7 +24700,10 @@ 0.15, 1.5 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-05-19" }, "gemini/gemini-3.5-flash-lite": { "cost": [ @@ -19217,7 +24712,10 @@ 0.03, 0.3 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-07-21" }, "gemini/gemini-3.6-flash": { "cost": [ @@ -19226,7 +24724,10 @@ 0.075, 0.75 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-07-21" }, "gemini/gemini-3.7-flash": { "cost": [ @@ -19235,7 +24736,10 @@ 0.075, 0.75 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-08-13" }, "gemini/gemini-3.8-flash": { "cost": [ @@ -19244,7 +24748,9 @@ 0.075, 0.75 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65536, + "released": "2026-09-02" }, "gemini/gemini-4-argon": { "cost": [ @@ -19253,7 +24759,10 @@ 0.1, 2.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-10-13" }, "minimax/minimax-m2.7": { "cost": [ @@ -19262,7 +24771,10 @@ 0.066, 0.42 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-03-18" }, "minimax/minimax-m3": { "cost": [ @@ -19272,6 +24784,9 @@ 0.33 ], "limit": 1024000, + "max_output": 512000, + "open": true, + "released": "2026-06-01", "tiers": [ { "cost": [ @@ -19294,7 +24809,11 @@ 0.18, 1.0 ], - "limit": 262000 + "knowledge": "2025-01", + "limit": 262000, + "max_output": 262000, + "open": true, + "released": "2026-04-20" }, "moonshot/kimi-k2.7-code": { "cost": [ @@ -19303,7 +24822,11 @@ 0.18, 1.0 ], - "limit": 262000 + "knowledge": "2025-01", + "limit": 262000, + "max_output": 262000, + "open": true, + "released": "2026-06-12" }, "moonshot/kimi-k3": { "cost": [ @@ -19312,7 +24835,10 @@ 0.3, 3.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-07-16" }, "openai/gpt-4o-mini": { "cost": [ @@ -19321,7 +24847,10 @@ 0.075, 0.15 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-07-18" }, "openai/gpt-5.4": { "cost": [ @@ -19330,7 +24859,10 @@ 0.25, 2.5 ], + "knowledge": "2025-08-31", "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05", "tiers": [ { "cost": [ @@ -19353,7 +24885,10 @@ 0.075, 0.75 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "openai/gpt-5.4-nano": { "cost": [ @@ -19362,7 +24897,10 @@ 0.02, 0.2 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "openai/gpt-5.5": { "cost": [ @@ -19371,7 +24909,10 @@ 0.5, 5.0 ], + "knowledge": "2025-12-01", "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23", "tiers": [ { "cost": [ @@ -19394,7 +24935,10 @@ 0.0, 0.0 ], + "knowledge": "2025-12-01", "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23", "tiers": [ { "cost": [ @@ -19417,7 +24961,10 @@ 0.02, 0.25 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -19440,7 +24987,10 @@ 0.4, 5.0 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -19463,7 +25013,10 @@ 0.2, 2.5 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -19486,7 +25039,10 @@ 1.0, 12.5 ], + "knowledge": "2026-04-30", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-04", "tiers": [ { "cost": [ @@ -19509,7 +25065,10 @@ 0.01, 0.125 ], + "knowledge": "2026-05-18", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -19532,7 +25091,10 @@ 0.2, 2.5 ], + "knowledge": "2026-04-20", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -19555,7 +25117,10 @@ 0.1, 2.5 ], + "knowledge": "2026-04-30", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-29", "tiers": [ { "cost": [ @@ -19579,6 +25144,8 @@ 0.24 ], "limit": 1000000, + "max_output": 65536, + "released": "2026-04-27", "tiers": [ { "cost": [ @@ -19601,7 +25168,10 @@ 0.032, 0.4 ], + "knowledge": "2025-04", "limit": 1000000, + "max_output": 65536, + "released": "2026-04-02", "tiers": [ { "cost": [ @@ -19625,6 +25195,8 @@ 0.04 ], "limit": 1000000, + "max_output": 65536, + "released": "2026-07-15", "tiers": [ { "cost": [ @@ -19659,7 +25231,9 @@ 0.375, 2.35 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 65536, + "released": "2026-05-21" }, "qwen/qwen3.7-plus": { "cost": [ @@ -19668,7 +25242,10 @@ 0.032, 0.4 ], + "knowledge": "2025-04", "limit": 1000000, + "max_output": 64000, + "released": "2026-06-02", "tiers": [ { "cost": [ @@ -19691,7 +25268,9 @@ 0.016, 0.2 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-08-26" }, "qwen/qwen3.8-max": { "cost": [ @@ -19700,7 +25279,9 @@ 0.23, 2.35 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-08-03" }, "qwen/qwen3.8-omni-flash": { "cost": [ @@ -19709,7 +25290,9 @@ 0.016, 0.13 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-09-17" }, "tencent/hy3": { "cost": [ @@ -19718,7 +25301,10 @@ 0.04, 0.16 ], - "limit": 262144 + "limit": 262144, + "max_output": 131072, + "open": true, + "released": "2026-07-06" }, "tencent/hy4-preview": { "cost": [ @@ -19727,7 +25313,10 @@ 0.048, 0.96 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65536, + "open": true, + "released": "2026-08-28" }, "x-ai/grok-4.3": { "cost": [ @@ -19737,6 +25326,8 @@ 1.25 ], "limit": 1000000, + "max_output": 1000000, + "released": "2026-04-17", "tiers": [ { "cost": [ @@ -19760,6 +25351,8 @@ 2.0 ], "limit": 500000, + "max_output": 500000, + "released": "2026-07-08", "tiers": [ { "cost": [ @@ -19782,7 +25375,10 @@ 0.5, 2.0 ], + "knowledge": "2026-02-01", "limit": 500000, + "max_output": 500000, + "released": "2026-08-12", "tiers": [ { "cost": [ @@ -19805,7 +25401,10 @@ 0.5, 2.0 ], + "knowledge": "2026-05", "limit": 500000, + "max_output": 500000, + "released": "2026-09-21", "tiers": [ { "cost": [ @@ -19829,6 +25428,8 @@ 1.0 ], "limit": 256000, + "max_output": 256000, + "released": "2026-04-16", "tiers": [ { "cost": [ @@ -19851,7 +25452,10 @@ 0.004, 0.16 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-09-22" }, "xiaomi/mimo-v2.6-pro": { "cost": [ @@ -19860,7 +25464,10 @@ 0.005, 0.47 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-09-22" }, "z-ai/glm-4.7": { "cost": [ @@ -19869,7 +25476,11 @@ 0.1, 0.47 ], + "knowledge": "2025-04", "limit": 200000, + "max_output": 128000, + "open": true, + "released": "2025-12-22", "tiers": [ { "cost": [ @@ -19893,6 +25504,9 @@ 0.6 ], "limit": 200000, + "max_output": 128000, + "open": true, + "released": "2026-02-12", "tiers": [ { "cost": [ @@ -19916,6 +25530,8 @@ 0.9 ], "limit": 200000, + "max_output": 128000, + "released": "2026-03-16", "tiers": [ { "cost": [ @@ -19939,6 +25555,9 @@ 1.0 ], "limit": 200000, + "max_output": 128000, + "open": true, + "released": "2026-04-07", "tiers": [ { "cost": [ @@ -19961,7 +25580,10 @@ 0.3, 1.2 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 128000, + "open": true, + "released": "2026-06-13" }, "z-ai/glm-5.3": { "cost": [ @@ -19970,7 +25592,10 @@ 0.3, 1.2 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 128000, + "open": true, + "released": "2026-08-14" }, "z-ai/glm-5.3-flash": { "cost": [ @@ -19979,7 +25604,10 @@ 0.03, 0.15 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 128000, + "open": true, + "released": "2026-08-26" } }, "name": "CrossModel" @@ -19994,6 +25622,9 @@ 0.0 ], "limit": 262144, + "max_output": 16384, + "open": true, + "released": "2025-07-21", "status": "deprecated" }, "deepseek-ai/DeepSeek-V3-0324": { @@ -20004,6 +25635,9 @@ 0.0 ], "limit": 163840, + "max_output": 163840, + "open": true, + "released": "2025-03-24", "status": "deprecated" }, "google/gemma-4-31b-it": { @@ -20013,7 +25647,11 @@ 0.14, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-04-02" }, "meta-llama/Llama-3.3-70B-Instruct": { "cost": [ @@ -20022,7 +25660,11 @@ 0.13, 0.0 ], + "knowledge": "2023-12", "limit": 128000, + "max_output": 4096, + "open": true, + "released": "2024-12-06", "status": "deprecated" }, "moonshotai/Kimi-K2.6": { @@ -20032,7 +25674,11 @@ 0.35, 0.0 ], + "knowledge": "2025-01", "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-20", "status": "deprecated" }, "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B": { @@ -20042,7 +25688,11 @@ 0.03, 0.0 ], - "limit": 262144 + "knowledge": "2025-06-25", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2025-12-15" }, "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B": { "cost": [ @@ -20051,7 +25701,11 @@ 0.15, 0.0 ], - "limit": 262144 + "knowledge": "2025-06", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-03-11" }, "nvidia/Nemotron-3-Nano-Omni-Reasoning-30B-A3B": { "cost": [ @@ -20060,7 +25714,10 @@ 0.3, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 65536, + "open": true, + "released": "2026-04-28" }, "openai/gpt-oss-120b": { "cost": [ @@ -20069,7 +25726,11 @@ 0.05, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "zai/GLM-5.1": { "cost": [ @@ -20079,6 +25740,9 @@ 0.0 ], "limit": 200000, + "max_output": 131072, + "open": true, + "released": "2026-04-07", "status": "deprecated" }, "zai/GLM-5.2": { @@ -20089,6 +25753,9 @@ 0.0 ], "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-13", "status": "deprecated" } }, @@ -20103,7 +25770,10 @@ 0.1, 5.0 ], - "limit": 200000 + "knowledge": "2025-02-28", + "limit": 200000, + "max_output": 64000, + "released": "2025-10-15" }, "claude-opus-4-8": { "cost": [ @@ -20112,7 +25782,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-28" }, "claude-sonnet-4-6": { "cost": [ @@ -20121,7 +25794,10 @@ 0.3, 3.75 ], - "limit": 1000000 + "knowledge": "2025-08-31", + "limit": 1000000, + "max_output": 64000, + "released": "2026-02-17" }, "gemini-3.1-pro-preview": { "cost": [ @@ -20130,7 +25806,10 @@ 0.2, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-02-19" }, "gpt-5.4": { "cost": [ @@ -20139,7 +25818,10 @@ 0.25, 0.0 ], - "limit": 1050000 + "knowledge": "2025-08-31", + "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05" }, "gpt-5.5": { "cost": [ @@ -20148,7 +25830,10 @@ 0.5, 0.0 ], - "limit": 1050000 + "knowledge": "2025-12-01", + "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23" }, "grok-4.3": { "cost": [ @@ -20157,7 +25842,9 @@ 0.2, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 30000, + "released": "2026-04-17" }, "grok-4.5": { "cost": [ @@ -20166,7 +25853,9 @@ 0.5, 0.0 ], - "limit": 500000 + "limit": 500000, + "max_output": 500000, + "released": "2026-07-08" }, "kimi-k2.5": { "cost": [ @@ -20175,7 +25864,11 @@ 0.8, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-01-27" } }, "name": "DaoXE" @@ -20189,7 +25882,10 @@ 0.1, 1.25 ], - "limit": 200000 + "knowledge": "2025-02-28", + "limit": 200000, + "max_output": 64000, + "released": "2025-10-15" }, "databricks-claude-opus-4-1": { "cost": [ @@ -20198,7 +25894,10 @@ 1.5, 18.75 ], - "limit": 200000 + "knowledge": "2025-03-31", + "limit": 200000, + "max_output": 32000, + "released": "2025-08-05" }, "databricks-claude-opus-4-5": { "cost": [ @@ -20207,7 +25906,10 @@ 0.5, 6.25 ], - "limit": 200000 + "knowledge": "2025-05", + "limit": 200000, + "max_output": 64000, + "released": "2025-11-24" }, "databricks-claude-opus-4-6": { "cost": [ @@ -20216,7 +25918,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2025-05-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-05" }, "databricks-claude-opus-4-7": { "cost": [ @@ -20225,7 +25930,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-16" }, "databricks-claude-sonnet-4": { "cost": [ @@ -20234,7 +25942,10 @@ 0.3, 3.75 ], + "knowledge": "2025-03-31", "limit": 200000, + "max_output": 64000, + "released": "2025-05-22", "status": "deprecated" }, "databricks-claude-sonnet-4-5": { @@ -20244,7 +25955,10 @@ 0.3, 3.75 ], - "limit": 200000 + "knowledge": "2025-07-31", + "limit": 200000, + "max_output": 64000, + "released": "2025-09-29" }, "databricks-claude-sonnet-4-6": { "cost": [ @@ -20253,7 +25967,10 @@ 0.3, 3.75 ], - "limit": 1000000 + "knowledge": "2025-08-31", + "limit": 1000000, + "max_output": 64000, + "released": "2026-02-17" }, "databricks-gemini-2-5-flash": { "cost": [ @@ -20262,7 +25979,10 @@ 0.03, 0.0 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2025-06-17", "status": "deprecated" }, "databricks-gemini-2-5-pro": { @@ -20272,7 +25992,10 @@ 0.125, 0.0 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2025-06-17", "status": "deprecated", "tiers": [ { @@ -20296,7 +26019,10 @@ 0.025, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-03-03" }, "databricks-gemini-3-1-flash-lite-fast": { "cost": [ @@ -20305,7 +26031,10 @@ 0.045, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-03-03" }, "databricks-gemini-3-1-pro": { "cost": [ @@ -20314,7 +26043,10 @@ 0.2, 0.0 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2026-02-19", "tiers": [ { "cost": [ @@ -20337,7 +26069,10 @@ 0.36, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-02-19" }, "databricks-gemini-3-5-flash": { "cost": [ @@ -20346,7 +26081,10 @@ 0.15, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-05-19" }, "databricks-gemini-3-5-flash-fast": { "cost": [ @@ -20355,7 +26093,10 @@ 0.27, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-05-19" }, "databricks-gemini-3-flash": { "cost": [ @@ -20364,7 +26105,10 @@ 0.05, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2025-12-17" }, "databricks-gemini-3-flash-fast": { "cost": [ @@ -20373,7 +26117,10 @@ 0.09, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2025-12-17" }, "databricks-gemini-3-pro": { "cost": [ @@ -20382,7 +26129,10 @@ 0.2, 0.0 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2025-11-18", "status": "deprecated", "tiers": [ { @@ -20406,7 +26156,10 @@ 0.26, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "databricks-glm-5-2-fast": { "cost": [ @@ -20415,7 +26168,10 @@ 0.455, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "databricks-gpt-5": { "cost": [ @@ -20424,7 +26180,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "databricks-gpt-5-1": { "cost": [ @@ -20433,7 +26192,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "databricks-gpt-5-1-fast": { "cost": [ @@ -20442,7 +26204,10 @@ 0.25, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "databricks-gpt-5-2": { "cost": [ @@ -20451,7 +26216,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "databricks-gpt-5-2-fast": { "cost": [ @@ -20460,7 +26228,10 @@ 0.35, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "databricks-gpt-5-4": { "cost": [ @@ -20469,7 +26240,10 @@ 0.25, 0.0 ], + "knowledge": "2025-08-31", "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05", "tiers": [ { "cost": [ @@ -20492,7 +26266,10 @@ 0.5, 0.0 ], - "limit": 1050000 + "knowledge": "2025-08-31", + "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05" }, "databricks-gpt-5-4-mini": { "cost": [ @@ -20501,7 +26278,10 @@ 0.075, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "databricks-gpt-5-4-mini-fast": { "cost": [ @@ -20510,7 +26290,10 @@ 0.15, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "databricks-gpt-5-4-nano": { "cost": [ @@ -20519,7 +26302,10 @@ 0.02, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "databricks-gpt-5-5": { "cost": [ @@ -20528,7 +26314,10 @@ 0.5, 0.0 ], + "knowledge": "2025-12-01", "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23", "tiers": [ { "cost": [ @@ -20551,7 +26340,10 @@ 1.25, 0.0 ], - "limit": 1050000 + "knowledge": "2025-12-01", + "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23" }, "databricks-gpt-5-6-luna": { "cost": [ @@ -20560,7 +26352,10 @@ 0.02, 0.25 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -20583,7 +26378,10 @@ 0.04, 0.5 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "databricks-gpt-5-6-sol": { "cost": [ @@ -20592,7 +26390,10 @@ 0.4, 5.0 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -20615,7 +26416,10 @@ 0.8, 10.0 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "databricks-gpt-5-6-terra": { "cost": [ @@ -20624,7 +26428,10 @@ 0.2, 2.5 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -20647,7 +26454,10 @@ 0.4, 5.0 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "databricks-gpt-5-fast": { "cost": [ @@ -20656,7 +26466,10 @@ 0.25, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "databricks-gpt-5-mini": { "cost": [ @@ -20665,7 +26478,10 @@ 0.025, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "databricks-gpt-5-mini-fast": { "cost": [ @@ -20674,7 +26490,10 @@ 0.045, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "databricks-gpt-5-nano": { "cost": [ @@ -20683,7 +26502,10 @@ 0.005, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "databricks-gpt-oss-120b": { "cost": [ @@ -20692,7 +26514,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 25000, + "open": true, + "released": "2025-08-05" }, "databricks-gpt-oss-20b": { "cost": [ @@ -20701,7 +26527,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 25000, + "open": true, + "released": "2025-08-05" }, "databricks-kimi-k2-7-code": { "cost": [ @@ -20710,7 +26540,11 @@ 0.19, 0.0 ], + "knowledge": "2025-01", "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-06-12", "status": "deprecated" } }, @@ -20726,6 +26560,8 @@ 0.0 ], "limit": 256000, + "max_output": 131072, + "released": "2026-02-14", "tiers": [ { "cost": [ @@ -20749,6 +26585,8 @@ 0.0 ], "limit": 256000, + "max_output": 32000, + "released": "2026-02-14", "tiers": [ { "cost": [ @@ -20772,6 +26610,8 @@ 0.0 ], "limit": 256000, + "max_output": 128000, + "released": "2026-02-14", "tiers": [ { "cost": [ @@ -20794,7 +26634,11 @@ 0.03, 0.0 ], + "knowledge": "2025-06", "limit": 196608, + "max_output": 131072, + "open": true, + "released": "2026-02-12", "status": "deprecated" }, "MiniMaxAI/MiniMax-M2.7": { @@ -20805,6 +26649,9 @@ 0.0 ], "limit": 196608, + "max_output": 131072, + "open": true, + "released": "2026-03-18", "status": "deprecated" }, "MiniMaxAI/MiniMax-M3": { @@ -20814,7 +26661,10 @@ 0.056, 0.0 ], - "limit": 524288 + "limit": 524288, + "max_output": 512000, + "open": true, + "released": "2026-06-01" }, "Qwen/Qwen3-235B-A22B-Instruct-2507": { "cost": [ @@ -20823,7 +26673,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 16384, + "open": true, + "released": "2025-07-21" }, "Qwen/Qwen3-30B-A3B": { "cost": [ @@ -20832,7 +26685,10 @@ 0.0, 0.0 ], - "limit": 40960 + "limit": 40960, + "max_output": 16384, + "open": true, + "released": "2025-04-28" }, "Qwen/Qwen3-32B": { "cost": [ @@ -20841,7 +26697,11 @@ 0.0, 0.0 ], - "limit": 40960 + "knowledge": "2025-04", + "limit": 40960, + "max_output": 16384, + "open": true, + "released": "2025-04-28" }, "Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo": { "cost": [ @@ -20850,7 +26710,11 @@ 0.1, 0.0 ], - "limit": 262144 + "knowledge": "2025-04", + "limit": 262144, + "max_output": 66536, + "open": true, + "released": "2025-07-22" }, "Qwen/Qwen3-Max": { "cost": [ @@ -20859,7 +26723,10 @@ 0.24, 0.0 ], + "knowledge": "2025-04", "limit": 256000, + "max_output": 65536, + "released": "2025-09-23", "status": "deprecated", "tiers": [ { @@ -20895,7 +26762,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-04", + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2025-09" }, "Qwen/Qwen3-VL-235B-A22B-Instruct": { "cost": [ @@ -20904,7 +26775,11 @@ 0.11, 0.0 ], - "limit": 262144 + "knowledge": "2025-03-31", + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2025-09-23" }, "Qwen/Qwen3-VL-30B-A3B-Instruct": { "cost": [ @@ -20913,7 +26788,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2025-10-04" }, "Qwen/Qwen3.5-122B-A10B": { "cost": [ @@ -20923,6 +26801,9 @@ 0.0 ], "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-23", "status": "deprecated" }, "Qwen/Qwen3.5-27B": { @@ -20932,7 +26813,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-23" }, "Qwen/Qwen3.5-35B-A3B": { "cost": [ @@ -20941,7 +26825,11 @@ 0.05, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 81920, + "open": true, + "released": "2026-02-23" }, "Qwen/Qwen3.5-397B-A17B": { "cost": [ @@ -20950,7 +26838,11 @@ 0.22, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 81920, + "open": true, + "released": "2026-02-15" }, "Qwen/Qwen3.5-9B": { "cost": [ @@ -20959,7 +26851,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-23" }, "Qwen/Qwen3.6-27B": { "cost": [ @@ -20968,7 +26863,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-04-22" }, "Qwen/Qwen3.6-35B-A3B": { "cost": [ @@ -20977,7 +26875,10 @@ 0.1, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 81920, + "open": true, + "released": "2026-04-17" }, "Qwen/Qwen3.7-Max": { "cost": [ @@ -20987,6 +26888,8 @@ 0.0 ], "limit": 256000, + "max_output": 131072, + "released": "2026-05-21", "tiers": [ { "cost": [ @@ -21022,6 +26925,9 @@ 0.0 ], "limit": 262144, + "max_output": 131072, + "open": true, + "released": "2026-08-12", "status": "deprecated" }, "Qwen/Qwen3.8-27B": { @@ -21031,7 +26937,10 @@ 0.05, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-08-14" }, "Qwen/Qwen3.8-Flash": { "cost": [ @@ -21040,7 +26949,9 @@ 0.0141, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-08-26" }, "Qwen/Qwen3.8-Max": { "cost": [ @@ -21049,7 +26960,9 @@ 0.206, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 131072, + "released": "2026-08-03" }, "XiaomiMiMo/MiMo-V2.5": { "cost": [ @@ -21058,7 +26971,11 @@ 0.0028, 0.0 ], + "knowledge": "2024-12", "limit": 262144, + "max_output": 16384, + "open": true, + "released": "2026-04-22", "status": "deprecated" }, "XiaomiMiMo/MiMo-V2.5-Pro": { @@ -21068,7 +26985,11 @@ 0.2, 0.0 ], + "knowledge": "2024-12", "limit": 1048576, + "max_output": 16384, + "open": true, + "released": "2026-04-22", "status": "deprecated" }, "XiaomiMiMo/MiMo-V2.6-Flash": { @@ -21078,7 +26999,10 @@ 0.0028, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-09-22" }, "XiaomiMiMo/MiMo-V2.6-Pro": { "cost": [ @@ -21087,7 +27011,10 @@ 0.0036, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-09-22" }, "anthropic/claude-fable-5": { "cost": [ @@ -21096,7 +27023,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-09" }, "deepseek-ai/DeepSeek-R1-0528": { "cost": [ @@ -21105,7 +27035,11 @@ 0.35, 0.0 ], - "limit": 163840 + "knowledge": "2024-07", + "limit": 163840, + "max_output": 64000, + "open": true, + "released": "2025-05-28" }, "deepseek-ai/DeepSeek-V3": { "cost": [ @@ -21114,7 +27048,10 @@ 0.0, 0.0 ], - "limit": 163840 + "limit": 163840, + "max_output": 8192, + "open": true, + "released": "2024-12-26" }, "deepseek-ai/DeepSeek-V3-0324": { "cost": [ @@ -21124,6 +27061,9 @@ 0.0 ], "limit": 163840, + "max_output": 163840, + "open": true, + "released": "2025-03-24", "status": "deprecated" }, "deepseek-ai/DeepSeek-V3.1": { @@ -21133,7 +27073,10 @@ 0.13, 0.0 ], - "limit": 163840 + "limit": 163840, + "max_output": 8192, + "open": true, + "released": "2025-08-21" }, "deepseek-ai/DeepSeek-V3.2": { "cost": [ @@ -21142,16 +27085,24 @@ 0.13, 0.0 ], - "limit": 163840 + "knowledge": "2024-07", + "limit": 163840, + "max_output": 64000, + "open": true, + "released": "2025-12-01" }, "deepseek-ai/DeepSeek-V4-Flash": { "cost": [ 0.09, 0.18, 0.018, - 0.0 + 0.1125 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 16384, + "open": true, + "released": "2026-04-24" }, "deepseek-ai/DeepSeek-V4-Flash-0731": { "cost": [ @@ -21160,7 +27111,11 @@ 0.015, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-07-31" }, "deepseek-ai/DeepSeek-V4-Flash-Vision-Exp": { "cost": [ @@ -21169,7 +27124,10 @@ 0.014, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-08-21" }, "deepseek-ai/DeepSeek-V4-Pro": { "cost": [ @@ -21178,7 +27136,11 @@ 0.1, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 16384, + "open": true, + "released": "2026-04-24" }, "deepseek-ai/DeepSeek-V4-Pro-0813": { "cost": [ @@ -21187,7 +27149,10 @@ 0.1, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-08-13" }, "deepseek-ai/DeepSeek-V4.1-Flash": { "cost": [ @@ -21196,7 +27161,11 @@ 0.006, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-09-10" }, "deepseek-ai/DeepSeek-V4.1-Flash-1017": { "cost": [ @@ -21205,7 +27174,11 @@ 0.006, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-10-17" }, "google/gemma-3-12b-it": { "cost": [ @@ -21214,7 +27187,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-08", + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2025-03-12" }, "google/gemma-3-27b-it": { "cost": [ @@ -21223,7 +27200,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-08", + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2025-03-12" }, "google/gemma-3-4b-it": { "cost": [ @@ -21232,7 +27213,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-08", + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2025-03-12" }, "google/gemma-4-26B-A4B-it": { "cost": [ @@ -21241,7 +27226,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-04-02" }, "google/gemma-4-31B-it": { "cost": [ @@ -21250,7 +27238,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-04-02" }, "google/gemma-4-E4B-it": { "cost": [ @@ -21260,6 +27252,9 @@ 0.0 ], "limit": 131072, + "max_output": 8192, + "open": true, + "released": "2026-04-02", "status": "deprecated" }, "meta-llama/Llama-3.3-70B-Instruct-Turbo": { @@ -21269,7 +27264,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2023-12", + "limit": 131072, + "max_output": 16384, + "open": true, + "released": "2024-12-06" }, "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8": { "cost": [ @@ -21278,7 +27277,11 @@ 0.0, 0.0 ], + "knowledge": "2024-08", "limit": 1048576, + "max_output": 16384, + "open": true, + "released": "2025-04-05", "status": "deprecated" }, "meta-llama/Llama-4-Scout-17B-16E-Instruct": { @@ -21288,7 +27291,11 @@ 0.0, 0.0 ], - "limit": 327680 + "knowledge": "2024-08", + "limit": 327680, + "max_output": 16384, + "open": true, + "released": "2025-04-05" }, "meta-llama/Llama-Guard-4-12B": { "cost": [ @@ -21297,7 +27304,10 @@ 0.0, 0.0 ], - "limit": 163840 + "limit": 163840, + "max_output": 163840, + "open": true, + "released": "2025-04-29" }, "mistralai/Mistral-Small-24B-Instruct-2501": { "cost": [ @@ -21306,7 +27316,11 @@ 0.0, 0.0 ], - "limit": 32768 + "knowledge": "2023-10-31", + "limit": 32768, + "max_output": 16384, + "open": true, + "released": "2025-01-30" }, "moonshotai/Kimi-K2.5": { "cost": [ @@ -21315,7 +27329,11 @@ 0.07, 0.0 ], + "knowledge": "2025-01", "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-01-27", "status": "deprecated" }, "moonshotai/Kimi-K2.6": { @@ -21325,16 +27343,24 @@ 0.15, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 16384, + "open": true, + "released": "2026-04-20" }, "moonshotai/Kimi-K2.7-Code": { "cost": [ 0.68, 3.4, 0.136, - 0.0 + 0.85 ], + "knowledge": "2025-01", "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-06-12", "status": "deprecated" }, "moonshotai/Kimi-K3": { @@ -21342,9 +27368,12 @@ 2.85, 14.25, 0.285, - 0.0 + 3.5625 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-16" }, "nvidia/Llama-3.3-Nemotron-Super-49B-v1.5": { "cost": [ @@ -21354,6 +27383,9 @@ 0.0 ], "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2025-07-25", "status": "deprecated" }, "nvidia/Nemotron-3-Nano-30B-A3B": { @@ -21363,7 +27395,11 @@ 0.025, 0.0 ], + "knowledge": "2025-06-25", "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2025-12-15", "status": "deprecated" }, "nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning": { @@ -21374,6 +27410,9 @@ 0.0 ], "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-04-28", "status": "deprecated" }, "openai/gpt-oss-120b": { @@ -21383,7 +27422,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 16384, + "open": true, + "released": "2025-08-05" }, "openai/gpt-oss-20b": { "cost": [ @@ -21392,7 +27435,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 16384, + "open": true, + "released": "2025-08-05" }, "stepfun-ai/Step-3.7-Flash": { "cost": [ @@ -21401,7 +27448,11 @@ 0.04, 0.0 ], + "knowledge": "2026-03-01", "limit": 262144, + "max_output": 256000, + "open": true, + "released": "2026-05-29", "status": "deprecated" }, "stepfun-ai/Step-5-Preview": { @@ -21411,7 +27462,10 @@ 0.1, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1000000, + "open": true, + "released": "2026-09-16" }, "tencent/Hy3": { "cost": [ @@ -21421,6 +27475,9 @@ 0.0 ], "limit": 262144, + "max_output": 128000, + "open": true, + "released": "2026-07-06", "status": "deprecated" }, "tencent/Hy4-preview": { @@ -21430,7 +27487,10 @@ 0.042, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 64000, + "open": true, + "released": "2026-08-28" }, "thinkingmachines/Inkling": { "cost": [ @@ -21440,6 +27500,9 @@ 0.0 ], "limit": 524288, + "max_output": 1048576, + "open": true, + "released": "2026-07-15", "status": "deprecated" }, "thinkingmachines/Inkling-Small": { @@ -21449,7 +27512,10 @@ 0.1, 0.0 ], - "limit": 524288 + "limit": 524288, + "max_output": 1048576, + "open": true, + "released": "2026-07-30" }, "zai-org/GLM-4.6": { "cost": [ @@ -21458,7 +27524,11 @@ 0.1, 0.0 ], - "limit": 202752 + "knowledge": "2025-04", + "limit": 202752, + "max_output": 131072, + "open": true, + "released": "2025-09-30" }, "zai-org/GLM-4.7": { "cost": [ @@ -21467,7 +27537,11 @@ 0.08, 0.0 ], - "limit": 202752 + "knowledge": "2025-04", + "limit": 202752, + "max_output": 16384, + "open": true, + "released": "2025-12-22" }, "zai-org/GLM-4.7-Flash": { "cost": [ @@ -21476,7 +27550,11 @@ 0.01, 0.0 ], + "knowledge": "2025-04", "limit": 202752, + "max_output": 16384, + "open": true, + "released": "2026-01-19", "status": "deprecated" }, "zai-org/GLM-5": { @@ -21486,7 +27564,11 @@ 0.12, 0.0 ], + "knowledge": "2025-12", "limit": 202752, + "max_output": 16384, + "open": true, + "released": "2026-02-12", "status": "deprecated" }, "zai-org/GLM-5.1": { @@ -21496,7 +27578,11 @@ 0.205, 0.0 ], + "knowledge": "2025-04", "limit": 202752, + "max_output": 16384, + "open": true, + "released": "2026-04-07", "status": "deprecated" }, "zai-org/GLM-5.2": { @@ -21504,9 +27590,12 @@ 0.75, 2.4, 0.14, - 0.0 + 0.9375 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 32768, + "open": true, + "released": "2026-06-13" }, "zai-org/GLM-5.3": { "cost": [ @@ -21515,7 +27604,10 @@ 0.2, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "zai-org/GLM-5.3-Flash": { "cost": [ @@ -21524,7 +27616,10 @@ 0.03, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-08-26" } }, "name": "Deep Infra" @@ -21538,7 +27633,11 @@ 0.003, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 393216, + "open": true, + "released": "2026-10-17" }, "deepseek-v4-flash": { "cost": [ @@ -21547,7 +27646,11 @@ 0.003, 0.0 ], + "knowledge": "2025-05", "limit": 1048576, + "max_output": 393216, + "open": true, + "released": "2026-10-17", "status": "deprecated" }, "deepseek-v4-flash-vision-exp": { @@ -21557,7 +27660,11 @@ 0.003, 0.0 ], + "knowledge": "2025-05", "limit": 1048576, + "max_output": 393216, + "open": true, + "released": "2026-10-17", "status": "deprecated" }, "deepseek-v4-pro": { @@ -21567,7 +27674,10 @@ 0.022, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 393216, + "open": true, + "released": "2026-08-13" } }, "name": "DeepSeek" @@ -21581,7 +27691,11 @@ 0.0, 0.0 ], - "limit": 256 + "limit": 256, + "max_output": 384, + "open": true, + "released": "2021-08-30", + "type": "embedding" }, "anthropic-claude-4.5-sonnet": { "cost": [ @@ -21590,7 +27704,10 @@ 0.3, 3.75 ], + "knowledge": "2025-07-31", "limit": 200000, + "max_output": 64000, + "released": "2025-09-29", "tiers": [ { "cost": [ @@ -21613,7 +27730,10 @@ 0.3, 3.75 ], + "knowledge": "2025-08-31", "limit": 200000, + "max_output": 8192, + "released": "2026-02-17", "tiers": [ { "cost": [ @@ -21636,7 +27756,10 @@ 0.2, 2.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-30" }, "anthropic-claude-5.5-haiku": { "cost": [ @@ -21645,7 +27768,10 @@ 0.01, 0.125 ], + "knowledge": "2026-06", "limit": 1000000, + "max_output": 128000, + "released": "2026-10-07", "tiers": [ { "cost": [ @@ -21668,7 +27794,10 @@ 1.0, 12.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-09" }, "anthropic-claude-fable-5.1": { "cost": [ @@ -21677,7 +27806,10 @@ 0.25, 12.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-01" }, "anthropic-claude-haiku-4.5": { "cost": [ @@ -21686,7 +27818,10 @@ 0.1, 1.25 ], - "limit": 200000 + "knowledge": "2025-02-28", + "limit": 200000, + "max_output": 8192, + "released": "2025-10-15" }, "anthropic-claude-opus-4.5": { "cost": [ @@ -21695,7 +27830,10 @@ 0.5, 6.25 ], - "limit": 200000 + "knowledge": "2025-05", + "limit": 200000, + "max_output": 8192, + "released": "2025-11-24" }, "anthropic-claude-opus-4.6": { "cost": [ @@ -21704,7 +27842,10 @@ 0.5, 6.25 ], + "knowledge": "2025-05-31", "limit": 200000, + "max_output": 8192, + "released": "2026-02-05", "tiers": [ { "cost": [ @@ -21727,7 +27868,10 @@ 0.5, 6.25 ], - "limit": 200000 + "knowledge": "2026-01-31", + "limit": 200000, + "max_output": 8192, + "released": "2026-04-16" }, "anthropic-claude-opus-4.8": { "cost": [ @@ -21736,7 +27880,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-28" }, "anthropic-claude-opus-5": { "cost": [ @@ -21745,7 +27892,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-05", + "limit": 1000000, + "max_output": 128000, + "released": "2026-07-24" }, "anthropic-claude-opus-5.5": { "cost": [ @@ -21754,7 +27904,10 @@ 0.2, 5.0 ], + "knowledge": "2026-06", "limit": 1000000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -21777,7 +27930,10 @@ 0.2, 2.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-28" }, "arcee-trinity-large-thinking": { "cost": [ @@ -21786,7 +27942,10 @@ 0.06, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 32000, + "open": true, + "released": "2026-04-01" }, "bge-m3": { "cost": [ @@ -21795,7 +27954,11 @@ 0.0, 0.0 ], - "limit": 8192 + "limit": 8192, + "max_output": 1024, + "open": true, + "released": "2024-01-30", + "type": "embedding" }, "bge-reranker-v2-m3": { "cost": [ @@ -21804,7 +27967,11 @@ 0.0, 0.0 ], - "limit": 8192 + "limit": 8192, + "max_output": 1, + "open": true, + "released": "2024-03-15", + "type": "reranking" }, "deepseek-3.2": { "cost": [ @@ -21813,7 +27980,11 @@ 0.15, 0.0 ], - "limit": 163840 + "knowledge": "2024-07", + "limit": 163840, + "max_output": 163840, + "open": true, + "released": "2025-12-01" }, "deepseek-4-flash": { "cost": [ @@ -21822,7 +27993,11 @@ 0.028, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "deepseek-v4-flash-0731": { "cost": [ @@ -21831,7 +28006,11 @@ 0.028, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-07-31" }, "deepseek-v4-pro": { "cost": [ @@ -21840,7 +28019,11 @@ 0.348, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "deepseek-v4-pro-0813": { "cost": [ @@ -21849,7 +28032,10 @@ 0.044, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-08-13" }, "deepseek-v4.1-flash": { "cost": [ @@ -21858,7 +28044,11 @@ 0.006, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-09-10" }, "deepseek-v4.1-flash-1017": { "cost": [ @@ -21867,7 +28057,11 @@ 0.006, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-10-17" }, "e5-large-v2": { "cost": [ @@ -21876,7 +28070,11 @@ 0.0, 0.0 ], - "limit": 512 + "limit": 512, + "max_output": 1024, + "open": true, + "released": "2023-05", + "type": "embedding" }, "gemma-4-31B-it": { "cost": [ @@ -21885,7 +28083,11 @@ 0.036, 0.0 ], - "limit": 256000 + "knowledge": "2025-01", + "limit": 256000, + "max_output": 8192, + "open": true, + "released": "2026-04-02" }, "glm-5.2": { "cost": [ @@ -21894,7 +28096,10 @@ 0.21, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "glm-5.3": { "cost": [ @@ -21903,7 +28108,10 @@ 0.26, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 128000, + "open": true, + "released": "2026-08-14" }, "glm-5.3-flash": { "cost": [ @@ -21912,7 +28120,10 @@ 0.03, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-08-26" }, "gte-large-en-v1.5": { "cost": [ @@ -21921,7 +28132,11 @@ 0.0, 0.0 ], - "limit": 8192 + "limit": 8192, + "max_output": 1024, + "open": true, + "released": "2024-03-27", + "type": "embedding" }, "kimi-k2.6": { "cost": [ @@ -21930,7 +28145,11 @@ 0.19, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-20" }, "kimi-k3": { "cost": [ @@ -21939,7 +28158,10 @@ 0.3, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-16" }, "llama-4-maverick": { "cost": [ @@ -21948,7 +28170,11 @@ 0.05, 0.0 ], - "limit": 128000 + "knowledge": "2024-08", + "limit": 128000, + "max_output": 16384, + "open": true, + "released": "2025-04-05" }, "mimo-v2.5-pro": { "cost": [ @@ -21957,7 +28183,11 @@ 0.16, 0.0 ], - "limit": 262144 + "knowledge": "2024-12", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-22" }, "minimax-m2.5": { "cost": [ @@ -21966,7 +28196,22 @@ 0.06, 0.0 ], - "limit": 65536 + "knowledge": "2025-08", + "limit": 65536, + "max_output": 65536, + "open": true, + "released": "2026-02-12" + }, + "minimax-m3.1-flash": { + "cost": [ + 0.15, + 0.6, + 0.015, + 0.0 + ], + "limit": 1048576, + "max_output": 1048576, + "released": "2026-10-19" }, "mistral-3-14B": { "cost": [ @@ -21975,7 +28220,10 @@ 0.04, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 128000, + "open": true, + "released": "2025-12-02" }, "multi-qa-mpnet-base-dot-v1": { "cost": [ @@ -21984,7 +28232,11 @@ 0.0, 0.0 ], - "limit": 512 + "limit": 512, + "max_output": 768, + "open": true, + "released": "2021-08-23", + "type": "embedding" }, "nemotron-3-nano-omni": { "cost": [ @@ -21993,7 +28245,10 @@ 0.1, 0.0 ], - "limit": 65536 + "limit": 65536, + "max_output": 65536, + "open": true, + "released": "2026-04-28" }, "nemotron-3-ultra-550b": { "cost": [ @@ -22002,7 +28257,11 @@ 0.18, 0.0 ], - "limit": 131072 + "knowledge": "2025-09", + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2026-06-04" }, "nemotron-3.5-super-vl": { "cost": [ @@ -22011,7 +28270,10 @@ 0.06, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-10-15" }, "nemotron-nano-12b-v2-vl": { "cost": [ @@ -22020,7 +28282,10 @@ 0.04, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 16384, + "open": true, + "released": "2025-10-28" }, "openai-gpt-4.1": { "cost": [ @@ -22029,7 +28294,10 @@ 0.5, 0.0 ], - "limit": 1047576 + "knowledge": "2024-04", + "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14" }, "openai-gpt-4o": { "cost": [ @@ -22038,7 +28306,10 @@ 1.25, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-05-13" }, "openai-gpt-4o-mini": { "cost": [ @@ -22047,7 +28318,10 @@ 0.075, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-07-18" }, "openai-gpt-5": { "cost": [ @@ -22056,7 +28330,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "openai-gpt-5-mini": { "cost": [ @@ -22065,7 +28342,10 @@ 0.025, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "openai-gpt-5-nano": { "cost": [ @@ -22074,7 +28354,10 @@ 0.005, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "openai-gpt-5.2": { "cost": [ @@ -22083,7 +28366,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "openai-gpt-5.2-pro": { "cost": [ @@ -22092,7 +28378,10 @@ 0.0, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "openai-gpt-5.3-codex": { "cost": [ @@ -22101,7 +28390,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-02-05" }, "openai-gpt-5.4": { "cost": [ @@ -22110,7 +28402,10 @@ 0.25, 0.0 ], + "knowledge": "2025-08-31", "limit": 400000, + "max_output": 128000, + "released": "2026-03-05", "tiers": [ { "cost": [ @@ -22133,7 +28428,10 @@ 0.075, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "openai-gpt-5.4-nano": { "cost": [ @@ -22142,7 +28440,10 @@ 0.02, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "openai-gpt-5.4-pro": { "cost": [ @@ -22151,7 +28452,10 @@ 0.0, 0.0 ], + "knowledge": "2025-08-31", "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05", "tiers": [ { "cost": [ @@ -22174,7 +28478,10 @@ 0.5, 0.0 ], + "knowledge": "2025-12-01", "limit": 1000000, + "max_output": 128000, + "released": "2026-04-23", "tiers": [ { "cost": [ @@ -22197,7 +28504,10 @@ 0.02, 0.25 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -22220,7 +28530,10 @@ 0.4, 5.0 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -22243,7 +28556,10 @@ 0.2, 2.5 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -22266,7 +28582,10 @@ 0.1, 2.5 ], + "knowledge": "2026-04-30", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-29", "tiers": [ { "cost": [ @@ -22289,7 +28608,10 @@ 1.0, 12.5 ], + "knowledge": "2026-04-30", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-04", "tiers": [ { "cost": [ @@ -22312,7 +28634,10 @@ 0.01, 0.125 ], + "knowledge": "2026-05-18", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -22335,7 +28660,10 @@ 0.2, 2.5 ], + "knowledge": "2026-04-20", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -22357,7 +28685,9 @@ 40.0, 1.25, 0.0 - ] + ], + "released": "2025-04-24", + "type": "image" }, "openai-gpt-image-1.5": { "cost": [ @@ -22365,7 +28695,10 @@ 10.0, 1.0, 0.0 - ] + ], + "max_output": 16384, + "released": "2025-11-25", + "type": "image" }, "openai-gpt-image-2": { "cost": [ @@ -22373,7 +28706,10 @@ 30.0, 0.0, 0.0 - ] + ], + "max_output": 16384, + "released": "2026-04-21", + "type": "image" }, "openai-gpt-oss-120b": { "cost": [ @@ -22382,7 +28718,11 @@ 0.02, 0.0 ], - "limit": 128000 + "knowledge": "2024-06", + "limit": 128000, + "max_output": 4096, + "open": true, + "released": "2025-08-05" }, "openai-gpt-oss-20b": { "cost": [ @@ -22391,7 +28731,11 @@ 0.01, 0.0 ], - "limit": 128000 + "knowledge": "2024-06", + "limit": 128000, + "max_output": 4096, + "open": true, + "released": "2025-08-05" }, "openai-o1": { "cost": [ @@ -22400,7 +28744,10 @@ 7.5, 0.0 ], - "limit": 200000 + "knowledge": "2023-09", + "limit": 200000, + "max_output": 100000, + "released": "2024-12-05" }, "openai-o3": { "cost": [ @@ -22409,7 +28756,10 @@ 0.5, 0.0 ], - "limit": 200000 + "knowledge": "2024-05", + "limit": 200000, + "max_output": 100000, + "released": "2025-04-16" }, "openai-o3-mini": { "cost": [ @@ -22418,7 +28768,10 @@ 0.55, 0.0 ], - "limit": 200000 + "knowledge": "2024-05", + "limit": 200000, + "max_output": 100000, + "released": "2024-12-20" }, "qwen3-embedding-0.6b": { "cost": [ @@ -22428,7 +28781,11 @@ 0.0 ], "limit": 8000, - "status": "beta" + "max_output": 1024, + "open": true, + "released": "2025-06-03", + "status": "beta", + "type": "embedding" }, "qwen3.5-397b-a17b": { "cost": [ @@ -22437,7 +28794,10 @@ 0.111, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2026-02-15" }, "qwen3.8-max": { "cost": [ @@ -22446,7 +28806,9 @@ 0.2, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 262144, + "released": "2026-08-03" }, "reflection-beam": { "cost": [ @@ -22455,7 +28817,9 @@ 0.04, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "released": "2026-10-21" } }, "name": "DigitalOcean" @@ -22469,7 +28833,11 @@ 0.0, 0.0 ], - "limit": 200000 + "knowledge": "2025-04", + "limit": 200000, + "max_output": 128000, + "open": true, + "released": "2025-12-22" }, "glm-5": { "cost": [ @@ -22478,7 +28846,10 @@ 0.0, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 128000, + "open": true, + "released": "2026-02-12" }, "glm-5.1": { "cost": [ @@ -22488,6 +28859,9 @@ 0.0 ], "limit": 200000, + "max_output": 128000, + "open": true, + "released": "2026-04-07", "status": "deprecated" }, "glm-5.2": { @@ -22498,6 +28872,9 @@ 0.0 ], "limit": 1000000, + "max_output": 128000, + "open": true, + "released": "2026-06-13", "status": "deprecated" }, "gpt-oss-120b": { @@ -22507,7 +28884,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "minimax-m2.5": { "cost": [ @@ -22517,6 +28898,9 @@ 0.0 ], "limit": 200000, + "max_output": 32000, + "open": true, + "released": "2026-02-12", "status": "deprecated" } }, @@ -22531,7 +28915,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-12", + "limit": 131072, + "max_output": 32000, + "open": true, + "released": "2025-01-20" }, "public/deepseek-v3": { "cost": [ @@ -22540,7 +28928,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-07", + "limit": 131072, + "max_output": 8192, + "open": true, + "released": "2024-12-26" }, "public/minimax-m25": { "cost": [ @@ -22549,7 +28941,10 @@ 0.0, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-02-12" } }, "name": "D.Run (China)" @@ -22563,7 +28958,11 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "DeepSeek-V4-Pro": { "cost": [ @@ -22572,7 +28971,11 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "GLM-5.1": { "cost": [ @@ -22581,7 +28984,10 @@ 0.0, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 131072, + "open": true, + "released": "2026-04-07" }, "Kimi-K2.6": { "cost": [ @@ -22590,7 +28996,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-20" } }, "name": "EBCloud" @@ -22605,6 +29015,8 @@ 0.0 ], "limit": 262144, + "max_output": 65536, + "released": "2026-07-19", "status": "beta" } }, @@ -22619,7 +29031,10 @@ 0.015, 0.0 ], - "limit": 300000 + "knowledge": "2024-10", + "limit": 300000, + "max_output": 10000, + "released": "2024-12-03" }, "amazon/amazon.nova-lite-v1:0@us": { "cost": [ @@ -22628,7 +29043,10 @@ 0.015, 0.0 ], - "limit": 300000 + "knowledge": "2024-10", + "limit": 300000, + "max_output": 10000, + "released": "2024-12-03" }, "amazon/amazon.nova-micro-v1:0": { "cost": [ @@ -22637,7 +29055,10 @@ 0.00875, 0.0 ], - "limit": 128000 + "knowledge": "2024-10", + "limit": 128000, + "max_output": 10000, + "released": "2024-12-03" }, "amazon/amazon.nova-micro-v1:0@us": { "cost": [ @@ -22646,7 +29067,10 @@ 0.00875, 0.0 ], - "limit": 128000 + "knowledge": "2024-10", + "limit": 128000, + "max_output": 10000, + "released": "2024-12-03" }, "amazon/amazon.nova-pro-v1:0": { "cost": [ @@ -22655,7 +29079,10 @@ 0.2, 0.0 ], - "limit": 300000 + "knowledge": "2024-10", + "limit": 300000, + "max_output": 10000, + "released": "2024-12-03" }, "amazon/amazon.nova-pro-v1:0@us": { "cost": [ @@ -22664,7 +29091,10 @@ 0.2, 0.0 ], - "limit": 300000 + "knowledge": "2024-10", + "limit": 300000, + "max_output": 10000, + "released": "2024-12-03" }, "amazon/google.gemma-3-12b-it": { "cost": [ @@ -22673,7 +29103,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-08", + "limit": 128000, + "max_output": 131072, + "open": true, + "released": "2025-03-12" }, "amazon/google.gemma-3-12b-it@us": { "cost": [ @@ -22682,7 +29116,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-08", + "limit": 128000, + "max_output": 131072, + "open": true, + "released": "2025-03-12" }, "amazon/google.gemma-3-27b-it": { "cost": [ @@ -22691,7 +29129,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-08", + "limit": 128000, + "max_output": 131072, + "open": true, + "released": "2025-03-12" }, "amazon/google.gemma-3-27b-it@us": { "cost": [ @@ -22700,7 +29142,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-08", + "limit": 128000, + "max_output": 131072, + "open": true, + "released": "2025-03-12" }, "amazon/google.gemma-3-4b-it": { "cost": [ @@ -22709,7 +29155,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-08", + "limit": 128000, + "max_output": 131072, + "open": true, + "released": "2025-03-12" }, "amazon/google.gemma-3-4b-it@us": { "cost": [ @@ -22718,7 +29168,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-08", + "limit": 128000, + "max_output": 131072, + "open": true, + "released": "2025-03-12" }, "amazon/mistral.pixtral-large-2502-v1:0": { "cost": [ @@ -22727,7 +29181,9 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 8192, + "released": "2025-04-08" }, "amazon/mistral.pixtral-large-2502-v1:0@us": { "cost": [ @@ -22736,7 +29192,9 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 8192, + "released": "2025-04-08" }, "amazon/mistral.voxtral-mini-3b-2507": { "cost": [ @@ -22745,7 +29203,10 @@ 0.0, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 32768, + "open": true, + "released": "2025-07-15" }, "amazon/mistral.voxtral-mini-3b-2507@us": { "cost": [ @@ -22754,7 +29215,10 @@ 0.0, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 32768, + "open": true, + "released": "2025-07-15" }, "amazon/mistral.voxtral-small-24b-2507": { "cost": [ @@ -22763,7 +29227,10 @@ 0.0, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 32768, + "open": true, + "released": "2025-07-15" }, "amazon/mistral.voxtral-small-24b-2507@us": { "cost": [ @@ -22772,7 +29239,10 @@ 0.0, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 32768, + "open": true, + "released": "2025-07-15" }, "amazon/moonshot.kimi-k2-thinking": { "cost": [ @@ -22781,7 +29251,11 @@ 0.0, 0.0 ], - "limit": 256000 + "knowledge": "2024-08", + "limit": 256000, + "max_output": 262144, + "open": true, + "released": "2025-11-06" }, "amazon/moonshotai.kimi-k2.5": { "cost": [ @@ -22790,7 +29264,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-01-27" }, "amazon/openai.gpt-oss-safeguard-20b": { "cost": [ @@ -22799,7 +29277,10 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 131072, + "open": true, + "released": "2025-10-29" }, "amazon/openai.gpt-oss-safeguard-20b@us": { "cost": [ @@ -22808,7 +29289,10 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 131072, + "open": true, + "released": "2025-10-29" }, "amazon/qwen.qwen3-coder-next": { "cost": [ @@ -22817,7 +29301,11 @@ 0.0, 0.0 ], - "limit": 256000 + "knowledge": "2025-09", + "limit": 256000, + "max_output": 65536, + "open": true, + "released": "2026-02-03" }, "amazon/zai.glm-4.7-flash": { "cost": [ @@ -22826,7 +29314,11 @@ 0.0, 0.0 ], - "limit": 203000 + "knowledge": "2025-04", + "limit": 203000, + "max_output": 131072, + "open": true, + "released": "2026-01-19" }, "amazon/zai.glm-4.7-flash@us": { "cost": [ @@ -22835,7 +29327,11 @@ 0.0, 0.0 ], - "limit": 203000 + "knowledge": "2025-04", + "limit": 203000, + "max_output": 131072, + "open": true, + "released": "2026-01-19" }, "anthropic/claude-fable-5": { "cost": [ @@ -22844,7 +29340,10 @@ 1.0, 12.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-09" }, "anthropic/claude-fable-5-1": { "cost": [ @@ -22853,7 +29352,10 @@ 0.25, 12.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-01" }, "anthropic/claude-fable-latest": { "cost": [ @@ -22862,7 +29364,10 @@ 0.25, 12.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-01" }, "anthropic/claude-haiku-5-5": { "cost": [ @@ -22871,7 +29376,10 @@ 0.01, 0.125 ], + "knowledge": "2026-06", "limit": 1000000, + "max_output": 128000, + "released": "2026-10-07", "tiers": [ { "cost": [ @@ -22894,7 +29402,10 @@ 0.01, 0.125 ], + "knowledge": "2026-06", "limit": 1000000, + "max_output": 128000, + "released": "2026-10-07", "tiers": [ { "cost": [ @@ -22917,7 +29428,10 @@ 0.5, 6.25 ], - "limit": 200000 + "knowledge": "2025-05", + "limit": 200000, + "max_output": 64000, + "released": "2025-11-24" }, "anthropic/claude-opus-4-5-20251101": { "cost": [ @@ -22926,7 +29440,10 @@ 0.5, 6.25 ], - "limit": 200000 + "knowledge": "2025-05", + "limit": 200000, + "max_output": 64000, + "released": "2025-11-24" }, "anthropic/claude-opus-4-6": { "cost": [ @@ -22935,7 +29452,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2025-05-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-05" }, "anthropic/claude-opus-4-7": { "cost": [ @@ -22944,7 +29464,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-16" }, "anthropic/claude-opus-4-8": { "cost": [ @@ -22953,7 +29476,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-28" }, "anthropic/claude-opus-5": { "cost": [ @@ -22962,7 +29488,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-05", + "limit": 1000000, + "max_output": 128000, + "released": "2026-07-24" }, "anthropic/claude-opus-5-5": { "cost": [ @@ -22971,7 +29500,10 @@ 0.2, 5.0 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-22" }, "anthropic/claude-opus-latest": { "cost": [ @@ -22980,7 +29512,10 @@ 0.2, 5.0 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-22" }, "anthropic/claude-sonnet-4-6": { "cost": [ @@ -22989,7 +29524,10 @@ 0.3, 3.75 ], - "limit": 1000000 + "knowledge": "2025-08-31", + "limit": 1000000, + "max_output": 64000, + "released": "2026-02-17" }, "anthropic/claude-sonnet-5": { "cost": [ @@ -22998,7 +29536,10 @@ 0.2, 2.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-30" }, "anthropic/claude-sonnet-5-5": { "cost": [ @@ -23007,7 +29548,10 @@ 0.1, 2.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-28" }, "anthropic/claude-sonnet-latest": { "cost": [ @@ -23016,7 +29560,162 @@ 0.1, 2.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-28" + }, + "arkanecloud/Qwen/Qwen3-235B-A22B-Instruct-2507": { + "cost": [ + 0.25, + 1.0, + 0.2, + 0.0 + ], + "limit": 262000, + "max_output": 16384, + "open": true, + "released": "2025-07-21" + }, + "arkanecloud/deepseek-ai/DeepSeek-V4.1-Flash": { + "cost": [ + 0.3, + 1.2, + 0.075, + 0.0 + ], + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-09-10" + }, + "arkanecloud/meta-llama/Llama-3.1-70B-Instruct": { + "cost": [ + 0.8, + 0.8, + 0.16, + 0.0 + ], + "knowledge": "2023-12", + "limit": 131072, + "max_output": 4096, + "open": true, + "released": "2024-07-23" + }, + "arkanecloud/meta-llama/Llama-3.1-8B-Instruct": { + "cost": [ + 0.15, + 0.15, + 0.03, + 0.0 + ], + "knowledge": "2023-12", + "limit": 131072, + "max_output": 4096, + "open": true, + "released": "2024-07-23" + }, + "arkanecloud/meta-llama/Llama-3.3-70B-Instruct": { + "cost": [ + 0.7, + 0.7, + 0.2, + 0.0 + ], + "knowledge": "2023-12", + "limit": 128000, + "max_output": 4096, + "open": true, + "released": "2024-12-06" + }, + "arkanecloud/ministral-14b": { + "cost": [ + 0.15, + 0.15, + 0.15, + 0.0 + ], + "limit": 32768, + "max_output": 262144, + "open": true, + "released": "2025-12-02" + }, + "arkanecloud/nvidia/nemotron-3-super-120b-a12b": { + "cost": [ + 0.4, + 0.8, + 0.1, + 0.0 + ], + "knowledge": "2025-06", + "limit": 256000, + "max_output": 262144, + "open": true, + "released": "2026-03-11" + }, + "arkanecloud/nvidia/nemotron-3-ultra-550b-a55b": { + "cost": [ + 0.6, + 3.5, + 0.2, + 0.0 + ], + "knowledge": "2025-09", + "limit": 512288, + "max_output": 128000, + "open": true, + "released": "2026-06-04" + }, + "arkanecloud/openai/gpt-oss-120b": { + "cost": [ + 0.15, + 0.6, + 0.1, + 0.0 + ], + "knowledge": "2024-06", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05" + }, + "arkanecloud/openai/gpt-oss-20b": { + "cost": [ + 0.07, + 0.25, + 0.05, + 0.0 + ], + "knowledge": "2024-06", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05" + }, + "azure/gpt-4.1-nano": { + "cost": [ + 0.1, + 0.4, + 0.025, + 0.0 + ], + "knowledge": "2024-04", + "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14" + }, + "azure/gpt-4.1-nano@eu": { + "cost": [ + 0.11, + 0.44, + 0.0275, + 0.0 + ], + "knowledge": "2024-04", + "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14" }, "azure/gpt-5.1-codex": { "cost": [ @@ -23025,7 +29724,10 @@ 0.125, 0.0 ], - "limit": 272000 + "knowledge": "2024-09-30", + "limit": 272000, + "max_output": 128000, + "released": "2025-11-13" }, "azure/gpt-5.1-codex-max": { "cost": [ @@ -23034,7 +29736,10 @@ 0.125, 0.0 ], - "limit": 272000 + "knowledge": "2024-09-30", + "limit": 272000, + "max_output": 128000, + "released": "2025-11-13" }, "azure/gpt-5.1-codex-mini": { "cost": [ @@ -23043,7 +29748,10 @@ 0.025, 0.0 ], - "limit": 272000 + "knowledge": "2024-09-30", + "limit": 272000, + "max_output": 128000, + "released": "2025-11-13" }, "azure/gpt-5.2-codex": { "cost": [ @@ -23052,7 +29760,10 @@ 0.175, 0.0 ], - "limit": 272000 + "knowledge": "2025-08-31", + "limit": 272000, + "max_output": 128000, + "released": "2025-12-11" }, "cerebras/gpt-oss-120b": { "cost": [ @@ -23061,7 +29772,11 @@ 0.35, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "cloudflare/@cf/aisingapore/gemma-sea-lion-v4-27b-it": { "cost": [ @@ -23070,7 +29785,10 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 128000, + "open": true, + "released": "2025-09-23" }, "cloudflare/@cf/deepseek-ai/deepseek-v4-flash-0731": { "cost": [ @@ -23079,7 +29797,11 @@ 0.014, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-07-31" }, "cloudflare/@cf/deepseek-ai/deepseek-v4-pro-0813": { "cost": [ @@ -23088,7 +29810,10 @@ 0.044, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-08-13" }, "cloudflare/@cf/deepseek-ai/deepseek-v4.1-flash-1017": { "cost": [ @@ -23097,7 +29822,11 @@ 0.006, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-10-17" }, "cloudflare/@cf/meta/llama-3.2-1b-instruct": { "cost": [ @@ -23106,7 +29835,11 @@ 0.0, 0.0 ], - "limit": 60000 + "knowledge": "2023-12", + "limit": 60000, + "max_output": 32000, + "open": true, + "released": "2024-09-25" }, "cloudflare/@cf/meta/llama-3.2-3b-instruct": { "cost": [ @@ -23115,7 +29848,11 @@ 0.0, 0.0 ], - "limit": 80000 + "knowledge": "2023-12", + "limit": 80000, + "max_output": 131072, + "open": true, + "released": "2024-09-25" }, "cloudflare/@cf/meta/llama-guard-3-8b": { "cost": [ @@ -23124,7 +29861,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2023-12", + "limit": 131072, + "max_output": 4096, + "open": true, + "released": "2024-07-23" }, "cloudflare/@cf/mistralai/mistral-small-3.1-24b-instruct": { "cost": [ @@ -23133,7 +29874,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2023-10-31", + "limit": 128000, + "max_output": 102400, + "open": true, + "released": "2025-03-17" }, "cloudflare/@cf/openai/gpt-oss-120b": { "cost": [ @@ -23142,7 +29887,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-06", + "limit": 128000, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "cloudflare/@cf/openai/gpt-oss-20b": { "cost": [ @@ -23151,7 +29900,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-06", + "limit": 128000, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "cloudflare/@cf/qwen/qwen2.5-coder-32b-instruct": { "cost": [ @@ -23160,7 +29913,10 @@ 0.0, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 8192, + "open": true, + "released": "2024-11-12" }, "cloudflare/@cf/zai-org/glm-4.7-flash": { "cost": [ @@ -23169,7 +29925,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2025-04", + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2026-01-19" }, "cohere/c4ai-aya-expanse-32b": { "cost": [ @@ -23178,7 +29938,10 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 4000, + "open": true, + "released": "2024-10-24" }, "cohere/command-a-03-2025": { "cost": [ @@ -23187,7 +29950,11 @@ 0.0, 0.0 ], - "limit": 288000 + "knowledge": "2024-06-01", + "limit": 288000, + "max_output": 8000, + "open": true, + "released": "2025-03-13" }, "cohere/command-r-08-2024": { "cost": [ @@ -23196,7 +29963,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-06-01", + "limit": 128000, + "max_output": 4000, + "open": true, + "released": "2024-08-30" }, "cohere/command-r-plus-08-2024": { "cost": [ @@ -23205,7 +29976,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-06-01", + "limit": 128000, + "max_output": 4000, + "open": true, + "released": "2024-08-30" }, "cohere/command-r7b-12-2024": { "cost": [ @@ -23214,7 +29989,11 @@ 0.0, 0.0 ], - "limit": 132000 + "knowledge": "2024-06-01", + "limit": 132000, + "max_output": 4000, + "open": true, + "released": "2024-12-13" }, "databricks/databricks-deepseek-v4-flash-0731": { "cost": [ @@ -23223,7 +30002,11 @@ 0.014, 0.14 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-07-31" }, "databricks/databricks-deepseek-v4-pro-0813": { "cost": [ @@ -23232,7 +30015,10 @@ 0.132, 1.31999 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-08-13" }, "databricks/databricks-gpt-oss-120b": { "cost": [ @@ -23241,7 +30027,11 @@ 0.015001, 0.15001 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "databricks/databricks-gpt-oss-120b@eu": { "cost": [ @@ -23250,7 +30040,11 @@ 0.015001, 0.15001 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "databricks/databricks-gpt-oss-20b": { "cost": [ @@ -23259,7 +30053,11 @@ 0.007, 0.07 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "databricks/databricks-gpt-oss-20b@eu": { "cost": [ @@ -23268,7 +30066,11 @@ 0.007, 0.07 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "databricks/databricks-inkling": { "cost": [ @@ -23277,7 +30079,10 @@ 0.1, 1.00002 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 1048576, + "open": true, + "released": "2026-07-15" }, "databricks/databricks-qwen3-next-80b-a3b-instruct": { "cost": [ @@ -23286,7 +30091,11 @@ 0.015001, 0.15001 ], - "limit": 262144 + "knowledge": "2025-04", + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2025-09" }, "databricks/databricks-qwen3-next-80b-a3b-instruct@eu": { "cost": [ @@ -23295,7 +30104,11 @@ 0.015001, 0.15001 ], - "limit": 262144 + "knowledge": "2025-04", + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2025-09" }, "deepinfra/ByteDance/Seed-2.0-code": { "cost": [ @@ -23304,7 +30117,9 @@ 0.1, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 131072, + "released": "2026-02-14" }, "deepinfra/ByteDance/Seed-2.0-mini": { "cost": [ @@ -23313,7 +30128,9 @@ 0.02, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 32000, + "released": "2026-02-14" }, "deepinfra/Gryphe/MythoMax-L2-13b": { "cost": [ @@ -23322,7 +30139,10 @@ 0.0, 0.0 ], - "limit": 4096 + "limit": 4096, + "max_output": 3200, + "open": true, + "released": "2023-08-10" }, "deepinfra/NousResearch/Hermes-3-Llama-3.1-405B": { "cost": [ @@ -23331,7 +30151,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2023-12-31", + "limit": 131072, + "max_output": 16384, + "open": true, + "released": "2024-08-16" }, "deepinfra/NousResearch/Hermes-3-Llama-3.1-70B": { "cost": [ @@ -23340,7 +30164,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2023-12-31", + "limit": 131072, + "max_output": 16384, + "open": true, + "released": "2024-08-18" }, "deepinfra/Qwen/Qwen2.5-7B-Instruct": { "cost": [ @@ -23349,7 +30177,10 @@ 0.0, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 8192, + "open": true, + "released": "2024-09-19" }, "deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507": { "cost": [ @@ -23358,7 +30189,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 16384, + "open": true, + "released": "2025-07-21" }, "deepinfra/Qwen/Qwen3-235B-A22B-Thinking-2507": { "cost": [ @@ -23367,7 +30201,10 @@ 0.2, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 81920, + "open": true, + "released": "2025-07-25" }, "deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct": { "cost": [ @@ -23376,7 +30213,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-04", + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2025-07-22" }, "deepinfra/Qwen/Qwen3-Max": { "cost": [ @@ -23385,7 +30226,10 @@ 0.24, 0.0 ], - "limit": 256000 + "knowledge": "2025-04", + "limit": 256000, + "max_output": 65536, + "released": "2025-09-23" }, "deepinfra/Qwen/Qwen3-Next-80B-A3B-Instruct": { "cost": [ @@ -23394,7 +30238,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-04", + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2025-09" }, "deepinfra/Qwen/Qwen3-VL-235B-A22B-Instruct": { "cost": [ @@ -23403,7 +30251,11 @@ 0.11, 0.0 ], - "limit": 262144 + "knowledge": "2025-03-31", + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2025-09-23" }, "deepinfra/Qwen/Qwen3-VL-30B-A3B-Instruct": { "cost": [ @@ -23412,7 +30264,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2025-10-04" }, "deepinfra/deepseek-ai/DeepSeek-R1": { "cost": [ @@ -23421,7 +30276,11 @@ 0.0, 0.0 ], - "limit": 163840 + "knowledge": "2024-07", + "limit": 163840, + "max_output": 32768, + "open": true, + "released": "2025-01-20" }, "deepinfra/deepseek-ai/DeepSeek-R1-0528": { "cost": [ @@ -23430,7 +30289,10 @@ 0.35, 0.0 ], - "limit": 163840 + "limit": 163840, + "max_output": 32768, + "open": true, + "released": "2025-05-28" }, "deepinfra/deepseek-ai/DeepSeek-V3": { "cost": [ @@ -23439,7 +30301,10 @@ 0.0, 0.0 ], - "limit": 163840 + "limit": 163840, + "max_output": 8192, + "open": true, + "released": "2024-12-26" }, "deepinfra/deepseek-ai/DeepSeek-V3-0324": { "cost": [ @@ -23448,7 +30313,10 @@ 0.135, 0.0 ], - "limit": 163840 + "limit": 163840, + "max_output": 163840, + "open": true, + "released": "2025-03-24" }, "deepinfra/deepseek-ai/DeepSeek-V4-Flash-0731": { "cost": [ @@ -23457,7 +30325,11 @@ 0.015, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-07-31" }, "deepinfra/deepseek-ai/DeepSeek-V4-Pro-0813": { "cost": [ @@ -23466,7 +30338,10 @@ 0.1, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-08-13" }, "deepinfra/deepseek-ai/DeepSeek-V4.1-Flash": { "cost": [ @@ -23475,7 +30350,11 @@ 0.006, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-09-10" }, "deepinfra/deepseek-ai/DeepSeek-V4.1-Flash-1017": { "cost": [ @@ -23484,7 +30363,11 @@ 0.006, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-10-17" }, "deepinfra/google/gemma-3-12b-it": { "cost": [ @@ -23493,7 +30376,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-08", + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2025-03-12" }, "deepinfra/google/gemma-3-27b-it": { "cost": [ @@ -23502,7 +30389,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-08", + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2025-03-12" }, "deepinfra/google/gemma-3-4b-it": { "cost": [ @@ -23511,7 +30402,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-08", + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2025-03-12" }, "deepinfra/ibm-granite/granite-4.2-8b": { "cost": [ @@ -23520,7 +30415,10 @@ 0.015, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 117964, + "open": true, + "released": "2026-08-25" }, "deepinfra/meta-llama/Llama-3.2-11B-Vision-Instruct": { "cost": [ @@ -23529,7 +30427,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2023-12", + "limit": 131072, + "max_output": 4096, + "open": true, + "released": "2024-09-25" }, "deepinfra/meta-llama/Llama-3.2-3B-Instruct": { "cost": [ @@ -23538,7 +30440,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2023-12", + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2024-09-25" }, "deepinfra/meta-llama/Llama-3.3-70B-Instruct": { "cost": [ @@ -23547,7 +30453,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2023-12", + "limit": 131072, + "max_output": 4096, + "open": true, + "released": "2024-12-06" }, "deepinfra/meta-llama/Llama-Guard-3-8B": { "cost": [ @@ -23556,7 +30466,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2023-12", + "limit": 131072, + "max_output": 4096, + "open": true, + "released": "2024-07-23" }, "deepinfra/meta-llama/Llama-Guard-4-12B": { "cost": [ @@ -23565,7 +30479,10 @@ 0.0, 0.0 ], - "limit": 163840 + "limit": 163840, + "max_output": 163840, + "open": true, + "released": "2025-04-29" }, "deepinfra/meta-models/Muse-Glimmer-30B": { "cost": [ @@ -23574,7 +30491,11 @@ 0.04, 0.0 ], - "limit": 131072 + "knowledge": "2026-01-04", + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2026-08-10" }, "deepinfra/microsoft/WizardLM-2-8x22B": { "cost": [ @@ -23583,7 +30504,10 @@ 0.0, 0.0 ], - "limit": 65536 + "limit": 65536, + "max_output": 8000, + "open": true, + "released": "2024-04-15" }, "deepinfra/mistralai/Mistral-Small-24B-Instruct-2501": { "cost": [ @@ -23592,7 +30516,11 @@ 0.0, 0.0 ], - "limit": 32768 + "knowledge": "2023-10-31", + "limit": 32768, + "max_output": 16384, + "open": true, + "released": "2025-01-30" }, "deepinfra/mistralai/Mixtral-8x7B-Instruct-v0.1": { "cost": [ @@ -23601,7 +30529,10 @@ 0.0, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 32768, + "open": true, + "released": "2023-12-11" }, "deepinfra/moonshotai/Kimi-K2-Instruct": { "cost": [ @@ -23610,7 +30541,10 @@ 0.0, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-07-11" }, "deepinfra/moonshotai/Kimi-K2.5": { "cost": [ @@ -23619,7 +30553,11 @@ 0.07, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-01-27" }, "deepinfra/nemotron-3-super-120b-a12b": { "cost": [ @@ -23628,7 +30566,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-06", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-03-11" }, "deepinfra/nemotron-3-ultra-550b-a55b": { "cost": [ @@ -23637,7 +30579,11 @@ 0.1, 0.0 ], - "limit": 262144 + "knowledge": "2025-09", + "limit": 262144, + "max_output": 128000, + "open": true, + "released": "2026-06-04" }, "deepinfra/nvidia/Llama-3.1-Nemotron-70B-Instruct": { "cost": [ @@ -23646,7 +30592,10 @@ 0.0, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 8192, + "open": true, + "released": "2025-04-15" }, "deepinfra/nvidia/Nemotron-3-Nano-30B-A3B": { "cost": [ @@ -23655,7 +30604,11 @@ 0.025, 0.0 ], - "limit": 262144 + "knowledge": "2025-06-25", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2025-12-15" }, "deepinfra/openai/gpt-oss-120b": { "cost": [ @@ -23664,7 +30617,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "deepinfra/openai/gpt-oss-20b": { "cost": [ @@ -23673,7 +30630,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "deepinfra/stepfun-ai/Step-3.5-Flash": { "cost": [ @@ -23682,7 +30643,11 @@ 0.02, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 256000, + "open": true, + "released": "2026-01-29" }, "deepinfra/stepfun-ai/Step-3.7-Flash": { "cost": [ @@ -23691,7 +30656,11 @@ 0.04, 0.0 ], - "limit": 262144 + "knowledge": "2026-03-01", + "limit": 262144, + "max_output": 256000, + "open": true, + "released": "2026-05-29" }, "deepinfra/stepfun-ai/Step-5-Preview": { "cost": [ @@ -23700,7 +30669,10 @@ 0.1, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1000000, + "open": true, + "released": "2026-09-16" }, "deepinfra/tencent/Hy3": { "cost": [ @@ -23709,7 +30681,10 @@ 0.033, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 128000, + "open": true, + "released": "2026-07-06" }, "deepinfra/tencent/Hy4-preview": { "cost": [ @@ -23718,7 +30693,10 @@ 0.042, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 64000, + "open": true, + "released": "2026-08-28" }, "deepinfra/thinkingmachines/Inkling": { "cost": [ @@ -23727,7 +30705,10 @@ 0.16, 0.0 ], - "limit": 524288 + "limit": 524288, + "max_output": 1048576, + "open": true, + "released": "2026-07-15" }, "deepinfra/thinkingmachines/Inkling-Small": { "cost": [ @@ -23736,7 +30717,10 @@ 0.1, 0.0 ], - "limit": 524288 + "limit": 524288, + "max_output": 1048576, + "open": true, + "released": "2026-07-30" }, "deepinfra/zai-org/GLM-4.7-Flash": { "cost": [ @@ -23745,7 +30729,11 @@ 0.01, 0.0 ], - "limit": 202752 + "knowledge": "2025-04", + "limit": 202752, + "max_output": 131072, + "open": true, + "released": "2026-01-19" }, "deepseek-v4-flash-vision-exp": { "cost": [ @@ -23754,7 +30742,10 @@ 0.003, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-08-21" }, "deepseek/deepseek-chat": { "cost": [ @@ -23763,7 +30754,11 @@ 0.003, 0.0 ], - "limit": 131072 + "knowledge": "2025-09", + "limit": 131072, + "max_output": 384000, + "open": true, + "released": "2025-12-01" }, "deepseek/deepseek-v4-flash": { "cost": [ @@ -23772,7 +30767,11 @@ 0.003, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "deepseek/deepseek-v4-flash-vision-exp": { "cost": [ @@ -23781,7 +30780,10 @@ 0.003, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-08-21" }, "deepseek/deepseek-v4-pro": { "cost": [ @@ -23790,7 +30792,11 @@ 0.022, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "fireworks_ai/accounts/fireworks/models/ember-1": { "cost": [ @@ -23799,7 +30805,9 @@ 0.3, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-09-22" }, "fireworks_ai/accounts/fireworks/models/gpt-oss-120b": { "cost": [ @@ -23808,7 +30816,11 @@ 0.015, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "fireworks_ai/accounts/fireworks/models/inkling": { "cost": [ @@ -23817,7 +30829,10 @@ 0.17, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-07-15" }, "fireworks_ai/accounts/fireworks/models/muse-spark-open": { "cost": [ @@ -23826,7 +30841,11 @@ 0.15, 0.0 ], - "limit": 1048576 + "knowledge": "2026-01-04", + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-10-15" }, "fireworks_ai/gpt-oss-120b": { "cost": [ @@ -23835,7 +30854,11 @@ 0.014, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "flexai/DeepSeek-V4-Flash-0731": { "cost": [ @@ -23844,7 +30867,11 @@ 0.0178, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-07-31" }, "flexai/DeepSeek-V4-Flash-0731@eu": { "cost": [ @@ -23853,7 +30880,11 @@ 0.0178, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-07-31" }, "flexai/DeepSeek-V4.1-Flash": { "cost": [ @@ -23862,7 +30893,11 @@ 0.0154, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-09-10" }, "flexai/DeepSeek-V4.1-Flash-1017": { "cost": [ @@ -23871,7 +30906,11 @@ 0.0225, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-10-17" }, "flexai/Muse-Glimmer-30B": { "cost": [ @@ -23880,7 +30919,11 @@ 0.045, 0.0 ], - "limit": 131072 + "knowledge": "2026-01-04", + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2026-08-10" }, "flexai/Step-3.7-Flash": { "cost": [ @@ -23889,7 +30932,11 @@ 0.03, 0.0 ], - "limit": 262144 + "knowledge": "2026-03-01", + "limit": 262144, + "max_output": 256000, + "open": true, + "released": "2026-05-29" }, "flexai/gpt-oss-120b": { "cost": [ @@ -23898,7 +30945,11 @@ 0.0075, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "flexai/gpt-oss-20b": { "cost": [ @@ -23907,7 +30958,11 @@ 0.003, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "google/deep-research-max-preview-04-2026": { "cost": [ @@ -23916,7 +30971,10 @@ 0.0, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-04-21" }, "google/deep-research-preview-04-2026": { "cost": [ @@ -23925,7 +30983,10 @@ 0.0, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-04-21" }, "google/gemini-2.5-flash-image": { "cost": [ @@ -23934,7 +30995,11 @@ 0.03, 0.083333 ], - "limit": 32768 + "knowledge": "2024-06", + "limit": 32768, + "max_output": 32768, + "released": "2025-08-26", + "type": "image" }, "google/gemini-3-flash-preview": { "cost": [ @@ -23943,7 +31008,10 @@ 0.05, 0.083333 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2025-12-17" }, "google/gemini-3-pro-image": { "cost": [ @@ -23952,7 +31020,11 @@ 0.2, 0.375 ], - "limit": 65536 + "knowledge": "2025-01", + "limit": 65536, + "max_output": 32768, + "released": "2026-05-28", + "type": "image" }, "google/gemini-3-pro-image-preview": { "cost": [ @@ -23961,7 +31033,11 @@ 0.2, 0.375 ], - "limit": 65536 + "knowledge": "2025-01", + "limit": 65536, + "max_output": 32768, + "released": "2025-11-20", + "type": "image" }, "google/gemini-3.1-flash-image": { "cost": [ @@ -23970,7 +31046,11 @@ 0.0, 0.0 ], - "limit": 65536 + "knowledge": "2025-01", + "limit": 65536, + "max_output": 32768, + "released": "2026-05-28", + "type": "image" }, "google/gemini-3.1-flash-image-preview": { "cost": [ @@ -23979,7 +31059,11 @@ 0.0, 0.0 ], - "limit": 65536 + "knowledge": "2025-01", + "limit": 65536, + "max_output": 65536, + "released": "2026-02-26", + "type": "image" }, "google/gemini-3.1-flash-lite": { "cost": [ @@ -23988,7 +31072,10 @@ 0.025, 0.083333 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-05-07" }, "google/gemini-3.1-flash-lite-image": { "cost": [ @@ -23997,7 +31084,11 @@ 0.0, 0.0 ], - "limit": 65536 + "knowledge": "2025-01", + "limit": 65536, + "max_output": 4096, + "released": "2026-06-30", + "type": "image" }, "google/gemini-3.1-flash-lite-preview": { "cost": [ @@ -24006,7 +31097,10 @@ 0.025, 0.083333 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-03-03" }, "google/gemini-3.1-pro-preview": { "cost": [ @@ -24015,7 +31109,10 @@ 0.2, 0.375 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2026-02-19", "tiers": [ { "cost": [ @@ -24038,7 +31135,10 @@ 0.2, 0.375 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2026-02-19", "tiers": [ { "cost": [ @@ -24061,7 +31161,10 @@ 0.15, 0.083333 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-05-19" }, "google/gemini-3.5-flash-lite": { "cost": [ @@ -24070,7 +31173,10 @@ 0.03, 0.083333 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-07-21" }, "google/gemini-3.6-flash": { "cost": [ @@ -24079,7 +31185,10 @@ 0.075, 0.041667 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-07-21" }, "google/gemini-3.7-flash": { "cost": [ @@ -24088,7 +31197,10 @@ 0.15, 0.083333 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-08-13" }, "google/gemini-3.8-flash": { "cost": [ @@ -24097,7 +31209,9 @@ 0.15, 0.083333 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65536, + "released": "2026-09-02" }, "google/gemini-4-argon": { "cost": [ @@ -24106,7 +31220,10 @@ 0.2, 0.375 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-10-13" }, "google/gemini-flash-latest": { "cost": [ @@ -24115,7 +31232,9 @@ 0.15, 0.083333 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65536, + "released": "2026-09-02" }, "google/gemini-nano-banana-2.1": { "cost": [ @@ -24124,7 +31243,10 @@ 0.0, 0.0 ], - "limit": 65536 + "limit": 65536, + "max_output": 32768, + "released": "2026-10-06", + "type": "image" }, "google/gemini-pro-latest": { "cost": [ @@ -24133,7 +31255,10 @@ 0.2, 0.375 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-10-13" }, "google/gemini-robotics-er-2-preview": { "cost": [ @@ -24142,16 +31267,9 @@ 0.1, 0.0 ], - "limit": 131072 - }, - "greenference/deepseek-v4.1-flash": { - "cost": [ - 0.22, - 0.88, - 0.007, - 0.0 - ], - "limit": 1048576 + "limit": 131072, + "max_output": 65536, + "released": "2026-07-30" }, "greenference/gpt-oss-20b": { "cost": [ @@ -24160,52 +31278,75 @@ 0.0045, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "greenpt/deepseek-v4-flash-0731": { "cost": [ - 0.15687, - 0.392175, - 0.04482, + 0.1561, + 0.39025, + 0.0446, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-07-31" }, "greenpt/deepseek-v4.1-flash": { "cost": [ - 0.24651, - 1.23255, - 0.012325, + 0.2453, + 1.2265, + 0.012265, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-09-10" }, "greenpt/gpt-oss-120b": { "cost": [ - 0.2241, - 0.78435, + 0.223, + 0.7805, 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-06", + "limit": 128000, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "greenpt/llama-3.3-70b-instruct": { "cost": [ - 1.23255, - 1.23255, + 1.2265, + 1.2265, 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2023-12", + "limit": 128000, + "max_output": 4096, + "open": true, + "released": "2024-12-06" }, "greenpt/qwen3-235b-a22b-instruct-2507": { "cost": [ - 1.00845, - 3.025349, + 1.0035, + 3.0105, 0.0, 0.0 ], - "limit": 250000 + "limit": 250000, + "max_output": 16384, + "open": true, + "released": "2025-07-21" }, "groq/meta-llama/llama-prompt-guard-2-22m": { "cost": [ @@ -24214,7 +31355,10 @@ 0.015, 0.0 ], - "limit": 512 + "limit": 512, + "max_output": 512, + "open": true, + "released": "2025-04-29" }, "groq/meta-llama/llama-prompt-guard-2-86m": { "cost": [ @@ -24223,7 +31367,10 @@ 0.02, 0.0 ], - "limit": 512 + "limit": 512, + "max_output": 512, + "open": true, + "released": "2025-04-29" }, "groq/openai/gpt-oss-120b": { "cost": [ @@ -24232,7 +31379,11 @@ 0.075, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "groq/openai/gpt-oss-20b": { "cost": [ @@ -24241,7 +31392,11 @@ 0.0375, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "groq/openai/gpt-oss-safeguard-20b": { "cost": [ @@ -24250,43 +31405,61 @@ 0.0375, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2025-10-29" }, "infomaniak/mistralai/Ministral-3-14B-Instruct-2512": { "cost": [ - 0.33615, - 0.4482, + 0.3345, + 0.446, 0.0, 0.0 ], - "limit": 100000 + "limit": 100000, + "max_output": 262144, + "open": true, + "released": "2025-12-02" }, "ionos/Qwen/Qwen3-Coder-Next": { "cost": [ - 0.168075, - 0.8964, + 0.16725, + 0.892, 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2025-09", + "limit": 128000, + "max_output": 65536, + "open": true, + "released": "2026-02-03" }, "ionos/meta-llama/Llama-3.3-70B-Instruct": { "cost": [ - 0.728325, - 0.728325, + 0.72475, + 0.72475, 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2023-12", + "limit": 128000, + "max_output": 4096, + "open": true, + "released": "2024-12-06" }, "ionos/openai/gpt-oss-120b": { "cost": [ - 0.168075, - 0.728325, + 0.16725, + 0.72475, 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-06", + "limit": 128000, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "meta/muse-spark-1.1": { "cost": [ @@ -24295,7 +31468,9 @@ 0.15, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-04-08" }, "meta/muse-spark-1.2": { "cost": [ @@ -24304,7 +31479,9 @@ 0.15, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-08-05" }, "meta/muse-spark-1.3": { "cost": [ @@ -24313,7 +31490,9 @@ 0.15, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-09-02" }, "meta/muse-wonder-1.0": { "cost": [ @@ -24322,7 +31501,33 @@ 0.2, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-10-12" + }, + "microsoft/gpt-4": { + "cost": [ + 30.0, + 60.0, + 0.0, + 0.0 + ], + "knowledge": "2023-11", + "limit": 8191, + "max_output": 8192, + "released": "2023-11-06" + }, + "microsoft/o3-mini": { + "cost": [ + 1.1, + 4.4, + 0.55, + 0.0 + ], + "knowledge": "2024-05", + "limit": 200000, + "max_output": 100000, + "released": "2024-12-20" }, "minimax/MiniMax-M2": { "cost": [ @@ -24331,7 +31536,10 @@ 0.0, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-10-27" }, "minimax/MiniMax-M2.1": { "cost": [ @@ -24340,7 +31548,10 @@ 0.03, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-12-23" }, "minimax/MiniMax-M2.5": { "cost": [ @@ -24349,7 +31560,10 @@ 0.03, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-02-12" }, "minimax/MiniMax-M2.7": { "cost": [ @@ -24358,7 +31572,10 @@ 0.06, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-03-18" }, "minimax/MiniMax-M3": { "cost": [ @@ -24367,7 +31584,10 @@ 0.06, 0.0 ], - "limit": 524288 + "limit": 524288, + "max_output": 512000, + "open": true, + "released": "2026-06-01" }, "minimax/MiniMax-M3.1-Flash": { "cost": [ @@ -24376,7 +31596,9 @@ 0.015, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 512000, + "released": "2026-10-19" }, "mistral/codestral-2508": { "cost": [ @@ -24385,7 +31607,9 @@ 0.03, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 8192, + "released": "2025-07-30" }, "mistral/codestral-latest": { "cost": [ @@ -24394,7 +31618,11 @@ 0.03, 0.0 ], - "limit": 256000 + "knowledge": "2024-10", + "limit": 256000, + "max_output": 4096, + "open": true, + "released": "2024-05-29" }, "mistral/devstral-2512": { "cost": [ @@ -24403,7 +31631,11 @@ 0.04, 0.0 ], - "limit": 262144 + "knowledge": "2025-12", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2025-12-09" }, "mistral/devstral-medium-latest": { "cost": [ @@ -24412,7 +31644,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-12", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2025-12-02" }, "mistral/magistral-medium-latest": { "cost": [ @@ -24421,7 +31657,10 @@ 0.15, 0.0 ], - "limit": 262144 + "knowledge": "2025-06", + "limit": 262144, + "max_output": 16384, + "released": "2025-03-17" }, "mistral/ministral-14b-2512": { "cost": [ @@ -24430,7 +31669,10 @@ 0.02, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 209715, + "open": true, + "released": "2025-12-02" }, "mistral/ministral-3b-2512": { "cost": [ @@ -24439,7 +31681,10 @@ 0.01, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 104857, + "open": true, + "released": "2025-12-02" }, "mistral/ministral-8b-2512": { "cost": [ @@ -24448,7 +31693,10 @@ 0.015, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 209715, + "open": true, + "released": "2025-12-02" }, "mistral/mistral-large-2407": { "cost": [ @@ -24457,7 +31705,11 @@ 0.2, 0.0 ], - "limit": 131072 + "knowledge": "2024-03-31", + "limit": 131072, + "max_output": 104857, + "open": true, + "released": "2024-07-24" }, "mistral/mistral-large-2512": { "cost": [ @@ -24466,7 +31718,11 @@ 0.05, 0.0 ], - "limit": 262144 + "knowledge": "2024-11", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2025-12-02" }, "mistral/mistral-large-latest": { "cost": [ @@ -24475,7 +31731,11 @@ 0.2, 0.0 ], - "limit": 262144 + "knowledge": "2024-11", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2024-11-01" }, "mistral/mistral-medium-2505": { "cost": [ @@ -24484,7 +31744,10 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2025-05", + "limit": 131072, + "max_output": 131072, + "released": "2025-05-07" }, "mistral/mistral-medium-2604": { "cost": [ @@ -24493,7 +31756,10 @@ 0.15, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-29" }, "mistral/mistral-medium-3": { "cost": [ @@ -24502,7 +31768,10 @@ 0.04, 0.0 ], - "limit": 262144 + "knowledge": "2025-03-31", + "limit": 262144, + "max_output": 104857, + "released": "2025-05-07" }, "mistral/mistral-medium-3-5": { "cost": [ @@ -24511,7 +31780,9 @@ 0.15, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 209715, + "released": "2026-04-30" }, "mistral/mistral-medium-latest": { "cost": [ @@ -24520,7 +31791,10 @@ 0.15, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-29" }, "mistral/mistral-small-2603": { "cost": [ @@ -24529,7 +31803,11 @@ 0.015, 0.0 ], - "limit": 262144 + "knowledge": "2025-06", + "limit": 262144, + "max_output": 256000, + "open": true, + "released": "2026-03-16" }, "mistral/mistral-small-latest": { "cost": [ @@ -24538,7 +31816,11 @@ 0.015, 0.0 ], - "limit": 262144 + "knowledge": "2025-06", + "limit": 262144, + "max_output": 256000, + "open": true, + "released": "2026-03-16" }, "mistral/voxtral-small-latest": { "cost": [ @@ -24547,7 +31829,10 @@ 0.01, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 32000, + "open": true, + "released": "2025-07-15" }, "moonshot/kimi-k2.6": { "cost": [ @@ -24556,7 +31841,11 @@ 0.16, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-20" }, "moonshot/kimi-k2.7-code": { "cost": [ @@ -24565,7 +31854,11 @@ 0.19, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-06-12" }, "moonshot/kimi-k2.7-code-highspeed": { "cost": [ @@ -24574,7 +31867,11 @@ 0.38, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-06-12" }, "moonshot/kimi-k3": { "cost": [ @@ -24583,7 +31880,21 @@ 0.3, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-16" + }, + "moonshot/kimi-k3.1-pro": { + "cost": [ + 2.0, + 10.0, + 0.2, + 0.0 + ], + "limit": 1048576, + "max_output": 131072, + "released": "2026-10-23" }, "nebius/Qwen/Qwen3-235B-A22B-Instruct-2507": { "cost": [ @@ -24592,7 +31903,10 @@ 0.2, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 16384, + "open": true, + "released": "2025-07-21" }, "nebius/Qwen/Qwen3-30B-A3B-Instruct-2507": { "cost": [ @@ -24601,7 +31915,10 @@ 0.1, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 16384, + "open": true, + "released": "2025-07-28" }, "nebius/deepseek-ai/DeepSeek-V4-Flash-0731": { "cost": [ @@ -24610,7 +31927,11 @@ 0.14, 0.0 ], - "limit": 1024000 + "knowledge": "2025-05", + "limit": 1024000, + "max_output": 384000, + "open": true, + "released": "2026-07-31" }, "nebius/deepseek-ai/DeepSeek-V4-Pro-0813": { "cost": [ @@ -24619,7 +31940,10 @@ 1.32, 0.0 ], - "limit": 979000 + "limit": 979000, + "max_output": 384000, + "open": true, + "released": "2026-08-13" }, "nebius/deepseek-ai/DeepSeek-V4.1-Flash": { "cost": [ @@ -24628,7 +31952,11 @@ 0.3, 0.0 ], - "limit": 1048000 + "knowledge": "2025-05", + "limit": 1048000, + "max_output": 384000, + "open": true, + "released": "2026-09-10" }, "nebius/deepseek-ai/DeepSeek-V4.1-Flash-1017": { "cost": [ @@ -24637,7 +31965,11 @@ 0.3, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-10-17" }, "nebius/google/gemma-3-27b-it": { "cost": [ @@ -24646,7 +31978,11 @@ 0.1, 0.0 ], - "limit": 110000 + "knowledge": "2024-08", + "limit": 110000, + "max_output": 131072, + "open": true, + "released": "2025-03-12" }, "nebius/meta-models/muse-spark-open": { "cost": [ @@ -24655,7 +31991,11 @@ 1.25, 0.0 ], - "limit": 1048576 + "knowledge": "2026-01-04", + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-10-15" }, "nebius/nvidia/Nemotron-3-Ultra-550b-a55b": { "cost": [ @@ -24664,7 +32004,11 @@ 1.0, 0.0 ], - "limit": 1048576 + "knowledge": "2025-09", + "limit": 1048576, + "max_output": 128000, + "open": true, + "released": "2026-06-04" }, "nebius/nvidia/nemotron-3-super-120b-a12b": { "cost": [ @@ -24673,7 +32017,11 @@ 0.3, 0.0 ], - "limit": 262144 + "knowledge": "2025-06", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-03-11" }, "nebius/openai/gpt-oss-120b": { "cost": [ @@ -24682,34 +32030,11 @@ 0.15, 0.0 ], - "limit": 131072 - }, - "openai/gpt-3.5-turbo": { - "cost": [ - 0.5, - 1.5, - 0.0, - 0.0 - ], - "limit": 16385 - }, - "openai/gpt-4": { - "cost": [ - 30.0, - 60.0, - 0.0, - 0.0 - ], - "limit": 8191 - }, - "openai/gpt-4-turbo": { - "cost": [ - 10.0, - 30.0, - 0.0, - 0.0 - ], - "limit": 128000 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "openai/gpt-4.1": { "cost": [ @@ -24718,7 +32043,10 @@ 0.5, 0.0 ], - "limit": 1047576 + "knowledge": "2024-04", + "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14" }, "openai/gpt-4.1-mini": { "cost": [ @@ -24727,16 +32055,10 @@ 0.1, 0.0 ], - "limit": 1047576 - }, - "openai/gpt-4.1-nano": { - "cost": [ - 0.1, - 0.4, - 0.025, - 0.0 - ], - "limit": 1047576 + "knowledge": "2024-04", + "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14" }, "openai/gpt-4o": { "cost": [ @@ -24745,7 +32067,10 @@ 1.25, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-05-13" }, "openai/gpt-4o-2024-08-06": { "cost": [ @@ -24754,7 +32079,10 @@ 1.25, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-08-06" }, "openai/gpt-4o-2024-11-20": { "cost": [ @@ -24763,7 +32091,10 @@ 1.25, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-11-20" }, "openai/gpt-4o-mini": { "cost": [ @@ -24772,7 +32103,10 @@ 0.075, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-07-18" }, "openai/gpt-5": { "cost": [ @@ -24781,7 +32115,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "openai/gpt-5-mini": { "cost": [ @@ -24790,7 +32127,10 @@ 0.025, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "openai/gpt-5-nano": { "cost": [ @@ -24799,7 +32139,10 @@ 0.005, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "openai/gpt-5-pro": { "cost": [ @@ -24808,7 +32151,10 @@ 0.0, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 272000, + "released": "2025-10-06" }, "openai/gpt-5-search-api": { "cost": [ @@ -24817,7 +32163,9 @@ 0.125, 0.0 ], - "limit": 272000 + "limit": 272000, + "max_output": 100000, + "released": "2025-10-14" }, "openai/gpt-5.1": { "cost": [ @@ -24826,7 +32174,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "openai/gpt-5.2": { "cost": [ @@ -24835,7 +32186,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "openai/gpt-5.2-pro": { "cost": [ @@ -24844,7 +32198,10 @@ 0.0, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "openai/gpt-5.3-codex": { "cost": [ @@ -24853,7 +32210,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-02-05" }, "openai/gpt-5.4": { "cost": [ @@ -24862,7 +32222,10 @@ 0.25, 0.0 ], + "knowledge": "2025-08-31", "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05", "tiers": [ { "cost": [ @@ -24885,7 +32248,10 @@ 0.075, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "openai/gpt-5.4-nano": { "cost": [ @@ -24894,7 +32260,10 @@ 0.02, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "openai/gpt-5.4-pro": { "cost": [ @@ -24903,7 +32272,10 @@ 0.0, 0.0 ], + "knowledge": "2025-08-31", "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05", "tiers": [ { "cost": [ @@ -24926,7 +32298,10 @@ 0.5, 0.0 ], + "knowledge": "2025-12-01", "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23", "tiers": [ { "cost": [ @@ -24949,7 +32324,10 @@ 0.0, 0.0 ], + "knowledge": "2025-12-01", "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23", "tiers": [ { "cost": [ @@ -24972,7 +32350,10 @@ 0.02, 0.25 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -24995,7 +32376,10 @@ 0.4, 5.0 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -25018,7 +32402,10 @@ 0.2, 2.5 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -25041,7 +32428,10 @@ 1.0, 12.5 ], + "knowledge": "2026-04-30", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-04", "tiers": [ { "cost": [ @@ -25064,7 +32454,10 @@ 0.01, 0.125 ], + "knowledge": "2026-05-18", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -25087,7 +32480,10 @@ 0.2, 2.5 ], + "knowledge": "2026-04-20", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -25110,7 +32506,10 @@ 0.1, 2.5 ], + "knowledge": "2026-04-30", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-29", "tiers": [ { "cost": [ @@ -25126,6 +32525,32 @@ } ] }, + "openai/gpt-6.1-terra": { + "cost": [ + 1.0, + 5.0, + 0.05, + 1.25 + ], + "knowledge": "2026-06-01", + "limit": 1050000, + "max_output": 128000, + "released": "2026-10-26", + "tiers": [ + { + "cost": [ + 2.0, + 7.5, + 0.1, + 2.5 + ], + "tier": { + "size": 272000, + "type": "context" + } + } + ] + }, "openai/gpt-latest": { "cost": [ 10.0, @@ -25133,7 +32558,10 @@ 1.0, 12.5 ], + "knowledge": "2026-04-30", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-04", "tiers": [ { "cost": [ @@ -25156,7 +32584,10 @@ 0.02, 0.25 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -25179,7 +32610,10 @@ 0.4, 5.0 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -25195,24 +32629,6 @@ } ] }, - "openai/o1": { - "cost": [ - 15.0, - 60.0, - 7.5, - 0.0 - ], - "limit": 200000 - }, - "openai/o1-pro": { - "cost": [ - 150.0, - 600.0, - 0.0, - 0.0 - ], - "limit": 200000 - }, "openai/o3": { "cost": [ 2.0, @@ -25220,16 +32636,10 @@ 0.5, 0.0 ], - "limit": 200000 - }, - "openai/o3-mini": { - "cost": [ - 1.1, - 4.4, - 0.55, - 0.0 - ], - "limit": 200000 + "knowledge": "2024-05", + "limit": 200000, + "max_output": 100000, + "released": "2025-04-16" }, "openai/o3-pro": { "cost": [ @@ -25238,16 +32648,10 @@ 0.0, 0.0 ], - "limit": 200000 - }, - "openai/o4-mini": { - "cost": [ - 1.1, - 4.4, - 0.275, - 0.0 - ], - "limit": 200000 + "knowledge": "2024-05", + "limit": 200000, + "max_output": 100000, + "released": "2025-06-10" }, "ovhcloud/gpt-oss-120b": { "cost": [ @@ -25256,7 +32660,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "ovhcloud/gpt-oss-20b": { "cost": [ @@ -25265,7 +32673,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "perplexityai/sonar": { "cost": [ @@ -25274,7 +32686,10 @@ 0.0, 0.0 ], - "limit": 127072 + "knowledge": "2025-09-01", + "limit": 127072, + "max_output": 4096, + "released": "2024-01-01" }, "perplexityai/sonar-deep-research": { "cost": [ @@ -25283,7 +32698,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2025-01", + "limit": 128000, + "max_output": 32768, + "reasoning": 3.0, + "released": "2025-02-01" }, "perplexityai/sonar-pro": { "cost": [ @@ -25292,7 +32711,10 @@ 0.0, 0.0 ], - "limit": 200000 + "knowledge": "2025-09-01", + "limit": 200000, + "max_output": 8192, + "released": "2024-01-01" }, "perplexityai/sonar-reasoning-pro": { "cost": [ @@ -25301,7 +32723,10 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2025-09-01", + "limit": 128000, + "max_output": 4096, + "released": "2024-01-01" }, "qwen/deepseek-v4-flash-0731": { "cost": [ @@ -25310,7 +32735,11 @@ 0.022, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-07-31" }, "qwen/deepseek-v4-pro-0813": { "cost": [ @@ -25319,7 +32748,10 @@ 0.066, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-08-13" }, "qwen/deepseek-v4.1-flash": { "cost": [ @@ -25328,7 +32760,11 @@ 0.015, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-09-10" }, "qwen/deepseek-v4.1-flash-1017": { "cost": [ @@ -25337,7 +32773,11 @@ 0.015, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-10-17" }, "qwen/qwen-max": { "cost": [ @@ -25346,7 +32786,10 @@ 0.32, 0.0 ], - "limit": 32768 + "knowledge": "2024-04", + "limit": 32768, + "max_output": 8192, + "released": "2024-04-03" }, "qwen/qwen-mt-plus": { "cost": [ @@ -25355,7 +32798,9 @@ 0.0, 0.0 ], - "limit": 4096 + "limit": 4096, + "max_output": 8192, + "released": "2025-07-24" }, "qwen/qwen3-coder-flash": { "cost": [ @@ -25364,7 +32809,10 @@ 0.06, 0.375 ], - "limit": 1000000 + "knowledge": "2025-04", + "limit": 1000000, + "max_output": 65536, + "released": "2025-07-28" }, "qwen/qwen3.8-2.4t-a95b": { "cost": [ @@ -25373,7 +32821,10 @@ 0.25, 2.5 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-12" }, "qwen/qwen3.8-27b": { "cost": [ @@ -25382,7 +32833,10 @@ 0.1, 0.625 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 32768, + "open": true, + "released": "2026-08-14" }, "qwen/qwen3.8-flash": { "cost": [ @@ -25391,7 +32845,9 @@ 0.016, 0.2 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-08-26" }, "qwen/qwen3.8-max": { "cost": [ @@ -25400,7 +32856,9 @@ 0.25, 2.5 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-08-03" }, "qwen/qwen3.8-max-0902": { "cost": [ @@ -25409,7 +32867,9 @@ 0.25, 2.5 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-09-02" }, "qwen/qwen3.8-omni-flash": { "cost": [ @@ -25418,25 +32878,35 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-09-17" }, "scaleway/deepseek-v4-flash-0731": { "cost": [ - 0.4482, - 0.8964, - 0.08964, + 0.446, + 0.892, + 0.0892, 0.0 ], - "limit": 256000 + "knowledge": "2025-05", + "limit": 256000, + "max_output": 384000, + "open": true, + "released": "2026-07-31" }, "scaleway/deepseek-v4.1-flash": { "cost": [ - 0.6723, - 2.016899, - 0.13446, + 0.669, + 2.007, + 0.1338, 0.0 ], - "limit": 256000 + "knowledge": "2025-05", + "limit": 256000, + "max_output": 384000, + "open": true, + "released": "2026-09-10" }, "scaleway/gemma-3-27b-it": { "cost": [ @@ -25445,34 +32915,49 @@ 0.0, 0.0 ], - "limit": 40000 + "knowledge": "2024-08", + "limit": 40000, + "max_output": 131072, + "open": true, + "released": "2025-03-12" }, "scaleway/gpt-oss-120b": { "cost": [ - 0.168075, - 0.6723, + 0.16725, + 0.669, 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-06", + "limit": 128000, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "scaleway/llama-3.3-70b-instruct": { "cost": [ - 1.00845, - 1.00845, + 1.0035, + 1.0035, 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2023-12", + "limit": 128000, + "max_output": 4096, + "open": true, + "released": "2024-12-06" }, "scaleway/qwen3-235b-a22b-instruct-2507": { "cost": [ - 0.840375, - 2.521124, + 0.83625, + 2.50875, 0.0, 0.0 ], - "limit": 250000 + "limit": 250000, + "max_output": 16384, + "open": true, + "released": "2025-07-21" }, "scaleway/qwen3-coder-30b-a3b-instruct": { "cost": [ @@ -25481,7 +32966,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2025-04", + "limit": 128000, + "max_output": 65536, + "open": true, + "released": "2025-07-31" }, "sference/deepseek-ai/DeepSeek-V4-Flash-0731": { "cost": [ @@ -25490,7 +32979,11 @@ 0.07, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-07-31" }, "sference/deepseek-ai/DeepSeek-V4.1-Flash-1017": { "cost": [ @@ -25499,7 +32992,11 @@ 0.05, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-10-17" }, "tencent/deepseek-v4-pro-0813": { "cost": [ @@ -25508,7 +33005,10 @@ 0.022, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-08-13" }, "tencent/deepseek-v4.1-flash": { "cost": [ @@ -25517,7 +33017,24 @@ 0.003, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-09-10" + }, + "tencent/deepseek-v4.1-flash-1017": { + "cost": [ + 0.15, + 0.6, + 0.003, + 0.0 + ], + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-10-17" }, "tencent/hy3": { "cost": [ @@ -25526,7 +33043,10 @@ 0.033, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 128000, + "open": true, + "released": "2026-07-06" }, "tencent/hy4-preview": { "cost": [ @@ -25535,7 +33055,10 @@ 0.042, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 64000, + "open": true, + "released": "2026-08-28" }, "tencent/step-5-preview": { "cost": [ @@ -25544,7 +33067,10 @@ 0.05, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 1000000, + "open": true, + "released": "2026-09-16" }, "tensorx/deepseek/deepseek-r1-0528": { "cost": [ @@ -25553,7 +33079,10 @@ 0.165, 0.0 ], - "limit": 164000 + "limit": 164000, + "max_output": 32768, + "open": true, + "released": "2025-05-28" }, "tensorx/deepseek/deepseek-v4-flash-0731": { "cost": [ @@ -25562,7 +33091,11 @@ 0.0625, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-07-31" }, "tensorx/deepseek/deepseek-v4-pro-0813": { "cost": [ @@ -25571,7 +33104,10 @@ 0.5, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-08-13" }, "tensorx/deepseek/deepseek-v4.1-flash": { "cost": [ @@ -25580,7 +33116,11 @@ 0.125, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-09-10" }, "tensorx/deepseek/deepseek-v4.1-flash-1017": { "cost": [ @@ -25589,7 +33129,11 @@ 0.125, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-10-17" }, "tensorx/moonshotai/kimi-k2.5": { "cost": [ @@ -25598,16 +33142,11 @@ 0.125, 0.0 ], - "limit": 262144 - }, - "together_ai/deepseek-ai/DeepSeek-V4-Flash-0731": { - "cost": [ - 0.14, - 0.28, - 0.03, - 0.0 - ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-01-27" }, "together_ai/deepseek-ai/DeepSeek-V4-Pro-0813": { "cost": [ @@ -25616,7 +33155,10 @@ 0.13, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-08-13" }, "together_ai/deepseek-ai/DeepSeek-V4.1-Flash": { "cost": [ @@ -25625,7 +33167,11 @@ 0.006, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-09-10" }, "together_ai/deepseek-ai/DeepSeek-V4.1-Flash-1017": { "cost": [ @@ -25634,7 +33180,11 @@ 0.006, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-10-17" }, "together_ai/meta-models/Muse-Glimmer-30B": { "cost": [ @@ -25643,7 +33193,11 @@ 0.04, 0.0 ], - "limit": 131072 + "knowledge": "2026-01-04", + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2026-08-10" }, "together_ai/openai/gpt-oss-120b": { "cost": [ @@ -25652,7 +33206,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "together_ai/reflection/Beam-1.0-501B-A23B": { "cost": [ @@ -25661,7 +33219,11 @@ 0.04, 0.0 ], - "limit": 1048576 + "knowledge": "2026-06-30", + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-10-05" }, "together_ai/thinkingmachines/Inkling": { "cost": [ @@ -25670,7 +33232,10 @@ 0.17, 0.0 ], - "limit": 524288 + "limit": 524288, + "max_output": 1048576, + "open": true, + "released": "2026-07-15" }, "vertex/gemini-2.5-flash-image": { "cost": [ @@ -25679,7 +33244,11 @@ 0.03, 0.083333 ], - "limit": 32768 + "knowledge": "2024-06", + "limit": 32768, + "max_output": 32768, + "released": "2025-08-26", + "type": "image" }, "vertex/gemini-3-flash-preview": { "cost": [ @@ -25688,7 +33257,10 @@ 0.05, 0.083333 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2025-12-17" }, "vertex/gemini-3-pro-image": { "cost": [ @@ -25697,7 +33269,11 @@ 0.2, 0.375 ], - "limit": 65536 + "knowledge": "2025-01", + "limit": 65536, + "max_output": 32768, + "released": "2026-05-28", + "type": "image" }, "vertex/gemini-3.1-flash-image": { "cost": [ @@ -25706,7 +33282,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2025-01", + "limit": 131072, + "max_output": 32768, + "released": "2026-05-28", + "type": "image" }, "vertex/gemini-3.1-flash-lite": { "cost": [ @@ -25715,7 +33295,10 @@ 0.025, 0.083333 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-05-07" }, "vertex/gemini-3.1-flash-lite-image": { "cost": [ @@ -25724,7 +33307,11 @@ 0.0, 0.0 ], - "limit": 65536 + "knowledge": "2025-01", + "limit": 65536, + "max_output": 4096, + "released": "2026-06-30", + "type": "image" }, "vertex/gemini-3.1-flash-lite@eu": { "cost": [ @@ -25733,7 +33320,10 @@ 0.025, 0.083333 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-05-07" }, "vertex/gemini-3.1-flash-lite@us": { "cost": [ @@ -25742,7 +33332,10 @@ 0.025, 0.083333 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-05-07" }, "vertex/gemini-3.1-pro-preview": { "cost": [ @@ -25751,7 +33344,10 @@ 0.2, 0.375 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2026-02-19", "tiers": [ { "cost": [ @@ -25774,7 +33370,10 @@ 0.15, 0.083333 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-05-19" }, "vertex/gemini-3.5-flash-lite": { "cost": [ @@ -25783,7 +33382,10 @@ 0.03, 0.083333 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-07-21" }, "vertex/gemini-3.5-flash-lite@eu": { "cost": [ @@ -25792,7 +33394,10 @@ 0.03, 0.083333 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-07-21" }, "vertex/gemini-3.5-flash-lite@us": { "cost": [ @@ -25801,7 +33406,10 @@ 0.03, 0.083333 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-07-21" }, "vertex/gemini-3.5-flash@eu": { "cost": [ @@ -25810,7 +33418,10 @@ 0.15, 0.083333 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-05-19" }, "vertex/gemini-3.5-flash@us": { "cost": [ @@ -25819,7 +33430,10 @@ 0.15, 0.083333 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-05-19" }, "vertex/gemini-3.6-flash": { "cost": [ @@ -25828,7 +33442,10 @@ 0.075, 0.041667 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-07-21" }, "vertex/gemini-3.6-flash@eu": { "cost": [ @@ -25837,7 +33454,10 @@ 0.075, 0.041667 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-07-21" }, "vertex/gemini-3.6-flash@us": { "cost": [ @@ -25846,7 +33466,10 @@ 0.075, 0.041667 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-07-21" }, "vertex/gemini-3.7-flash": { "cost": [ @@ -25855,7 +33478,10 @@ 0.15, 0.083333 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-08-13" }, "vertex/gemini-3.7-flash@eu": { "cost": [ @@ -25864,7 +33490,10 @@ 0.15, 0.083333 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-08-13" }, "vertex/gemini-3.7-flash@us": { "cost": [ @@ -25873,7 +33502,10 @@ 0.15, 0.083333 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-08-13" }, "vertex/gemini-3.8-flash": { "cost": [ @@ -25882,7 +33514,9 @@ 0.15, 0.083333 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65536, + "released": "2026-09-02" }, "vertex/gemini-3.8-flash@eu": { "cost": [ @@ -25891,7 +33525,9 @@ 0.15, 0.083333 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65536, + "released": "2026-09-02" }, "vertex/gemini-3.8-flash@us": { "cost": [ @@ -25900,7 +33536,9 @@ 0.15, 0.083333 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65536, + "released": "2026-09-02" }, "vertex/gemini-4-argon": { "cost": [ @@ -25909,7 +33547,10 @@ 0.2, 0.375 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-10-13" }, "vertex/gemini-4-argon@eu": { "cost": [ @@ -25918,7 +33559,10 @@ 0.2, 0.375 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-10-13" }, "vertex/gemini-4-argon@us": { "cost": [ @@ -25927,7 +33571,10 @@ 0.2, 0.375 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-10-13" }, "vertex/gemini-flash-latest": { "cost": [ @@ -25936,7 +33583,9 @@ 0.15, 0.083333 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65536, + "released": "2026-09-02" }, "vertex/gemini-nano-banana-2.1": { "cost": [ @@ -25945,7 +33594,10 @@ 0.0, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 32768, + "released": "2026-10-06", + "type": "image" }, "vertex/gemini-pro-latest": { "cost": [ @@ -25954,7 +33606,10 @@ 0.2, 0.375 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-10-13" }, "xai/grok-4-fast-non-reasoning": { "cost": [ @@ -25964,6 +33619,8 @@ 0.0 ], "limit": 2000000, + "max_output": 2000000, + "released": "2025-12-18", "tiers": [ { "cost": [ @@ -25987,6 +33644,8 @@ 0.0 ], "limit": 1000000, + "max_output": 30000, + "released": "2026-03-09", "tiers": [ { "cost": [ @@ -26010,6 +33669,8 @@ 0.0 ], "limit": 1000000, + "max_output": 30000, + "released": "2026-03-09", "tiers": [ { "cost": [ @@ -26033,6 +33694,8 @@ 0.0 ], "limit": 1000000, + "max_output": 30000, + "released": "2026-04-17", "tiers": [ { "cost": [ @@ -26056,6 +33719,8 @@ 0.0 ], "limit": 500000, + "max_output": 500000, + "released": "2026-07-08", "tiers": [ { "cost": [ @@ -26078,7 +33743,10 @@ 0.5, 0.0 ], + "knowledge": "2026-02-01", "limit": 500000, + "max_output": 500000, + "released": "2026-08-12", "tiers": [ { "cost": [ @@ -26101,7 +33769,10 @@ 0.5, 0.0 ], + "knowledge": "2026-05", "limit": 500000, + "max_output": 500000, + "released": "2026-09-21", "tiers": [ { "cost": [ @@ -26125,6 +33796,8 @@ 0.0 ], "limit": 256000, + "max_output": 256000, + "released": "2026-04-16", "tiers": [ { "cost": [ @@ -26147,7 +33820,10 @@ 0.5, 0.0 ], + "knowledge": "2026-05", "limit": 500000, + "max_output": 500000, + "released": "2026-09-21", "tiers": [ { "cost": [ @@ -26170,7 +33846,11 @@ 0.11, 0.0 ], - "limit": 202752 + "knowledge": "2025-04", + "limit": 202752, + "max_output": 131072, + "open": true, + "released": "2025-09-30" }, "zai/glm-4.6v": { "cost": [ @@ -26179,7 +33859,11 @@ 0.05, 0.0 ], - "limit": 131072 + "knowledge": "2025-04", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-12-08" }, "zai/glm-4.7": { "cost": [ @@ -26188,7 +33872,11 @@ 0.11, 0.0 ], - "limit": 202752 + "knowledge": "2025-04", + "limit": 202752, + "max_output": 131072, + "open": true, + "released": "2025-12-22" }, "zai/glm-5": { "cost": [ @@ -26197,7 +33885,10 @@ 0.2, 0.0 ], - "limit": 202752 + "limit": 202752, + "max_output": 131072, + "open": true, + "released": "2026-02-12" }, "zai/glm-5-turbo": { "cost": [ @@ -26206,7 +33897,9 @@ 0.24, 0.0 ], - "limit": 202752 + "limit": 202752, + "max_output": 131072, + "released": "2026-03-16" }, "zai/glm-5.1": { "cost": [ @@ -26215,7 +33908,10 @@ 0.26, 0.0 ], - "limit": 202752 + "limit": 202752, + "max_output": 131072, + "open": true, + "released": "2026-04-07" }, "zai/glm-5.2": { "cost": [ @@ -26224,7 +33920,10 @@ 0.26, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "zai/glm-5.3": { "cost": [ @@ -26233,7 +33932,10 @@ 0.26, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "zai/glm-5.3-flash": { "cost": [ @@ -26242,7 +33944,10 @@ 0.03, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-08-26" }, "zai/glm-5v-turbo": { "cost": [ @@ -26251,23 +33956,15 @@ 0.24, 0.0 ], - "limit": 202752 + "limit": 202752, + "max_output": 131072, + "released": "2026-04-01" } }, "name": "Eden AI" }, "empiriolabs": { "models": { - "deepseek-v4-1-flash": { - "cost": [ - 0.3, - 1.2, - 0.3, - 0.0 - ], - "limit": 1000000, - "status": "deprecated" - }, "deepseek-v4-1-flash-1017": { "cost": [ 0.3, @@ -26275,7 +33972,11 @@ 0.3, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 393216, + "open": true, + "released": "2026-10-17" }, "deepseek-v4-flash-0731": { "cost": [ @@ -26284,7 +33985,11 @@ 0.424, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 393216, + "open": true, + "released": "2026-07-31" }, "deepseek-v4-pro": { "cost": [ @@ -26293,7 +33998,11 @@ 1.65, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 393216, + "open": true, + "released": "2026-04-24" }, "deepseek-v4-pro-0813": { "cost": [ @@ -26302,7 +34011,10 @@ 1.32, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 393216, + "open": true, + "released": "2026-08-13" }, "fugu-max": { "cost": [ @@ -26311,7 +34023,9 @@ 0.25, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-09-11" }, "fugu-ultra-v1-0": { "cost": [ @@ -26321,6 +34035,8 @@ 0.0 ], "limit": 1000000, + "max_output": 131072, + "released": "2026-06-15", "tiers": [ { "cost": [ @@ -26344,6 +34060,8 @@ 0.0 ], "limit": 1000000, + "max_output": 131072, + "released": "2026-06-15", "tiers": [ { "cost": [ @@ -26366,7 +34084,10 @@ 0.5, 0.0 ], + "knowledge": "2026-08-28", "limit": 1000000, + "max_output": 131072, + "released": "2026-09-11", "tiers": [ { "cost": [ @@ -26389,7 +34110,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-08", + "limit": 128000, + "max_output": 8192, + "open": true, + "released": "2025-03-12" }, "gemma-4-26b-a4b": { "cost": [ @@ -26398,7 +34123,10 @@ 0.025, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-04-02" }, "glm-4-5-flash": { "cost": [ @@ -26407,7 +34135,10 @@ 0.0, 0.0 ], - "limit": 200000 + "knowledge": "2025-04", + "limit": 200000, + "max_output": 98304, + "released": "2025-07-28" }, "glm-4-6v-flash": { "cost": [ @@ -26416,7 +34147,10 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 32768, + "open": true, + "released": "2025-12-08" }, "glm-4-7-flash": { "cost": [ @@ -26425,7 +34159,11 @@ 0.0, 0.0 ], - "limit": 200000 + "knowledge": "2025-04", + "limit": 200000, + "max_output": 131072, + "open": true, + "released": "2026-01-19" }, "glm-5-1": { "cost": [ @@ -26435,6 +34173,9 @@ 0.0 ], "limit": 202000, + "max_output": 128000, + "open": true, + "released": "2026-04-07", "tiers": [ { "cost": [ @@ -26457,7 +34198,10 @@ 1.4, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "glm-5-3": { "cost": [ @@ -26466,7 +34210,10 @@ 1.4, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "glm-5-3-flash": { "cost": [ @@ -26475,7 +34222,10 @@ 0.075, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-26" }, "kimi-k2-6": { "cost": [ @@ -26484,7 +34234,11 @@ 0.1788, 0.0 ], - "limit": 256000 + "knowledge": "2025-01", + "limit": 256000, + "max_output": 16000, + "open": true, + "released": "2026-04-20" }, "kimi-k2-7-code": { "cost": [ @@ -26493,7 +34247,11 @@ 0.95, 0.0 ], - "limit": 256000 + "knowledge": "2025-01", + "limit": 256000, + "max_output": 131072, + "open": true, + "released": "2026-06-12" }, "kimi-k2-7-code-highspeed": { "cost": [ @@ -26502,7 +34260,11 @@ 1.9, 0.0 ], - "limit": 256000 + "knowledge": "2025-01", + "limit": 256000, + "max_output": 131072, + "open": true, + "released": "2026-06-12" }, "kimi-k3": { "cost": [ @@ -26511,7 +34273,10 @@ 3.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-07-16" }, "mimo-v2-6-flash": { "cost": [ @@ -26520,7 +34285,10 @@ 0.14, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-09-22" }, "mimo-v2-6-pro": { "cost": [ @@ -26529,7 +34297,10 @@ 0.435, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-09-22" }, "mimo-v2-6-pro-ultraspeed": { "cost": [ @@ -26538,7 +34309,10 @@ 4.35, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-09-21" }, "minimax-m2-7": { "cost": [ @@ -26548,6 +34322,9 @@ 0.0 ], "limit": 200000, + "max_output": 32768, + "open": true, + "released": "2026-03-18", "status": "deprecated" }, "minimax-m2-7-highspeed": { @@ -26558,6 +34335,9 @@ 0.0 ], "limit": 200000, + "max_output": 32768, + "open": true, + "released": "2026-03-18", "status": "deprecated" }, "minimax-m3": { @@ -26568,6 +34348,9 @@ 0.0 ], "limit": 1000000, + "max_output": 524288, + "open": true, + "released": "2026-06-01", "tiers": [ { "cost": [ @@ -26590,7 +34373,9 @@ 0.01125, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 524288, + "released": "2026-10-19" }, "mistral-small-4": { "cost": [ @@ -26599,7 +34384,11 @@ 0.15, 0.0 ], - "limit": 256000 + "knowledge": "2025-06", + "limit": 256000, + "max_output": 65536, + "open": true, + "released": "2026-03-16" }, "muse-glimmer-30b": { "cost": [ @@ -26608,7 +34397,11 @@ 0.05, 0.0 ], - "limit": 131072 + "knowledge": "2026-01-04", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2026-08-10" }, "muse-spark-1-1": { "cost": [ @@ -26617,7 +34410,9 @@ 1.0, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-04-08" }, "muse-spark-1-2": { "cost": [ @@ -26626,7 +34421,9 @@ 1.0, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-08-05" }, "muse-spark-1-3": { "cost": [ @@ -26635,7 +34432,9 @@ 1.0, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-09-02" }, "qwen3-5-122b-a10b": { "cost": [ @@ -26645,6 +34444,9 @@ 0.0 ], "limit": 256000, + "max_output": 64000, + "open": true, + "released": "2026-02-23", "tiers": [ { "cost": [ @@ -26668,6 +34470,9 @@ 0.0 ], "limit": 256000, + "max_output": 64000, + "open": true, + "released": "2026-02-23", "tiers": [ { "cost": [ @@ -26691,6 +34496,9 @@ 0.0 ], "limit": 256000, + "max_output": 64000, + "open": true, + "released": "2026-02-23", "tiers": [ { "cost": [ @@ -26714,6 +34522,9 @@ 0.0 ], "limit": 256000, + "max_output": 64000, + "open": true, + "released": "2026-02-15", "status": "deprecated", "tiers": [ { @@ -26737,7 +34548,10 @@ 0.02, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-03-02" }, "qwen3-5-9b": { "cost": [ @@ -26746,7 +34560,10 @@ 0.045, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-02-23" }, "qwen3-5-flash": { "cost": [ @@ -26755,7 +34572,9 @@ 0.09, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 32768, + "released": "2026-02-23" }, "qwen3-5-plus": { "cost": [ @@ -26764,7 +34583,10 @@ 0.36, 0.0 ], + "knowledge": "2025-04", "limit": 1000000, + "max_output": 65536, + "released": "2026-02-16", "status": "deprecated", "tiers": [ { @@ -26788,7 +34610,10 @@ 0.412564, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 64000, + "open": true, + "released": "2026-04-22" }, "qwen3-6-35b-a3b": { "cost": [ @@ -26797,7 +34622,10 @@ 0.035, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 16384, + "open": true, + "released": "2026-04-17" }, "qwen3-6-flash": { "cost": [ @@ -26807,6 +34635,8 @@ 0.0 ], "limit": 1000000, + "max_output": 65536, + "released": "2026-04-27", "tiers": [ { "cost": [ @@ -26829,7 +34659,10 @@ 0.5, 0.0 ], + "knowledge": "2025-04", "limit": 1000000, + "max_output": 65536, + "released": "2026-04-02", "tiers": [ { "cost": [ @@ -26853,6 +34686,8 @@ 0.0 ], "limit": 1000000, + "max_output": 65536, + "released": "2026-07-15", "tiers": [ { "cost": [ @@ -26887,7 +34722,9 @@ 2.5, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 65536, + "released": "2026-05-21" }, "qwen3-7-plus": { "cost": [ @@ -26896,7 +34733,10 @@ 0.4, 0.0 ], + "knowledge": "2025-04", "limit": 1000000, + "max_output": 65536, + "released": "2026-06-02", "tiers": [ { "cost": [ @@ -26919,7 +34759,10 @@ 0.08, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-08-14" }, "qwen3-8-flash": { "cost": [ @@ -26928,7 +34771,9 @@ 0.16, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-08-26" }, "qwen3-8-max": { "cost": [ @@ -26937,7 +34782,9 @@ 2.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-08-03" }, "qwen3-8-max-0902": { "cost": [ @@ -26946,7 +34793,9 @@ 2.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-09-02" }, "qwen3-8-omni-flash": { "cost": [ @@ -26955,7 +34804,9 @@ 0.3, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-09-17" }, "seed-2-0-code": { "cost": [ @@ -26965,6 +34816,8 @@ 0.0 ], "limit": 256000, + "max_output": 128000, + "released": "2026-02-14", "tiers": [ { "cost": [ @@ -26988,6 +34841,8 @@ 0.0 ], "limit": 256000, + "max_output": 128000, + "released": "2026-02-14", "tiers": [ { "cost": [ @@ -27011,6 +34866,8 @@ 0.0 ], "limit": 256000, + "max_output": 128000, + "released": "2026-02-14", "tiers": [ { "cost": [ @@ -27034,6 +34891,8 @@ 0.0 ], "limit": 256000, + "max_output": 128000, + "released": "2026-02-14", "tiers": [ { "cost": [ @@ -27056,7 +34915,9 @@ 0.63, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 65536, + "released": "2026-06-23" }, "step-3-5-flash": { "cost": [ @@ -27065,7 +34926,11 @@ 0.02, 0.0 ], - "limit": 256000 + "knowledge": "2025-01", + "limit": 256000, + "max_output": 131072, + "open": true, + "released": "2026-01-29" }, "step-3-5-flash-2603": { "cost": [ @@ -27074,7 +34939,11 @@ 0.02, 0.0 ], - "limit": 256000 + "knowledge": "2025-01", + "limit": 256000, + "max_output": 131072, + "open": true, + "released": "2026-04-02" }, "step-3-7-flash": { "cost": [ @@ -27083,7 +34952,11 @@ 0.04, 0.0 ], - "limit": 256000 + "knowledge": "2026-03-01", + "limit": 256000, + "max_output": 131072, + "open": true, + "released": "2026-05-29" }, "step-5-preview": { "cost": [ @@ -27092,7 +34965,10 @@ 0.05, 0.0 ], - "limit": 1024000 + "limit": 1024000, + "max_output": 131072, + "open": true, + "released": "2026-09-16" } }, "name": "EmpirioLabs AI" @@ -27106,7 +34982,11 @@ 0.009, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 128000, + "open": true, + "released": "2026-07-31" }, "deepseek-v4.1-flash": { "cost": [ @@ -27115,7 +34995,11 @@ 0.006, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 65536, + "open": true, + "released": "2026-09-10" }, "deepseek-v4.1-flash-1017": { "cost": [ @@ -27124,7 +35008,11 @@ 0.006, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 65536, + "open": true, + "released": "2026-10-17" }, "glm-5.2": { "cost": [ @@ -27133,7 +35021,10 @@ 0.18, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-06-13" }, "glm-5.3": { "cost": [ @@ -27142,7 +35033,10 @@ 0.18, 0.0 ], - "limit": 327680 + "limit": 327680, + "max_output": 32768, + "open": true, + "released": "2026-08-14" }, "glm-5.3-flash": { "cost": [ @@ -27151,7 +35045,10 @@ 0.027, 0.0 ], - "limit": 327680 + "limit": 327680, + "max_output": 32768, + "open": true, + "released": "2026-08-26" }, "kimi-k3": { "cost": [ @@ -27160,7 +35057,10 @@ 0.195, 0.0 ], - "limit": 1113088 + "limit": 1113088, + "max_output": 65536, + "open": true, + "released": "2026-07-16" }, "qwen3.6-35b-a3b": { "cost": [ @@ -27169,7 +35069,10 @@ 0.015, 0.0 ], - "limit": 208192 + "limit": 208192, + "max_output": 8192, + "open": true, + "released": "2026-04-17" }, "qwen3.8-27b": { "cost": [ @@ -27178,7 +35081,10 @@ 0.015, 0.0 ], - "limit": 1001536 + "limit": 1001536, + "max_output": 65536, + "open": true, + "released": "2026-08-14" } }, "name": "engy" @@ -27192,7 +35098,11 @@ 0.0, 0.0 ], - "limit": 40960 + "limit": 40960, + "max_output": 4096, + "open": true, + "released": "2025-06-05", + "type": "embedding" }, "Qwen/Qwen3-Reranker-4B": { "cost": [ @@ -27201,7 +35111,11 @@ 0.0, 0.0 ], - "limit": 32000 + "limit": 32000, + "max_output": 4096, + "open": true, + "released": "2025-07-30", + "type": "reranking" }, "Qwen/Qwen3.6-35B-A3B": { "cost": [ @@ -27210,7 +35124,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-04-17" }, "Qwen/Qwen3.8-27B": { "cost": [ @@ -27219,7 +35136,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-08-14" }, "evroc/roc": { "cost": [ @@ -27228,7 +35148,10 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2026-01", + "limit": 262144, + "max_output": 262144, + "released": "2026-06-06" }, "google/gemma-4-26B-A4B-it": { "cost": [ @@ -27237,7 +35160,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-04-02" }, "intfloat/multilingual-e5-large-instruct": { "cost": [ @@ -27246,7 +35172,11 @@ 0.0, 0.0 ], - "limit": 512 + "limit": 512, + "max_output": 512, + "open": true, + "released": "2024-06-01", + "type": "embedding" }, "mistralai/Mistral-Medium-3.5-128B": { "cost": [ @@ -27255,7 +35185,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-29" }, "moonshotai/Kimi-K2.6": { "cost": [ @@ -27264,7 +35197,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-20" }, "nvidia/Llama-3.3-70B-Instruct-FP8": { "cost": [ @@ -27273,7 +35210,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2023-12", + "limit": 128000, + "max_output": 4096, + "open": true, + "released": "2024-12-06" }, "openai/gpt-oss-120b": { "cost": [ @@ -27282,7 +35223,11 @@ 0.0, 0.0 ], - "limit": 65536 + "knowledge": "2024-06", + "limit": 65536, + "max_output": 65536, + "open": true, + "released": "2025-08-05" }, "openai/whisper-large-v3": { "cost": [ @@ -27291,7 +35236,11 @@ 0.0, 0.0 ], - "limit": 448 + "limit": 448, + "max_output": 4096, + "open": true, + "released": "2023-11-06", + "type": "transcription" }, "openai/whisper-large-v3-turbo": { "cost": [ @@ -27300,7 +35249,11 @@ 0.0, 0.0 ], - "limit": 448 + "limit": 448, + "max_output": 448, + "open": true, + "released": "2024-10-01", + "type": "transcription" }, "zai-org/GLM-5.2": { "cost": [ @@ -27309,7 +35262,10 @@ 0.0, 0.0 ], - "limit": 524288 + "limit": 524288, + "max_output": 131072, + "open": true, + "released": "2026-06-13" } }, "name": "evroc" @@ -27323,7 +35279,10 @@ 1.5, 18.75 ], - "limit": 200000 + "knowledge": "2025-03-31", + "limit": 200000, + "max_output": 32000, + "released": "2025-08-05" }, "anthropic/claude-opus-4.8": { "cost": [ @@ -27332,7 +35291,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-28" }, "anthropic/claude-sonnet-4.6": { "cost": [ @@ -27341,7 +35303,10 @@ 0.3, 3.75 ], - "limit": 1000000 + "knowledge": "2025-08-31", + "limit": 1000000, + "max_output": 64000, + "released": "2026-02-17" }, "deepseek/deepseek-v4-pro": { "cost": [ @@ -27350,7 +35315,11 @@ 0.145, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "google/gemini-2.5-flash": { "cost": [ @@ -27359,7 +35328,10 @@ 0.03, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2025-06-17" }, "google/gemini-2.5-pro": { "cost": [ @@ -27368,7 +35340,10 @@ 0.125, 0.0 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2025-06-17", "tiers": [ { "cost": [ @@ -27391,7 +35366,11 @@ 0.0, 0.0 ], - "limit": 65536 + "knowledge": "2025-01", + "limit": 65536, + "max_output": 32768, + "released": "2025-11-20", + "type": "image" }, "google/gemini-3.1-flash-image-preview": { "cost": [ @@ -27400,7 +35379,11 @@ 0.0, 0.0 ], - "limit": 65536 + "knowledge": "2025-01", + "limit": 65536, + "max_output": 65536, + "released": "2026-02-26", + "type": "image" }, "google/gemini-3.1-pro-preview": { "cost": [ @@ -27409,7 +35392,10 @@ 0.2, 0.0 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2026-02-19", "tiers": [ { "cost": [ @@ -27432,7 +35418,10 @@ 0.15, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-05-19" }, "google/gemma-4-31b-it": { "cost": [ @@ -27441,7 +35430,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-04-02" }, "minimax/minimax-m2.7": { "cost": [ @@ -27450,7 +35443,10 @@ 0.06, 0.375 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-03-18" }, "minimax/minimax-m2.7-highspeed": { "cost": [ @@ -27459,7 +35455,10 @@ 0.06, 0.375 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-03-18" }, "moonshotai/kimi-k2.6": { "cost": [ @@ -27468,7 +35467,11 @@ 0.15, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-20" }, "openai/gpt-4.1": { "cost": [ @@ -27477,7 +35480,10 @@ 0.5, 0.0 ], - "limit": 1047576 + "knowledge": "2024-04", + "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14" }, "openai/gpt-5": { "cost": [ @@ -27486,7 +35492,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-10-01", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "openai/gpt-5-mini": { "cost": [ @@ -27495,7 +35504,10 @@ 0.025, 0.0 ], - "limit": 400000 + "knowledge": "2024-10-01", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "openai/gpt-5-nano": { "cost": [ @@ -27504,7 +35516,10 @@ 0.005, 0.0 ], - "limit": 400000 + "knowledge": "2024-10-01", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "openai/gpt-5.3-codex": { "cost": [ @@ -27513,7 +35528,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-02-05" }, "openai/gpt-5.4-mini": { "cost": [ @@ -27522,7 +35540,10 @@ 0.075, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "openai/gpt-5.4-nano": { "cost": [ @@ -27531,7 +35552,10 @@ 0.02, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "openai/gpt-5.5": { "cost": [ @@ -27540,7 +35564,10 @@ 0.5, 0.0 ], + "knowledge": "2025-12-01", "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23", "tiers": [ { "cost": [ @@ -27563,7 +35590,10 @@ 0.0, 0.0 ], + "knowledge": "2025-12-01", "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23", "tiers": [ { "cost": [ @@ -27586,7 +35616,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "openai/gpt-oss-20b": { "cost": [ @@ -27595,7 +35629,11 @@ 0.007, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "sarvam/sarvam-105b": { "cost": [ @@ -27604,7 +35642,10 @@ 0.025, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2026-02-18" }, "x-ai/grok-4": { "cost": [ @@ -27613,7 +35654,10 @@ 0.75, 15.0 ], + "knowledge": "2025-07", "limit": 256000, + "max_output": 64000, + "released": "2025-07-09", "status": "deprecated" }, "x-ai/grok-4.3": { @@ -27624,6 +35668,8 @@ 0.0 ], "limit": 1000000, + "max_output": 30000, + "released": "2026-04-17", "tiers": [ { "cost": [ @@ -27647,6 +35693,8 @@ 0.0 ], "limit": 256000, + "max_output": 256000, + "released": "2026-04-16", "tiers": [ { "cost": [ @@ -27669,7 +35717,10 @@ 0.12, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-02-12" }, "z-ai/glm-5.1": { "cost": [ @@ -27678,7 +35729,10 @@ 0.205, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 131072, + "open": true, + "released": "2026-04-07" } }, "name": "FastRouter" @@ -27692,7 +35746,11 @@ 0.006, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-09-10" }, "accounts/fireworks/models/deepseek-v4p1-flash-1017": { "cost": [ @@ -27701,7 +35759,11 @@ 0.006, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-10-17" }, "accounts/fireworks/models/deepseek-v4p1-flash-1017-priority": { "cost": [ @@ -27710,7 +35772,11 @@ 0.0075, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-10-17" }, "accounts/fireworks/models/deepseek-v4p1-flash-priority": { "cost": [ @@ -27719,7 +35785,11 @@ 0.0075, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-09-10" }, "accounts/fireworks/models/ember-1": { "cost": [ @@ -27728,7 +35798,9 @@ 0.3, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-09-22" }, "accounts/fireworks/models/glm-5p3": { "cost": [ @@ -27737,7 +35809,10 @@ 0.26, 0.0 ], - "limit": 1048573 + "limit": 1048573, + "max_output": 262144, + "open": true, + "released": "2026-08-14" }, "accounts/fireworks/models/glm-5p3-flash": { "cost": [ @@ -27746,7 +35821,10 @@ 0.03, 0.0 ], - "limit": 1048573 + "limit": 1048573, + "max_output": 131072, + "open": true, + "released": "2026-08-26" }, "accounts/fireworks/models/glm-5p3-flash-priority": { "cost": [ @@ -27755,7 +35833,10 @@ 0.0375, 0.0 ], - "limit": 1048573 + "limit": 1048573, + "max_output": 131072, + "open": true, + "released": "2026-08-26" }, "accounts/fireworks/models/glm-5p3-priority": { "cost": [ @@ -27764,7 +35845,10 @@ 0.325, 0.0 ], - "limit": 1048573 + "limit": 1048573, + "max_output": 262144, + "open": true, + "released": "2026-08-14" }, "accounts/fireworks/models/gpt-oss-120b": { "cost": [ @@ -27773,7 +35857,11 @@ 0.015, 0.0 ], + "knowledge": "2024-06", "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05", "status": "deprecated" }, "accounts/fireworks/models/gpt-oss-120b-priority": { @@ -27783,7 +35871,11 @@ 0.018, 0.0 ], + "knowledge": "2024-06", "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05", "status": "deprecated" }, "accounts/fireworks/models/inkling": { @@ -27794,6 +35886,9 @@ 0.0 ], "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-07-15", "status": "deprecated" }, "accounts/fireworks/models/kimi-k3": { @@ -27803,7 +35898,10 @@ 0.3, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-16" }, "accounts/fireworks/models/kimi-k3-priority": { "cost": [ @@ -27812,7 +35910,10 @@ 0.375, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-16" }, "accounts/fireworks/models/minimax-m3": { "cost": [ @@ -27821,7 +35922,10 @@ 0.06, 0.0 ], - "limit": 512000 + "limit": 512000, + "max_output": 512000, + "open": true, + "released": "2026-06-01" }, "accounts/fireworks/models/minimax-m3-priority": { "cost": [ @@ -27830,7 +35934,10 @@ 0.09, 0.0 ], - "limit": 512000 + "limit": 512000, + "max_output": 512000, + "open": true, + "released": "2026-06-01" }, "accounts/fireworks/models/minimax-m3p1-flash": { "cost": [ @@ -27839,7 +35946,20 @@ 0.015, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 512000, + "released": "2026-10-19" + }, + "accounts/fireworks/models/minimax-m3p1-flash-priority": { + "cost": [ + 0.225, + 0.9, + 0.0225, + 0.0 + ], + "limit": 1000000, + "max_output": 512000, + "released": "2026-10-19" }, "accounts/fireworks/models/muse-spark-open": { "cost": [ @@ -27848,7 +35968,11 @@ 0.15, 0.0 ], - "limit": 1048576 + "knowledge": "2026-01-04", + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-10-15" }, "accounts/fireworks/models/nemotron-3-ultra-nvfp4": { "cost": [ @@ -27857,7 +35981,11 @@ 0.12, 0.0 ], + "knowledge": "2025-09", "limit": 262144, + "max_output": 128000, + "open": true, + "released": "2026-06-04", "status": "deprecated" }, "accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b": { @@ -27867,7 +35995,11 @@ 0.01, 0.0 ], + "knowledge": "2025-09", "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-08-11", "status": "deprecated" }, "accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b-priority": { @@ -27877,7 +36009,11 @@ 0.0125, 0.0 ], + "knowledge": "2025-09", "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-08-11", "status": "deprecated" }, "accounts/fireworks/models/qwen3p8-2p4t-a95b": { @@ -27887,7 +36023,10 @@ 0.25, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 131072, + "open": true, + "released": "2026-08-12" }, "accounts/fireworks/models/qwen3p8-max": { "cost": [ @@ -27896,7 +36035,9 @@ 0.25, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 131072, + "released": "2026-08-03" }, "accounts/fireworks/models/qwen3p8-max-priority": { "cost": [ @@ -27905,7 +36046,9 @@ 0.375, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 131072, + "released": "2026-08-03" }, "accounts/fireworks/routers/deepseek-flash-latest": { "cost": [ @@ -27914,7 +36057,11 @@ 0.006, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-10-17" }, "accounts/fireworks/routers/deepseek-flash-latest-priority": { "cost": [ @@ -27923,7 +36070,11 @@ 0.0075, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-10-17" }, "accounts/fireworks/routers/deepseek-v4p1-flash-1017-spot": { "cost": [ @@ -27932,7 +36083,11 @@ 0.0042, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-10-17" }, "accounts/fireworks/routers/deepseek-v4p1-flash-spot": { "cost": [ @@ -27941,7 +36096,11 @@ 0.0042, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-09-10" }, "accounts/fireworks/routers/glm-5p3-fast": { "cost": [ @@ -27950,7 +36109,10 @@ 0.39, 0.0 ], - "limit": 1048572 + "limit": 1048572, + "max_output": 262144, + "open": true, + "released": "2026-08-14" }, "accounts/fireworks/routers/glm-5p3-spot": { "cost": [ @@ -27959,7 +36121,10 @@ 0.182, 0.0 ], - "limit": 1048573 + "limit": 1048573, + "max_output": 262144, + "open": true, + "released": "2026-08-14" }, "accounts/fireworks/routers/glm-fast-latest": { "cost": [ @@ -27968,7 +36133,10 @@ 0.39, 0.0 ], - "limit": 1048572 + "limit": 1048572, + "max_output": 262144, + "open": true, + "released": "2026-08-14" }, "accounts/fireworks/routers/glm-flash-latest": { "cost": [ @@ -27977,7 +36145,10 @@ 0.03, 0.0 ], - "limit": 1048573 + "limit": 1048573, + "max_output": 131072, + "open": true, + "released": "2026-08-26" }, "accounts/fireworks/routers/glm-flash-latest-priority": { "cost": [ @@ -27986,7 +36157,10 @@ 0.0375, 0.0 ], - "limit": 1048573 + "limit": 1048573, + "max_output": 131072, + "open": true, + "released": "2026-08-26" }, "accounts/fireworks/routers/glm-latest": { "cost": [ @@ -27995,7 +36169,10 @@ 0.26, 0.0 ], - "limit": 1048573 + "limit": 1048573, + "max_output": 262144, + "open": true, + "released": "2026-08-14" }, "accounts/fireworks/routers/glm-latest-priority": { "cost": [ @@ -28004,7 +36181,10 @@ 0.325, 0.0 ], - "limit": 1048573 + "limit": 1048573, + "max_output": 262144, + "open": true, + "released": "2026-08-14" }, "accounts/fireworks/routers/kimi-fast-latest": { "cost": [ @@ -28013,7 +36193,10 @@ 0.45, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-16" }, "accounts/fireworks/routers/kimi-k3-fast": { "cost": [ @@ -28022,7 +36205,10 @@ 0.45, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-16" }, "accounts/fireworks/routers/kimi-k3-spot": { "cost": [ @@ -28031,7 +36217,10 @@ 0.21, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-16" }, "accounts/fireworks/routers/kimi-latest": { "cost": [ @@ -28040,7 +36229,10 @@ 0.3, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-16" }, "accounts/fireworks/routers/kimi-latest-priority": { "cost": [ @@ -28049,7 +36241,10 @@ 0.375, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-16" }, "accounts/fireworks/routers/minimax-latest": { "cost": [ @@ -28058,7 +36253,10 @@ 0.06, 0.0 ], - "limit": 512000 + "limit": 512000, + "max_output": 512000, + "open": true, + "released": "2026-06-01" }, "accounts/fireworks/routers/minimax-latest-priority": { "cost": [ @@ -28067,7 +36265,10 @@ 0.09, 0.0 ], - "limit": 512000 + "limit": 512000, + "max_output": 512000, + "open": true, + "released": "2026-06-01" }, "accounts/fireworks/routers/qwen-max-latest": { "cost": [ @@ -28076,7 +36277,9 @@ 0.25, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 131072, + "released": "2026-08-03" }, "accounts/fireworks/routers/qwen-max-latest-priority": { "cost": [ @@ -28085,7 +36288,9 @@ 0.375, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 131072, + "released": "2026-08-03" } }, "name": "Fireworks AI" @@ -28099,7 +36304,10 @@ 1.0, 12.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-09" }, "claude-haiku-4-5-20251001": { "cost": [ @@ -28108,7 +36316,10 @@ 0.1, 1.25 ], - "limit": 200000 + "knowledge": "2025-02-28", + "limit": 200000, + "max_output": 64000, + "released": "2025-10-15" }, "claude-opus-4-6": { "cost": [ @@ -28117,7 +36328,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2025-05-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-05" }, "claude-opus-4-7": { "cost": [ @@ -28126,7 +36340,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-16" }, "claude-opus-4-8": { "cost": [ @@ -28135,7 +36352,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-28" }, "claude-sonnet-4-6": { "cost": [ @@ -28144,7 +36364,10 @@ 0.3, 3.75 ], - "limit": 1000000 + "knowledge": "2025-08-31", + "limit": 1000000, + "max_output": 64000, + "released": "2026-02-17" }, "gpt-5.3-codex": { "cost": [ @@ -28153,7 +36376,10 @@ 0.175, 1.75 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-02-05" }, "gpt-5.4": { "cost": [ @@ -28162,7 +36388,10 @@ 0.25, 2.5 ], - "limit": 1050000 + "knowledge": "2025-08-31", + "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05" }, "gpt-5.4-mini": { "cost": [ @@ -28171,7 +36400,10 @@ 0.075, 0.75 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "gpt-5.5": { "cost": [ @@ -28180,22 +36412,16 @@ 0.5, 5.0 ], - "limit": 1050000 + "knowledge": "2025-12-01", + "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23" } }, "name": "FreeModel" }, "friendli": { "models": { - "deepseek-ai/DeepSeek-V3.2": { - "cost": [ - 0.5, - 1.5, - 0.25, - 0.0 - ], - "limit": 163840 - }, "google/gemma-4-31B-it": { "cost": [ 0.14, @@ -28203,7 +36429,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-04-02" }, "zai-org/GLM-5.1": { "cost": [ @@ -28212,7 +36442,10 @@ 0.26, 0.0 ], - "limit": 202752 + "limit": 202752, + "max_output": 131072, + "open": true, + "released": "2026-04-07" }, "zai-org/GLM-5.2": { "cost": [ @@ -28221,7 +36454,10 @@ 0.26, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "zai-org/GLM-5.3": { "cost": [ @@ -28230,7 +36466,10 @@ 0.234, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "zai-org/GLM-5.3-Flash": { "cost": [ @@ -28239,7 +36478,10 @@ 0.03, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-08-26" } }, "name": "Friendli" @@ -28253,7 +36495,10 @@ 0.1, 1.25 ], - "limit": 200000 + "knowledge": "2025-02-28", + "limit": 200000, + "max_output": 64000, + "released": "2025-10-15" }, "claude-opus-4-6": { "cost": [ @@ -28262,7 +36507,10 @@ 0.5, 6.25 ], - "limit": 200000 + "knowledge": "2025-05-31", + "limit": 200000, + "max_output": 128000, + "released": "2026-02-05" }, "claude-opus-4-7": { "cost": [ @@ -28271,7 +36519,10 @@ 0.5, 6.25 ], - "limit": 200000 + "knowledge": "2026-01-31", + "limit": 200000, + "max_output": 128000, + "released": "2026-04-16" }, "claude-sonnet-4-6": { "cost": [ @@ -28280,7 +36531,10 @@ 0.3, 3.75 ], - "limit": 200000 + "knowledge": "2025-08-31", + "limit": 200000, + "max_output": 64000, + "released": "2026-02-17" }, "deepseek-v4-pro": { "cost": [ @@ -28289,7 +36543,11 @@ 0.044, 0.0 ], - "limit": 128000 + "knowledge": "2026-01", + "limit": 128000, + "max_output": 8192, + "open": true, + "released": "2026-04-24" }, "gemini-2.5-flash": { "cost": [ @@ -28298,7 +36556,10 @@ 0.075, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2025-06-17" }, "gemini-2.5-pro": { "cost": [ @@ -28307,7 +36568,10 @@ 0.31, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2025-06-17" }, "gemini-3-1-pro-preview": { "cost": [ @@ -28316,7 +36580,10 @@ 0.2, 0.0 ], - "limit": 1000000 + "knowledge": "2026-01", + "limit": 1000000, + "max_output": 64000, + "released": "2026-02-19" }, "gemini-3-flash-preview": { "cost": [ @@ -28325,7 +36592,10 @@ 0.05, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2025-12-17" }, "gpt-4o": { "cost": [ @@ -28334,7 +36604,10 @@ 1.25, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-05-13" }, "gpt-5-3-codex": { "cost": [ @@ -28343,7 +36616,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2026-01-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-02-05" }, "gpt-5-4-mini": { "cost": [ @@ -28352,7 +36628,10 @@ 0.075, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "gpt-5-4-nano": { "cost": [ @@ -28361,7 +36640,10 @@ 0.02, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "gpt-5-5": { "cost": [ @@ -28370,7 +36652,10 @@ 0.5, 0.0 ], - "limit": 272000 + "knowledge": "2025-08-31", + "limit": 272000, + "max_output": 128000, + "released": "2026-04-23" }, "gpt-oss-120b": { "cost": [ @@ -28379,7 +36664,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "gpt-oss-20b": { "cost": [ @@ -28388,7 +36677,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "grok-4-1-fast-non-reasoning": { "cost": [ @@ -28397,7 +36690,10 @@ 0.05, 0.0 ], - "limit": 2000000 + "knowledge": "2025-11", + "limit": 2000000, + "max_output": 128000, + "released": "2025-11-19" }, "grok-4-1-fast-reasoning": { "cost": [ @@ -28406,7 +36702,10 @@ 0.05, 0.0 ], - "limit": 2000000 + "knowledge": "2025-11", + "limit": 2000000, + "max_output": 128000, + "released": "2025-11-19" }, "grok-4-3": { "cost": [ @@ -28415,7 +36714,10 @@ 0.2, 0.0 ], - "limit": 1000000 + "knowledge": "2024-11", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-17" }, "grok-code-fast-1": { "cost": [ @@ -28424,7 +36726,10 @@ 0.02, 0.0 ], - "limit": 256000 + "knowledge": "2023-10", + "limit": 256000, + "max_output": 128000, + "released": "2025-09-02" }, "kimi-k2-6": { "cost": [ @@ -28433,7 +36738,11 @@ 0.16, 0.0 ], - "limit": 256000 + "knowledge": "2025-01", + "limit": 256000, + "max_output": 128000, + "open": true, + "released": "2026-04-20" }, "kimi-k2.5": { "cost": [ @@ -28442,7 +36751,11 @@ 0.1, 0.0 ], + "knowledge": "2025-01", "limit": 256000, + "max_output": 128000, + "open": true, + "released": "2026-01-27", "status": "deprecated" }, "minimax-m2-5": { @@ -28452,7 +36765,11 @@ 0.03, 0.0 ], + "knowledge": "2024-09", "limit": 192000, + "max_output": 8192, + "open": true, + "released": "2026-02-12", "status": "deprecated" }, "minimax-m2-7": { @@ -28462,7 +36779,11 @@ 0.06, 0.0 ], + "knowledge": "2024-09", "limit": 192000, + "max_output": 8192, + "open": true, + "released": "2026-03-18", "status": "deprecated" }, "qwen-3-6-plus": { @@ -28472,7 +36793,10 @@ 0.1, 0.0 ], + "knowledge": "2025-04", "limit": 1000000, + "max_output": 64000, + "released": "2026-04-02", "status": "deprecated" }, "zai-glm-5-1": { @@ -28482,7 +36806,11 @@ 0.26, 0.0 ], + "knowledge": "2024-10", "limit": 198000, + "max_output": 8192, + "open": true, + "released": "2026-04-07", "status": "deprecated" } }, @@ -28497,7 +36825,10 @@ 1.0, 12.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-09" }, "claude-fable-5.1": { "cost": [ @@ -28506,7 +36837,10 @@ 0.25, 12.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-01" }, "claude-haiku-4.5": { "cost": [ @@ -28515,7 +36849,10 @@ 0.1, 1.25 ], - "limit": 200000 + "knowledge": "2025-02-28", + "limit": 200000, + "max_output": 64000, + "released": "2025-10-15" }, "claude-haiku-5.5": { "cost": [ @@ -28524,7 +36861,10 @@ 0.01, 0.125 ], + "knowledge": "2026-06", "limit": 1000000, + "max_output": 128000, + "released": "2026-10-07", "tiers": [ { "cost": [ @@ -28547,7 +36887,10 @@ 0.5, 6.25 ], + "knowledge": "2026-01-31", "limit": 200000, + "max_output": 32000, + "released": "2026-04-16", "status": "deprecated" }, "claude-opus-4.7-fast": { @@ -28557,7 +36900,10 @@ 3.0, 37.5 ], + "knowledge": "2026-01-31", "limit": 200000, + "max_output": 32000, + "released": "2026-04-16", "status": "deprecated" }, "claude-opus-4.8": { @@ -28567,7 +36913,10 @@ 0.5, 6.25 ], - "limit": 200000 + "knowledge": "2026-01", + "limit": 200000, + "max_output": 64000, + "released": "2026-05-28" }, "claude-opus-4.8-fast": { "cost": [ @@ -28576,7 +36925,10 @@ 1.0, 12.5 ], - "limit": 200000 + "knowledge": "2026-01", + "limit": 200000, + "max_output": 64000, + "released": "2026-05-28" }, "claude-opus-5": { "cost": [ @@ -28585,7 +36937,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-05", + "limit": 1000000, + "max_output": 64000, + "released": "2026-07-24" }, "claude-opus-5.5": { "cost": [ @@ -28594,7 +36949,10 @@ 0.2, 5.0 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-22" }, "claude-sonnet-4.6": { "cost": [ @@ -28603,7 +36961,10 @@ 0.3, 3.75 ], - "limit": 200000 + "knowledge": "2025-08-31", + "limit": 200000, + "max_output": 32000, + "released": "2026-02-17" }, "claude-sonnet-5": { "cost": [ @@ -28612,7 +36973,10 @@ 0.2, 2.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-30" }, "claude-sonnet-5.5": { "cost": [ @@ -28621,7 +36985,10 @@ 0.1, 2.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-28" }, "gemini-3.5-flash": { "cost": [ @@ -28630,7 +36997,10 @@ 0.15, 0.0 ], + "knowledge": "2025-01", "limit": 200000, + "max_output": 64000, + "released": "2026-05-19", "status": "deprecated" }, "gemini-3.6-flash": { @@ -28640,7 +37010,10 @@ 0.075, 0.0 ], + "knowledge": "2026-03", "limit": 1000000, + "max_output": 64000, + "released": "2026-07-21", "status": "deprecated" }, "gemini-3.7-flash": { @@ -28650,7 +37023,10 @@ 0.075, 0.0 ], + "knowledge": "2026-03", "limit": 1000000, + "max_output": 64000, + "released": "2026-08-13", "status": "deprecated" }, "gemini-3.8-flash": { @@ -28660,7 +37036,9 @@ 0.075, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 64000, + "released": "2026-09-02" }, "gemini-4-argon": { "cost": [ @@ -28669,7 +37047,10 @@ 0.1, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-10-13" }, "gpt-5-mini": { "cost": [ @@ -28678,7 +37059,10 @@ 0.025, 0.0 ], + "knowledge": "2024-05-30", "limit": 264000, + "max_output": 64000, + "released": "2025-08-07", "status": "deprecated" }, "gpt-5.3-codex": { @@ -28688,7 +37072,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-02-05" }, "gpt-5.4": { "cost": [ @@ -28697,7 +37084,10 @@ 0.25, 0.0 ], + "knowledge": "2025-08-31", "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05", "status": "deprecated", "tiers": [ { @@ -28721,7 +37111,10 @@ 0.075, 0.0 ], + "knowledge": "2025-08-31", "limit": 400000, + "max_output": 128000, + "released": "2026-03-17", "status": "deprecated" }, "gpt-5.4-nano": { @@ -28731,7 +37124,10 @@ 0.02, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "gpt-5.5": { "cost": [ @@ -28740,7 +37136,10 @@ 0.5, 0.0 ], + "knowledge": "2025-12-01", "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23", "status": "deprecated", "tiers": [ { @@ -28764,7 +37163,10 @@ 0.02, 0.25 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -28787,7 +37189,10 @@ 0.4, 5.0 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -28810,7 +37215,10 @@ 0.2, 2.5 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -28833,7 +37241,10 @@ 1.0, 12.5 ], + "knowledge": "2026-04-30", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-04", "tiers": [ { "cost": [ @@ -28856,7 +37267,10 @@ 0.01, 0.125 ], + "knowledge": "2026-05-18", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -28879,7 +37293,10 @@ 0.2, 2.5 ], + "knowledge": "2026-04-20", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -28902,7 +37319,10 @@ 0.1, 2.5 ], + "knowledge": "2026-04-30", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-29", "tiers": [ { "cost": [ @@ -28918,6 +37338,32 @@ } ] }, + "gpt-6.1-terra": { + "cost": [ + 1.0, + 5.0, + 0.05, + 1.25 + ], + "knowledge": "2026-06-01", + "limit": 1050000, + "max_output": 128000, + "released": "2026-10-26", + "tiers": [ + { + "cost": [ + 2.0, + 7.5, + 0.1, + 2.5 + ], + "tier": { + "size": 272000, + "type": "context" + } + } + ] + }, "grok-4.5": { "cost": [ 2.0, @@ -28926,6 +37372,8 @@ 0.0 ], "limit": 500000, + "max_output": 128000, + "released": "2026-07-08", "tiers": [ { "cost": [ @@ -28948,7 +37396,10 @@ 0.5, 0.0 ], + "knowledge": "2026-02-01", "limit": 500000, + "max_output": 128000, + "released": "2026-08-12", "tiers": [ { "cost": [ @@ -28971,7 +37422,10 @@ 0.5, 0.0 ], + "knowledge": "2026-05", "limit": 500000, + "max_output": 128000, + "released": "2026-09-21", "tiers": [ { "cost": [ @@ -28994,7 +37448,11 @@ 0.19, 0.0 ], + "knowledge": "2025-01", "limit": 256000, + "max_output": 32000, + "open": true, + "released": "2026-06-12", "status": "deprecated" }, "kimi-k3": { @@ -29004,7 +37462,10 @@ 0.3, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-16" }, "mai-code-1.1-flash": { "cost": [ @@ -29013,7 +37474,9 @@ 0.02, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 128000, + "released": "2026-08-11" } }, "name": "GitHub Copilot" @@ -29027,7 +37490,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-09" }, "duo-chat-fable-5-1": { "cost": [ @@ -29036,7 +37502,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-01" }, "duo-chat-gpt-5-1": { "cost": [ @@ -29045,7 +37514,10 @@ 0.0, 0.0 ], + "knowledge": "2024-09-30", "limit": 400000, + "max_output": 128000, + "released": "2025-11-13", "status": "deprecated" }, "duo-chat-gpt-5-2": { @@ -29055,7 +37527,10 @@ 0.0, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "duo-chat-gpt-5-2-codex": { "cost": [ @@ -29064,7 +37539,10 @@ 0.0, 0.0 ], + "knowledge": "2025-08-31", "limit": 400000, + "max_output": 128000, + "released": "2025-12-11", "status": "deprecated" }, "duo-chat-gpt-5-3-codex": { @@ -29074,7 +37552,10 @@ 0.0, 0.0 ], + "knowledge": "2025-08-31", "limit": 400000, + "max_output": 128000, + "released": "2026-02-05", "status": "deprecated" }, "duo-chat-gpt-5-4": { @@ -29084,7 +37565,10 @@ 0.0, 0.0 ], - "limit": 1050000 + "knowledge": "2025-08-31", + "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05" }, "duo-chat-gpt-5-4-mini": { "cost": [ @@ -29093,7 +37577,10 @@ 0.0, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "duo-chat-gpt-5-4-nano": { "cost": [ @@ -29102,7 +37589,10 @@ 0.0, 0.0 ], + "knowledge": "2025-08-31", "limit": 400000, + "max_output": 128000, + "released": "2026-03-17", "status": "deprecated" }, "duo-chat-gpt-5-5": { @@ -29112,7 +37602,10 @@ 0.0, 0.0 ], - "limit": 1050000 + "knowledge": "2025-12-01", + "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23" }, "duo-chat-gpt-5-6-luna": { "cost": [ @@ -29121,7 +37614,10 @@ 0.0, 0.0 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "duo-chat-gpt-5-6-sol": { "cost": [ @@ -29130,7 +37626,10 @@ 0.0, 0.0 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "duo-chat-gpt-5-6-terra": { "cost": [ @@ -29139,7 +37638,10 @@ 0.0, 0.0 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "duo-chat-gpt-5-codex": { "cost": [ @@ -29148,7 +37650,10 @@ 0.0, 0.0 ], + "knowledge": "2024-09-30", "limit": 400000, + "max_output": 128000, + "released": "2025-09-15", "status": "deprecated" }, "duo-chat-gpt-5-mini": { @@ -29158,7 +37663,10 @@ 0.0, 0.0 ], + "knowledge": "2024-05-30", "limit": 400000, + "max_output": 128000, + "released": "2025-08-07", "status": "deprecated" }, "duo-chat-gpt-6-1-sol": { @@ -29168,7 +37676,10 @@ 0.0, 0.0 ], - "limit": 1050000 + "knowledge": "2026-04-30", + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-29" }, "duo-chat-gpt-6-astra": { "cost": [ @@ -29177,7 +37688,10 @@ 0.0, 0.0 ], - "limit": 1050000 + "knowledge": "2026-04-30", + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-04" }, "duo-chat-gpt-6-luna": { "cost": [ @@ -29186,7 +37700,10 @@ 0.0, 0.0 ], - "limit": 1050000 + "knowledge": "2026-05-18", + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22" }, "duo-chat-gpt-6-sol": { "cost": [ @@ -29195,7 +37712,10 @@ 0.0, 0.0 ], - "limit": 1050000 + "knowledge": "2026-04-20", + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22" }, "duo-chat-haiku-4-5": { "cost": [ @@ -29204,7 +37724,22 @@ 0.0, 0.0 ], - "limit": 200000 + "knowledge": "2025-02-28", + "limit": 200000, + "max_output": 64000, + "released": "2025-10-15" + }, + "duo-chat-haiku-5-5": { + "cost": [ + 0.0, + 0.0, + 0.0, + 0.0 + ], + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-10-07" }, "duo-chat-opus-4-5": { "cost": [ @@ -29213,7 +37748,10 @@ 0.0, 0.0 ], - "limit": 200000 + "knowledge": "2025-05", + "limit": 200000, + "max_output": 64000, + "released": "2025-11-24" }, "duo-chat-opus-4-6": { "cost": [ @@ -29222,7 +37760,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-05" }, "duo-chat-opus-4-7": { "cost": [ @@ -29231,7 +37772,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-16" }, "duo-chat-opus-4-8": { "cost": [ @@ -29240,7 +37784,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2026-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-28" }, "duo-chat-opus-5": { "cost": [ @@ -29249,7 +37796,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2026-05", + "limit": 1000000, + "max_output": 128000, + "released": "2026-07-24" }, "duo-chat-opus-5-5": { "cost": [ @@ -29258,7 +37808,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-22" }, "duo-chat-sonnet-4-5": { "cost": [ @@ -29267,7 +37820,10 @@ 0.0, 0.0 ], + "knowledge": "2025-07-31", "limit": 200000, + "max_output": 64000, + "released": "2025-09-29", "status": "deprecated" }, "duo-chat-sonnet-4-6": { @@ -29277,7 +37833,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-08-31", + "limit": 1000000, + "max_output": 64000, + "released": "2026-02-17" }, "duo-chat-sonnet-5": { "cost": [ @@ -29286,7 +37845,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 64000, + "released": "2026-06-30" }, "duo-chat-sonnet-5-5": { "cost": [ @@ -29295,7 +37857,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 64000, + "released": "2026-09-28" } }, "name": "GitLab Duo" @@ -29309,7 +37874,10 @@ 0.06, 0.0 ], - "limit": 196608 + "limit": 196608, + "max_output": 131072, + "open": true, + "released": "2026-03-18" }, "MiniMaxAI/MiniMax-M3": { "cost": [ @@ -29319,6 +37887,9 @@ 0.0 ], "limit": 1048576, + "max_output": 512000, + "open": true, + "released": "2026-06-01", "tiers": [ { "cost": [ @@ -29341,7 +37912,9 @@ 0.25, 3.125 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-05-21" }, "Qwen/Qwen3.8-Flash": { "cost": [ @@ -29350,7 +37923,9 @@ 0.016, 0.2 ], - "limit": 1048575 + "limit": 1048575, + "max_output": 131072, + "released": "2026-08-26" }, "Qwen/Qwen3.8-Max": { "cost": [ @@ -29359,7 +37934,9 @@ 0.25, 2.5 ], - "limit": 262144 + "limit": 262144, + "max_output": 131072, + "released": "2026-08-03" }, "anthropic/claude-opus-4.6": { "cost": [ @@ -29368,7 +37945,10 @@ 0.5, 0.0 ], - "limit": 409600 + "knowledge": "2025-05-31", + "limit": 409600, + "max_output": 128000, + "released": "2026-02-05" }, "anthropic/claude-opus-4.7": { "cost": [ @@ -29377,7 +37957,10 @@ 0.45, 0.0 ], - "limit": 409600 + "knowledge": "2026-01-31", + "limit": 409600, + "max_output": 128000, + "released": "2026-04-16" }, "anthropic/claude-opus-4.7-fast": { "cost": [ @@ -29386,7 +37969,10 @@ 3.0, 37.5 ], - "limit": 409600 + "knowledge": "2026-01-31", + "limit": 409600, + "max_output": 128000, + "released": "2026-04-16" }, "anthropic/claude-opus-4.8": { "cost": [ @@ -29395,7 +37981,10 @@ 0.5, 0.0 ], - "limit": 1000000 + "knowledge": "2026-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-28" }, "anthropic/claude-sonnet-4.6": { "cost": [ @@ -29404,7 +37993,10 @@ 0.3, 0.0 ], - "limit": 409600 + "knowledge": "2025-08-31", + "limit": 409600, + "max_output": 64000, + "released": "2026-02-17" }, "deepseek-ai/DeepSeek-V4-Flash": { "cost": [ @@ -29413,7 +38005,11 @@ 0.022, 0.0 ], - "limit": 1048575 + "knowledge": "2025-05", + "limit": 1048575, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "deepseek-ai/DeepSeek-V4-Pro": { "cost": [ @@ -29422,7 +38018,11 @@ 0.116, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "moonshotai/Kimi-K2.6": { "cost": [ @@ -29431,7 +38031,11 @@ 0.144, 0.0 ], - "limit": 65536 + "knowledge": "2025-01", + "limit": 65536, + "max_output": 65536, + "open": true, + "released": "2026-04-20" }, "moonshotai/kimi-k2.7-code-highspeed": { "cost": [ @@ -29440,7 +38044,11 @@ 0.38, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-06-12" }, "openai/gpt-5.5": { "cost": [ @@ -29449,7 +38057,10 @@ 0.5, 0.0 ], - "limit": 1050000 + "knowledge": "2025-12-01", + "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23" }, "zai-org/GLM-5-FP8": { "cost": [ @@ -29458,7 +38069,10 @@ 0.12, 0.0 ], - "limit": 202752 + "limit": 202752, + "max_output": 131072, + "open": true, + "released": "2026-02-12" }, "zai-org/GLM-5.1-FP8": { "cost": [ @@ -29467,7 +38081,10 @@ 0.182, 0.0 ], - "limit": 202752 + "limit": 202752, + "max_output": 131072, + "open": true, + "released": "2026-04-07" }, "zai-org/GLM-5.2-FP8": { "cost": [ @@ -29476,7 +38093,10 @@ 0.182, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-13" } }, "name": "GMI Cloud" @@ -29490,7 +38110,10 @@ 0.2, 0.0 ], + "knowledge": "2025-01", "limit": 131072, + "max_output": 65536, + "released": "2026-04-21", "tiers": [ { "cost": [ @@ -29513,7 +38136,10 @@ 0.2, 0.0 ], + "knowledge": "2025-01", "limit": 131072, + "max_output": 65536, + "released": "2026-04-21", "tiers": [ { "cost": [ @@ -29536,7 +38162,10 @@ 0.0, 0.0 ], + "knowledge": "2025-01", "limit": 128000, + "max_output": 64000, + "released": "2025-10-07", "tiers": [ { "cost": [ @@ -29559,7 +38188,10 @@ 0.03, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2025-06-17" }, "gemini-2.5-flash-image": { "cost": [ @@ -29568,7 +38200,12 @@ 0.075, 0.0 ], - "limit": 32768 + "knowledge": "2024-06", + "limit": 32768, + "max_output": 32768, + "released": "2025-08-26", + "status": "deprecated", + "type": "image" }, "gemini-2.5-flash-lite": { "cost": [ @@ -29577,7 +38214,10 @@ 0.01, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2025-06-17" }, "gemini-2.5-flash-preview-tts": { "cost": [ @@ -29586,7 +38226,11 @@ 0.0, 0.0 ], - "limit": 8192 + "knowledge": "2025-01", + "limit": 8192, + "max_output": 16384, + "released": "2025-05-01", + "type": "speech" }, "gemini-2.5-pro": { "cost": [ @@ -29595,7 +38239,10 @@ 0.125, 0.0 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2025-06-17", "tiers": [ { "cost": [ @@ -29618,7 +38265,11 @@ 0.0, 0.0 ], - "limit": 8192 + "knowledge": "2025-01", + "limit": 8192, + "max_output": 16384, + "released": "2025-05-01", + "type": "speech" }, "gemini-3-flash-preview": { "cost": [ @@ -29627,7 +38278,10 @@ 0.05, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2025-12-17" }, "gemini-3-pro-image": { "cost": [ @@ -29636,16 +38290,11 @@ 0.0, 0.0 ], - "limit": 65536 - }, - "gemini-3-pro-image-preview": { - "cost": [ - 2.0, - 120.0, - 0.0, - 0.0 - ], - "limit": 131072 + "knowledge": "2025-01", + "limit": 65536, + "max_output": 32768, + "released": "2026-05-28", + "type": "image" }, "gemini-3.1-flash-image": { "cost": [ @@ -29654,16 +38303,11 @@ 0.0, 0.0 ], - "limit": 131072 - }, - "gemini-3.1-flash-image-preview": { - "cost": [ - 0.5, - 60.0, - 0.0, - 0.0 - ], - "limit": 65536 + "knowledge": "2025-01", + "limit": 131072, + "max_output": 32768, + "released": "2026-05-28", + "type": "image" }, "gemini-3.1-flash-lite": { "cost": [ @@ -29672,7 +38316,10 @@ 0.025, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-05-07" }, "gemini-3.1-flash-lite-image": { "cost": [ @@ -29681,7 +38328,11 @@ 0.0, 0.0 ], - "limit": 65536 + "knowledge": "2025-01", + "limit": 65536, + "max_output": 4096, + "released": "2026-06-30", + "type": "image" }, "gemini-3.1-flash-lite-preview": { "cost": [ @@ -29690,7 +38341,10 @@ 0.025, 0.0 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2026-03-03", "status": "deprecated" }, "gemini-3.1-flash-live-preview": { @@ -29700,7 +38354,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2025-01", + "limit": 131072, + "max_output": 65536, + "released": "2026-03-26", + "type": "realtime" }, "gemini-3.1-flash-tts-preview": { "cost": [ @@ -29709,7 +38367,11 @@ 0.0, 0.0 ], - "limit": 8192 + "knowledge": "2025-01", + "limit": 8192, + "max_output": 16384, + "released": "2026-04-15", + "type": "speech" }, "gemini-3.1-pro-preview": { "cost": [ @@ -29718,7 +38380,10 @@ 0.2, 0.0 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2026-02-19", "tiers": [ { "cost": [ @@ -29741,7 +38406,10 @@ 0.2, 0.0 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2026-02-19", "tiers": [ { "cost": [ @@ -29764,7 +38432,10 @@ 0.15, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-05-19" }, "gemini-3.5-flash-lite": { "cost": [ @@ -29773,7 +38444,10 @@ 0.03, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-07-21" }, "gemini-3.5-live-translate-preview": { "cost": [ @@ -29782,7 +38456,11 @@ 0.0, 0.0 ], - "limit": 16384 + "knowledge": "2025-01", + "limit": 16384, + "max_output": 32768, + "released": "2026-06-09", + "type": "realtime" }, "gemini-3.6-flash": { "cost": [ @@ -29791,7 +38469,10 @@ 0.075, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-07-21" }, "gemini-3.7-flash": { "cost": [ @@ -29800,7 +38481,10 @@ 0.075, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-08-13" }, "gemini-3.8-flash": { "cost": [ @@ -29809,7 +38493,9 @@ 0.075, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65536, + "released": "2026-09-02" }, "gemini-4-argon": { "cost": [ @@ -29818,7 +38504,10 @@ 0.1, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 32768, + "released": "2026-10-13" }, "gemini-embedding-001": { "cost": [ @@ -29827,7 +38516,11 @@ 0.0, 0.0 ], - "limit": 2048 + "knowledge": "2025-05", + "limit": 2048, + "max_output": 1, + "released": "2025-05-20", + "type": "embedding" }, "gemini-embedding-2": { "cost": [ @@ -29836,7 +38529,11 @@ 0.0, 0.0 ], - "limit": 8192 + "knowledge": "2025-11", + "limit": 8192, + "max_output": 1, + "released": "2026-04-22", + "type": "embedding" }, "gemini-flash-latest": { "cost": [ @@ -29845,7 +38542,10 @@ 0.075, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-08-13" }, "gemini-flash-lite-latest": { "cost": [ @@ -29854,7 +38554,10 @@ 0.03, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-07-21" }, "gemini-omni-flash-preview": { "cost": [ @@ -29863,7 +38566,10 @@ 0.0, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 65536, + "released": "2026-06-30", + "type": "video" }, "gemini-pro-latest": { "cost": [ @@ -29872,7 +38578,10 @@ 0.2, 0.0 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2026-02-19", "tiers": [ { "cost": [ @@ -29895,7 +38604,9 @@ 0.0, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65536, + "released": "2026-03-25" }, "lyria-3-pro-preview": { "cost": [ @@ -29904,7 +38615,9 @@ 0.0, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65536, + "released": "2026-03-25" } }, "name": "Google" @@ -29918,7 +38631,10 @@ 0.25, 12.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-01" }, "claude-fable-5@default": { "cost": [ @@ -29927,7 +38643,10 @@ 1.0, 12.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-09" }, "claude-haiku-4-5@20251001": { "cost": [ @@ -29936,7 +38655,10 @@ 0.1, 1.25 ], - "limit": 200000 + "knowledge": "2025-02-28", + "limit": 200000, + "max_output": 64000, + "released": "2025-10-15" }, "claude-haiku-5-5@default": { "cost": [ @@ -29945,7 +38667,10 @@ 0.01, 0.125 ], + "knowledge": "2026-06", "limit": 1000000, + "max_output": 128000, + "released": "2026-10-07", "tiers": [ { "cost": [ @@ -29968,7 +38693,10 @@ 1.5, 18.75 ], + "knowledge": "2025-03-31", "limit": 200000, + "max_output": 32000, + "released": "2025-08-05", "status": "deprecated" }, "claude-opus-4-5@20251101": { @@ -29978,7 +38706,10 @@ 0.5, 6.25 ], - "limit": 200000 + "knowledge": "2025-05", + "limit": 200000, + "max_output": 64000, + "released": "2025-11-24" }, "claude-opus-4-6@default": { "cost": [ @@ -29987,7 +38718,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2025-05-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-05" }, "claude-opus-4-7@default": { "cost": [ @@ -29996,7 +38730,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-16" }, "claude-opus-4-8@default": { "cost": [ @@ -30005,7 +38742,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-28" }, "claude-opus-4@20250514": { "cost": [ @@ -30014,7 +38754,10 @@ 1.5, 18.75 ], + "knowledge": "2025-03-31", "limit": 200000, + "max_output": 32000, + "released": "2025-05-22", "status": "deprecated" }, "claude-opus-5-5@default": { @@ -30024,7 +38767,10 @@ 0.2, 5.0 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-22" }, "claude-opus-5@default": { "cost": [ @@ -30033,7 +38779,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-05", + "limit": 1000000, + "max_output": 128000, + "released": "2026-07-24" }, "claude-sonnet-4-5@20250929": { "cost": [ @@ -30042,7 +38791,10 @@ 0.3, 3.75 ], + "knowledge": "2025-07-31", "limit": 200000, + "max_output": 64000, + "released": "2025-09-29", "status": "deprecated" }, "claude-sonnet-4-6@default": { @@ -30052,7 +38804,10 @@ 0.3, 3.75 ], - "limit": 1000000 + "knowledge": "2025-08-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-17" }, "claude-sonnet-4@20250514": { "cost": [ @@ -30061,7 +38816,10 @@ 0.3, 3.75 ], + "knowledge": "2025-03-31", "limit": 200000, + "max_output": 64000, + "released": "2025-05-22", "status": "deprecated" }, "claude-sonnet-5-5@default": { @@ -30071,7 +38829,10 @@ 0.1, 2.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-28" }, "claude-sonnet-5@default": { "cost": [ @@ -30080,7 +38841,10 @@ 0.2, 2.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-30" }, "codestral-2": { "cost": [ @@ -30089,7 +38853,9 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 8192, + "released": "2025-07-30" }, "deepseek-ai/deepseek-v3.1-maas": { "cost": [ @@ -30099,6 +38865,9 @@ 0.0 ], "limit": 163840, + "max_output": 32768, + "open": true, + "released": "2025-08-28", "status": "deprecated" }, "deepseek-ai/deepseek-v3.2-maas": { @@ -30109,6 +38878,9 @@ 0.0 ], "limit": 163840, + "max_output": 65536, + "open": true, + "released": "2025-12-17", "status": "deprecated" }, "gemini-2.5-flash": { @@ -30118,7 +38890,10 @@ 0.03, 0.0 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2025-06-17", "status": "deprecated" }, "gemini-2.5-flash-image": { @@ -30128,7 +38903,11 @@ 0.0, 0.0 ], - "limit": 32768 + "knowledge": "2024-06", + "limit": 32768, + "max_output": 32768, + "released": "2025-08-26", + "type": "image" }, "gemini-2.5-flash-lite": { "cost": [ @@ -30137,7 +38916,10 @@ 0.01, 0.0 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2025-06-17", "status": "deprecated" }, "gemini-2.5-flash-tts": { @@ -30147,7 +38929,11 @@ 0.0, 0.0 ], - "limit": 32768 + "knowledge": "2025-01", + "limit": 32768, + "max_output": 16384, + "released": "2025-09-30", + "type": "speech" }, "gemini-2.5-pro": { "cost": [ @@ -30156,7 +38942,10 @@ 0.125, 0.0 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2025-06-17", "status": "deprecated", "tiers": [ { @@ -30180,7 +38969,11 @@ 0.0, 0.0 ], - "limit": 32768 + "knowledge": "2025-01", + "limit": 32768, + "max_output": 16384, + "released": "2025-09-30", + "type": "speech" }, "gemini-3-flash-preview": { "cost": [ @@ -30189,7 +38982,10 @@ 0.05, 0.0 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2025-12-17", "status": "beta" }, "gemini-3-pro-image": { @@ -30199,7 +38995,11 @@ 0.2, 0.0 ], - "limit": 65536 + "knowledge": "2025-01", + "limit": 65536, + "max_output": 32768, + "released": "2026-05-28", + "type": "image" }, "gemini-3.1-flash-image": { "cost": [ @@ -30208,7 +39008,11 @@ 0.05, 0.0 ], - "limit": 131072 + "knowledge": "2025-01", + "limit": 131072, + "max_output": 32768, + "released": "2026-05-28", + "type": "image" }, "gemini-3.1-flash-lite": { "cost": [ @@ -30217,7 +39021,10 @@ 0.025, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-05-07" }, "gemini-3.1-flash-lite-image": { "cost": [ @@ -30226,7 +39033,11 @@ 0.025, 0.0 ], - "limit": 65536 + "knowledge": "2025-01", + "limit": 65536, + "max_output": 4096, + "released": "2026-06-30", + "type": "image" }, "gemini-3.1-pro-preview": { "cost": [ @@ -30235,7 +39046,10 @@ 0.2, 0.0 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2026-02-19", "status": "beta", "tiers": [ { @@ -30259,7 +39073,10 @@ 0.2, 0.0 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2026-02-19", "status": "beta", "tiers": [ { @@ -30283,7 +39100,10 @@ 0.15, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-05-19" }, "gemini-3.5-flash-lite": { "cost": [ @@ -30292,7 +39112,10 @@ 0.03, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-07-21" }, "gemini-3.6-flash": { "cost": [ @@ -30301,7 +39124,10 @@ 0.075, 0.0 ], + "knowledge": "2026-03", "limit": 1048576, + "max_output": 65536, + "released": "2026-07-21", "status": "deprecated" }, "gemini-3.7-flash": { @@ -30311,7 +39137,10 @@ 0.075, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-08-13" }, "gemini-3.8-flash": { "cost": [ @@ -30320,7 +39149,9 @@ 0.075, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65536, + "released": "2026-09-02" }, "gemini-4-argon": { "cost": [ @@ -30329,7 +39160,10 @@ 0.1, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-10-13" }, "gemini-embedding-001": { "cost": [ @@ -30338,7 +39172,11 @@ 0.0, 0.0 ], - "limit": 2048 + "knowledge": "2025-05", + "limit": 2048, + "max_output": 1, + "released": "2025-05-20", + "type": "embedding" }, "gemini-nano-banana-2.1": { "cost": [ @@ -30347,7 +39185,10 @@ 0.15, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 32768, + "released": "2026-10-06", + "type": "image" }, "google/gemma-4-26b-a4b-it-maas": { "cost": [ @@ -30357,6 +39198,9 @@ 0.0 ], "limit": 262144, + "max_output": 128000, + "open": true, + "released": "2026-04-02", "status": "alpha" }, "meta/llama-3.3-70b-instruct-maas": { @@ -30366,7 +39210,11 @@ 0.0, 0.0 ], + "knowledge": "2023-12", "limit": 128000, + "max_output": 8192, + "open": true, + "released": "2025-04-29", "status": "deprecated" }, "meta/llama-4-maverick-17b-128e-instruct-maas": { @@ -30376,7 +39224,11 @@ 0.0, 0.0 ], - "limit": 524288 + "knowledge": "2024-08", + "limit": 524288, + "max_output": 8192, + "open": true, + "released": "2025-04-29" }, "meta/llama-4-scout-17b-16e-instruct-maas": { "cost": [ @@ -30385,7 +39237,11 @@ 0.0, 0.0 ], - "limit": 1310720 + "knowledge": "2024-08", + "limit": 1310720, + "max_output": 8192, + "open": true, + "released": "2025-04-05" }, "mistral-medium-3": { "cost": [ @@ -30394,7 +39250,10 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2025-05", + "limit": 131072, + "max_output": 131072, + "released": "2025-05-07" }, "mistral-small-2503": { "cost": [ @@ -30403,7 +39262,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-06", + "limit": 128000, + "max_output": 16384, + "open": true, + "released": "2025-03-17" }, "moonshotai/kimi-k2-thinking-maas": { "cost": [ @@ -30412,7 +39275,11 @@ 0.06, 0.0 ], + "knowledge": "2024-08", "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2025-11-13", "status": "deprecated" }, "openai/gpt-oss-120b-maas": { @@ -30422,7 +39289,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2025-08-05" }, "openai/gpt-oss-20b-maas": { "cost": [ @@ -30432,6 +39303,9 @@ 0.0 ], "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05", "status": "deprecated" }, "qwen/qwen3-235b-a22b-instruct-2507-maas": { @@ -30442,6 +39316,9 @@ 0.0 ], "limit": 262144, + "max_output": 16384, + "open": true, + "released": "2025-08-13", "status": "deprecated" }, "xai/grok-4.1-fast-non-reasoning": { @@ -30452,6 +39329,8 @@ 0.0 ], "limit": 128000, + "max_output": 30000, + "released": "2025-11-19", "status": "deprecated" }, "xai/grok-4.1-fast-reasoning": { @@ -30462,6 +39341,8 @@ 0.0 ], "limit": 128000, + "max_output": 30000, + "released": "2025-11-19", "status": "deprecated" }, "xai/grok-4.20-non-reasoning": { @@ -30472,6 +39353,8 @@ 0.0 ], "limit": 2000000, + "max_output": 30000, + "released": "2026-03-09", "tiers": [ { "cost": [ @@ -30495,6 +39378,8 @@ 0.0 ], "limit": 2000000, + "max_output": 30000, + "released": "2026-03-09", "tiers": [ { "cost": [ @@ -30518,6 +39403,8 @@ 0.0 ], "limit": 200000, + "max_output": 30000, + "released": "2026-04-17", "status": "beta", "tiers": [ { @@ -30541,7 +39428,10 @@ 0.5, 0.0 ], + "knowledge": "2026-02-01", "limit": 524288, + "max_output": 500000, + "released": "2026-08-12", "tiers": [ { "cost": [ @@ -30564,7 +39454,10 @@ 0.5, 0.0 ], + "knowledge": "2026-05", "limit": 524288, + "max_output": 500000, + "released": "2026-09-21", "status": "beta", "tiers": [ { @@ -30588,7 +39481,11 @@ 0.06, 0.0 ], + "knowledge": "2025-04", "limit": 200000, + "max_output": 128000, + "open": true, + "released": "2026-01-06", "status": "deprecated" }, "zai-org/glm-5-maas": { @@ -30599,6 +39496,9 @@ 0.0 ], "limit": 200000, + "max_output": 128000, + "open": true, + "released": "2026-02-12", "status": "deprecated" }, "zai-org/glm-5.2-maas": { @@ -30609,6 +39509,9 @@ 0.0 ], "limit": 1000000, + "max_output": 64000, + "open": true, + "released": "2026-06-13", "status": "beta" } }, @@ -30623,7 +39526,10 @@ 0.25, 12.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-01" }, "claude-fable-5@default": { "cost": [ @@ -30632,7 +39538,10 @@ 1.0, 12.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-09" }, "claude-haiku-4-5@20251001": { "cost": [ @@ -30641,7 +39550,10 @@ 0.1, 1.25 ], - "limit": 200000 + "knowledge": "2025-02-28", + "limit": 200000, + "max_output": 64000, + "released": "2025-10-15" }, "claude-haiku-5-5@default": { "cost": [ @@ -30650,7 +39562,10 @@ 0.01, 0.125 ], + "knowledge": "2026-06", "limit": 1000000, + "max_output": 128000, + "released": "2026-10-07", "tiers": [ { "cost": [ @@ -30673,7 +39588,10 @@ 1.5, 18.75 ], + "knowledge": "2025-03-31", "limit": 200000, + "max_output": 32000, + "released": "2025-08-05", "status": "deprecated" }, "claude-opus-4-5@20251101": { @@ -30683,7 +39601,10 @@ 0.5, 6.25 ], - "limit": 200000 + "knowledge": "2025-05", + "limit": 200000, + "max_output": 64000, + "released": "2025-11-24" }, "claude-opus-4-6@default": { "cost": [ @@ -30692,7 +39613,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2025-05-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-05" }, "claude-opus-4-7@default": { "cost": [ @@ -30701,7 +39625,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-16" }, "claude-opus-4-8@default": { "cost": [ @@ -30710,7 +39637,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-28" }, "claude-opus-4@20250514": { "cost": [ @@ -30719,7 +39649,10 @@ 1.5, 18.75 ], + "knowledge": "2025-03-31", "limit": 200000, + "max_output": 32000, + "released": "2025-05-22", "status": "deprecated" }, "claude-opus-5-5@default": { @@ -30729,7 +39662,10 @@ 0.2, 5.0 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-22" }, "claude-opus-5@default": { "cost": [ @@ -30738,7 +39674,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-05", + "limit": 1000000, + "max_output": 128000, + "released": "2026-07-24" }, "claude-sonnet-4-5@20250929": { "cost": [ @@ -30747,7 +39686,10 @@ 0.3, 3.75 ], + "knowledge": "2025-07-31", "limit": 200000, + "max_output": 64000, + "released": "2025-09-29", "status": "deprecated" }, "claude-sonnet-4-6@default": { @@ -30757,7 +39699,10 @@ 0.3, 3.75 ], - "limit": 1000000 + "knowledge": "2025-08-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-17" }, "claude-sonnet-4@20250514": { "cost": [ @@ -30766,7 +39711,10 @@ 0.3, 3.75 ], + "knowledge": "2025-03-31", "limit": 200000, + "max_output": 64000, + "released": "2025-05-22", "status": "deprecated" }, "claude-sonnet-5-5@default": { @@ -30776,7 +39724,10 @@ 0.1, 2.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-28" }, "claude-sonnet-5@default": { "cost": [ @@ -30785,7 +39736,10 @@ 0.2, 2.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-30" } }, "name": "Vertex (Anthropic)" @@ -30799,7 +39753,11 @@ 0.0456, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-07-31" }, "deepseek-v4.1-flash": { "cost": [ @@ -30808,7 +39766,11 @@ 0.0127776, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-09-10" }, "devstral-2-123b-instruct-2512": { "cost": [ @@ -30817,7 +39779,11 @@ 0.0, 0.0 ], + "knowledge": "2025-12", "limit": 200000, + "max_output": 16384, + "open": true, + "released": "2025-12-09", "status": "deprecated" }, "gemma-3-27b-it": { @@ -30827,7 +39793,11 @@ 0.0, 0.0 ], + "knowledge": "2024-08", "limit": 40000, + "max_output": 8192, + "open": true, + "released": "2025-03-12", "status": "deprecated" }, "gemma4": { @@ -30837,7 +39807,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-04-02" }, "glm-5.1": { "cost": [ @@ -30847,6 +39820,9 @@ 0.0 ], "limit": 200000, + "max_output": 131072, + "open": true, + "released": "2026-04-07", "status": "deprecated" }, "glm-5.2": { @@ -30856,7 +39832,10 @@ 0.4486, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "glm-5.2-caveman": { "cost": [ @@ -30865,7 +39844,10 @@ 0.4486, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "glm-5.2-caveman-lite": { "cost": [ @@ -30874,7 +39856,10 @@ 0.4486, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "glm-5.2-caveman-ultra": { "cost": [ @@ -30883,7 +39868,10 @@ 0.4486, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "glm-5.2-honey": { "cost": [ @@ -30892,7 +39880,10 @@ 0.4486, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "glm-5.2-honey-lite": { "cost": [ @@ -30901,7 +39892,10 @@ 0.4486, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "glm-5.2-honey-ultra": { "cost": [ @@ -30910,7 +39904,10 @@ 0.4486, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "glm-5.2-ponytail": { "cost": [ @@ -30919,7 +39916,10 @@ 0.4486, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "glm-5.2-ponytail-lite": { "cost": [ @@ -30928,7 +39928,10 @@ 0.4486, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "glm-5.2-ponytail-ultra": { "cost": [ @@ -30937,7 +39940,10 @@ 0.4486, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "glm-5.3": { "cost": [ @@ -30946,7 +39952,10 @@ 0.319385, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "glm-5.3-flash": { "cost": [ @@ -30955,7 +39964,10 @@ 0.0255508, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-26" }, "gpt-oss-120b": { "cost": [ @@ -30964,7 +39976,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "green-l": { "cost": [ @@ -30973,7 +39989,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2025-03", + "limit": 128000, + "max_output": 32768, + "open": true, + "released": "2025-06-20" }, "green-l-raw": { "cost": [ @@ -30982,7 +40002,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2025-03", + "limit": 128000, + "max_output": 32768, + "open": true, + "released": "2025-06-20" }, "green-r": { "cost": [ @@ -30991,7 +40015,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "green-r-raw": { "cost": [ @@ -31000,7 +40028,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "holo2-30b-a3b": { "cost": [ @@ -31010,6 +40042,9 @@ 0.0 ], "limit": 22016, + "max_output": 16384, + "open": true, + "released": "2025-11", "status": "deprecated" }, "kimi-k2.6": { @@ -31019,7 +40054,11 @@ 0.2508, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-20" }, "kimi-k2.6-fast": { "cost": [ @@ -31028,7 +40067,11 @@ 0.0, 0.0 ], + "knowledge": "2025-01", "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-20", "status": "deprecated" }, "kimi-k2.7-code": { @@ -31038,7 +40081,11 @@ 0.222057, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-06-12" }, "kimi-k3": { "cost": [ @@ -31047,7 +40094,10 @@ 0.9405, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-16" }, "llama-3.3-70b-instruct": { "cost": [ @@ -31056,7 +40106,11 @@ 0.0, 0.0 ], - "limit": 100000 + "knowledge": "2023-12", + "limit": 100000, + "max_output": 16384, + "open": true, + "released": "2024-12-06" }, "minimax-m2.5": { "cost": [ @@ -31065,7 +40119,10 @@ 0.123365, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-02-12" }, "mistral-medium-3.5-128b": { "cost": [ @@ -31074,7 +40131,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 16384, + "open": true, + "released": "2026-04-29" }, "mistral-small-3.2-24b-instruct-2506": { "cost": [ @@ -31083,7 +40143,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2025-03", + "limit": 128000, + "max_output": 32768, + "open": true, + "released": "2025-06-20" }, "pixtral-12b-2409": { "cost": [ @@ -31092,7 +40156,11 @@ 0.0, 0.0 ], + "knowledge": "2024-09", "limit": 128000, + "max_output": 4096, + "open": true, + "released": "2024-09-11", "status": "deprecated" }, "qwen3-235b-a22b-instruct-2507": { @@ -31102,7 +40170,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-04", + "limit": 262144, + "max_output": 16384, + "open": true, + "released": "2025-07-21" }, "qwen3-coder-30b-a3b-instruct": { "cost": [ @@ -31111,7 +40183,11 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 128000, + "max_output": 32768, + "open": true, + "released": "2025-07-31", "status": "deprecated" }, "qwen3.5-397b-a17b": { @@ -31121,7 +40197,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 16384, + "open": true, + "released": "2026-02-15" }, "qwen3.6-35b-a3b": { "cost": [ @@ -31130,7 +40209,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-04-17" }, "voxtral-small-24b-2507": { "cost": [ @@ -31139,7 +40221,11 @@ 0.0, 0.0 ], + "knowledge": "2025-07", "limit": 32768, + "max_output": 16384, + "open": true, + "released": "2025-07-15", "status": "deprecated" } }, @@ -31154,7 +40240,10 @@ 0.0, 0.0 ], - "limit": 4096 + "limit": 4096, + "max_output": 4096, + "open": true, + "released": "2025-01-23" }, "llama-3.1-8b-instant": { "cost": [ @@ -31163,7 +40252,11 @@ 0.0, 0.0 ], + "knowledge": "2023-12", "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2024-07-23", "status": "deprecated" }, "llama-3.3-70b-versatile": { @@ -31173,7 +40266,11 @@ 0.0, 0.0 ], + "knowledge": "2023-12", "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2024-12-06", "status": "deprecated" }, "meta-llama/llama-prompt-guard-2-22m": { @@ -31184,6 +40281,9 @@ 0.0 ], "limit": 512, + "max_output": 512, + "open": true, + "released": "2025-04-29", "status": "beta" }, "meta-llama/llama-prompt-guard-2-86m": { @@ -31194,6 +40294,9 @@ 0.0 ], "limit": 512, + "max_output": 512, + "open": true, + "released": "2025-04-29", "status": "beta" }, "openai/gpt-oss-120b": { @@ -31203,7 +40306,11 @@ 0.075, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 65536, + "open": true, + "released": "2025-08-05" }, "openai/gpt-oss-20b": { "cost": [ @@ -31212,7 +40319,11 @@ 0.0375, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 65536, + "open": true, + "released": "2025-08-05" }, "openai/gpt-oss-safeguard-20b": { "cost": [ @@ -31222,6 +40333,9 @@ 0.0 ], "limit": 131072, + "max_output": 65536, + "open": true, + "released": "2025-10-29", "status": "beta" }, "qwen/qwen3.6-27b": { @@ -31232,6 +40346,9 @@ 0.0 ], "limit": 131072, + "max_output": 16384, + "open": true, + "released": "2026-04-22", "status": "deprecated" }, "qwen/qwen3.8-27b": { @@ -31242,6 +40359,9 @@ 0.0 ], "limit": 131072, + "max_output": 16384, + "open": true, + "released": "2026-08-14", "status": "beta" } }, @@ -31256,7 +40376,10 @@ 2.5, 0.0 ], - "limit": 128000 + "knowledge": "2024-08", + "limit": 128000, + "max_output": 16384, + "released": "2024-08-14" }, "claude-3-haiku-20240307": { "cost": [ @@ -31265,7 +40388,10 @@ 0.03, 0.3 ], - "limit": 200000 + "knowledge": "2024-03", + "limit": 200000, + "max_output": 4096, + "released": "2024-03-13" }, "claude-3.5-haiku": { "cost": [ @@ -31274,7 +40400,10 @@ 0.08, 1.0 ], - "limit": 200000 + "knowledge": "2024-10", + "limit": 200000, + "max_output": 8192, + "released": "2024-10-22" }, "claude-3.5-sonnet-v2": { "cost": [ @@ -31283,7 +40412,10 @@ 0.3, 3.75 ], - "limit": 200000 + "knowledge": "2024-10", + "limit": 200000, + "max_output": 8192, + "released": "2024-10-22" }, "claude-3.7-sonnet": { "cost": [ @@ -31292,7 +40424,10 @@ 0.3, 3.75 ], - "limit": 200000 + "knowledge": "2025-02", + "limit": 200000, + "max_output": 64000, + "released": "2025-02-19" }, "claude-4.5-haiku": { "cost": [ @@ -31301,7 +40436,10 @@ 0.1, 1.25 ], - "limit": 200000 + "knowledge": "2025-10", + "limit": 200000, + "max_output": 8192, + "released": "2025-10-15" }, "claude-4.5-opus": { "cost": [ @@ -31310,7 +40448,10 @@ 0.5, 6.25 ], - "limit": 200000 + "knowledge": "2025-11", + "limit": 200000, + "max_output": 64000, + "released": "2025-11-24" }, "claude-4.5-sonnet": { "cost": [ @@ -31319,7 +40460,10 @@ 0.3, 3.75 ], - "limit": 200000 + "knowledge": "2025-09", + "limit": 200000, + "max_output": 64000, + "released": "2025-09-29" }, "claude-haiku-4-5-20251001": { "cost": [ @@ -31328,7 +40472,10 @@ 0.1, 1.25 ], - "limit": 200000 + "knowledge": "2025-10", + "limit": 200000, + "max_output": 8192, + "released": "2025-10-15" }, "claude-opus-4": { "cost": [ @@ -31337,7 +40484,10 @@ 1.5, 18.75 ], - "limit": 200000 + "knowledge": "2025-05", + "limit": 200000, + "max_output": 32000, + "released": "2025-05-22" }, "claude-opus-4-1": { "cost": [ @@ -31346,7 +40496,10 @@ 1.5, 18.75 ], - "limit": 200000 + "knowledge": "2025-08", + "limit": 200000, + "max_output": 32000, + "released": "2025-08-05" }, "claude-opus-4-1-20250805": { "cost": [ @@ -31355,7 +40508,10 @@ 1.5, 18.75 ], - "limit": 200000 + "knowledge": "2025-08", + "limit": 200000, + "max_output": 32000, + "released": "2025-08-05" }, "claude-sonnet-4": { "cost": [ @@ -31364,7 +40520,10 @@ 0.3, 3.75 ], - "limit": 200000 + "knowledge": "2025-05", + "limit": 200000, + "max_output": 64000, + "released": "2025-05-22" }, "claude-sonnet-4-5-20250929": { "cost": [ @@ -31373,7 +40532,10 @@ 0.3, 3.75 ], - "limit": 200000 + "knowledge": "2025-09", + "limit": 200000, + "max_output": 64000, + "released": "2025-09-29" }, "deepseek-r1-distill-llama-70b": { "cost": [ @@ -31382,7 +40544,10 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2025-01", + "limit": 128000, + "max_output": 4096, + "released": "2025-01-20" }, "deepseek-reasoner": { "cost": [ @@ -31391,7 +40556,11 @@ 0.07, 0.0 ], - "limit": 128000 + "knowledge": "2025-01", + "limit": 128000, + "max_output": 64000, + "open": true, + "released": "2025-12-01" }, "deepseek-tng-r1t2-chimera": { "cost": [ @@ -31400,7 +40569,10 @@ 0.0, 0.0 ], - "limit": 130000 + "knowledge": "2025-07", + "limit": 130000, + "max_output": 163840, + "released": "2025-07-02" }, "deepseek-v3": { "cost": [ @@ -31409,7 +40581,10 @@ 0.07, 0.0 ], - "limit": 128000 + "knowledge": "2024-12", + "limit": 128000, + "max_output": 8192, + "released": "2024-12-26" }, "deepseek-v3.1-terminus": { "cost": [ @@ -31418,7 +40593,10 @@ 0.216, 0.0 ], - "limit": 128000 + "knowledge": "2025-09", + "limit": 128000, + "max_output": 16384, + "released": "2025-09-22" }, "deepseek-v3.2": { "cost": [ @@ -31427,7 +40605,11 @@ 0.0, 0.0 ], - "limit": 163840 + "knowledge": "2025-09", + "limit": 163840, + "max_output": 65536, + "open": true, + "released": "2025-12-01" }, "ernie-4.5-21b-a3b-thinking": { "cost": [ @@ -31436,7 +40618,10 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2025-03", + "limit": 128000, + "max_output": 8000, + "released": "2025-03-16" }, "gemini-2.5-flash": { "cost": [ @@ -31445,7 +40630,10 @@ 0.075, 0.3 ], - "limit": 1048576 + "knowledge": "2025-06", + "limit": 1048576, + "max_output": 65535, + "released": "2025-06-17" }, "gemini-2.5-flash-lite": { "cost": [ @@ -31454,7 +40642,10 @@ 0.025, 0.1 ], - "limit": 1048576 + "knowledge": "2025-07", + "limit": 1048576, + "max_output": 65535, + "released": "2025-06-17" }, "gemini-2.5-pro": { "cost": [ @@ -31463,7 +40654,10 @@ 0.3125, 1.25 ], - "limit": 1048576 + "knowledge": "2025-06", + "limit": 1048576, + "max_output": 65536, + "released": "2025-06-17" }, "gemini-3-pro-preview": { "cost": [ @@ -31472,7 +40666,10 @@ 0.2, 0.0 ], - "limit": 1048576 + "knowledge": "2025-11", + "limit": 1048576, + "max_output": 65536, + "released": "2025-11-18" }, "gemma-3-12b-it": { "cost": [ @@ -31481,7 +40678,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-12", + "limit": 131072, + "max_output": 8192, + "open": true, + "released": "2025-03-12" }, "gemma2-9b-it": { "cost": [ @@ -31490,7 +40691,10 @@ 0.0, 0.0 ], - "limit": 8192 + "knowledge": "2024-06", + "limit": 8192, + "max_output": 8192, + "released": "2024-06-25" }, "glm-4.6": { "cost": [ @@ -31499,7 +40703,11 @@ 0.0, 0.0 ], - "limit": 204800 + "knowledge": "2024-07", + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-09-30" }, "gpt-4.1": { "cost": [ @@ -31508,7 +40716,10 @@ 0.5, 0.0 ], - "limit": 1047576 + "knowledge": "2025-04", + "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14" }, "gpt-4.1-mini": { "cost": [ @@ -31517,7 +40728,10 @@ 0.1, 0.0 ], - "limit": 1047576 + "knowledge": "2025-04", + "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14" }, "gpt-4.1-mini-2025-04-14": { "cost": [ @@ -31526,7 +40740,10 @@ 0.1, 0.0 ], - "limit": 1047576 + "knowledge": "2025-04", + "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14" }, "gpt-4.1-nano": { "cost": [ @@ -31535,7 +40752,10 @@ 0.025, 0.0 ], - "limit": 1047576 + "knowledge": "2025-04", + "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14" }, "gpt-4o": { "cost": [ @@ -31544,7 +40764,10 @@ 1.25, 0.0 ], - "limit": 128000 + "knowledge": "2024-05", + "limit": 128000, + "max_output": 16384, + "released": "2024-05-13" }, "gpt-4o-mini": { "cost": [ @@ -31553,7 +40776,10 @@ 0.075, 0.0 ], - "limit": 128000 + "knowledge": "2024-07", + "limit": 128000, + "max_output": 16384, + "released": "2024-07-18" }, "gpt-5": { "cost": [ @@ -31562,7 +40788,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2025-01", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "gpt-5-chat-latest": { "cost": [ @@ -31571,7 +40800,10 @@ 0.125, 0.0 ], - "limit": 128000 + "knowledge": "2024-09", + "limit": 128000, + "max_output": 16384, + "released": "2025-08-07" }, "gpt-5-codex": { "cost": [ @@ -31580,7 +40812,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2025-01", + "limit": 400000, + "max_output": 128000, + "released": "2025-09-15" }, "gpt-5-mini": { "cost": [ @@ -31589,7 +40824,10 @@ 0.025, 0.0 ], - "limit": 400000 + "knowledge": "2025-01", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "gpt-5-nano": { "cost": [ @@ -31598,7 +40836,10 @@ 0.005, 0.0 ], - "limit": 400000 + "knowledge": "2025-01", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "gpt-5-pro": { "cost": [ @@ -31607,7 +40848,10 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2025-01", + "limit": 128000, + "max_output": 32768, + "released": "2025-10-06" }, "gpt-5.1": { "cost": [ @@ -31616,7 +40860,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2025-01", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "gpt-5.1-chat-latest": { "cost": [ @@ -31625,7 +40872,10 @@ 0.125, 0.0 ], - "limit": 128000 + "knowledge": "2025-01", + "limit": 128000, + "max_output": 16384, + "released": "2025-11-13" }, "gpt-5.1-codex": { "cost": [ @@ -31634,7 +40884,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2025-01", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "gpt-5.1-codex-mini": { "cost": [ @@ -31643,7 +40896,10 @@ 0.025, 0.0 ], - "limit": 400000 + "knowledge": "2025-01", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "gpt-oss-120b": { "cost": [ @@ -31652,7 +40908,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2025-08-05" }, "gpt-oss-20b": { "cost": [ @@ -31661,7 +40921,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2025-08-05" }, "grok-3": { "cost": [ @@ -31670,7 +40934,10 @@ 0.75, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 131072, + "released": "2024-06-01" }, "grok-3-mini": { "cost": [ @@ -31679,7 +40946,10 @@ 0.075, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 131072, + "released": "2024-06-01" }, "grok-4": { "cost": [ @@ -31688,7 +40958,10 @@ 0.75, 0.0 ], - "limit": 256000 + "knowledge": "2024-07", + "limit": 256000, + "max_output": 256000, + "released": "2024-07-09" }, "grok-4-1-fast-non-reasoning": { "cost": [ @@ -31697,7 +40970,10 @@ 0.05, 0.0 ], - "limit": 2000000 + "knowledge": "2025-11", + "limit": 2000000, + "max_output": 30000, + "released": "2025-11-19" }, "grok-4-1-fast-reasoning": { "cost": [ @@ -31706,7 +40982,10 @@ 0.05, 0.0 ], - "limit": 2000000 + "knowledge": "2025-11", + "limit": 2000000, + "max_output": 2000000, + "released": "2025-11-19" }, "grok-4-fast-non-reasoning": { "cost": [ @@ -31715,7 +40994,10 @@ 0.05, 0.0 ], - "limit": 2000000 + "knowledge": "2025-09", + "limit": 2000000, + "max_output": 2000000, + "released": "2025-12-18" }, "grok-4-fast-reasoning": { "cost": [ @@ -31724,7 +41006,10 @@ 0.05, 0.0 ], - "limit": 2000000 + "knowledge": "2025-09", + "limit": 2000000, + "max_output": 2000000, + "released": "2025-12-18" }, "grok-code-fast-1": { "cost": [ @@ -31733,7 +41018,10 @@ 0.02, 0.0 ], - "limit": 256000 + "knowledge": "2024-08", + "limit": 256000, + "max_output": 10000, + "released": "2025-09-02" }, "hermes-2-pro-llama-3-8b": { "cost": [ @@ -31742,7 +41030,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-05", + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2024-04-30" }, "kimi-k2-0711": { "cost": [ @@ -31751,7 +41043,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2025-01", + "limit": 131072, + "max_output": 16384, + "open": true, + "released": "2025-07-11" }, "kimi-k2-0905": { "cost": [ @@ -31760,7 +41056,11 @@ 0.4, 0.0 ], - "limit": 262144 + "knowledge": "2025-09", + "limit": 262144, + "max_output": 16384, + "open": true, + "released": "2025-09-05" }, "kimi-k2-thinking": { "cost": [ @@ -31769,7 +41069,11 @@ 0.0, 0.0 ], - "limit": 256000 + "knowledge": "2025-11", + "limit": 256000, + "max_output": 262144, + "open": true, + "released": "2025-11-06" }, "llama-3.1-8b-instant": { "cost": [ @@ -31778,7 +41082,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-07", + "limit": 131072, + "max_output": 32678, + "open": true, + "released": "2024-07-23" }, "llama-3.1-8b-instruct": { "cost": [ @@ -31787,7 +41095,11 @@ 0.0, 0.0 ], - "limit": 16384 + "knowledge": "2024-07", + "limit": 16384, + "max_output": 16384, + "open": true, + "released": "2024-07-23" }, "llama-3.1-8b-instruct-turbo": { "cost": [ @@ -31796,7 +41108,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-07", + "limit": 128000, + "max_output": 128000, + "open": true, + "released": "2024-07-23" }, "llama-3.3-70b-instruct": { "cost": [ @@ -31805,7 +41121,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-12", + "limit": 128000, + "max_output": 16400, + "open": true, + "released": "2024-12-06" }, "llama-3.3-70b-versatile": { "cost": [ @@ -31814,7 +41134,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-12", + "limit": 131072, + "max_output": 32678, + "open": true, + "released": "2024-12-06" }, "llama-4-maverick": { "cost": [ @@ -31823,7 +41147,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2025-01", + "limit": 131072, + "max_output": 8192, + "open": true, + "released": "2025-04-05" }, "llama-4-scout": { "cost": [ @@ -31832,7 +41160,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2025-01", + "limit": 131072, + "max_output": 8192, + "open": true, + "released": "2025-04-05" }, "llama-guard-4": { "cost": [ @@ -31841,7 +41173,10 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2025-01", + "limit": 131072, + "max_output": 1024, + "released": "2025-01-01" }, "llama-prompt-guard-2-22m": { "cost": [ @@ -31850,7 +41185,11 @@ 0.0, 0.0 ], - "limit": 512 + "knowledge": "2024-10", + "limit": 512, + "max_output": 2, + "open": true, + "released": "2025-04-29" }, "llama-prompt-guard-2-86m": { "cost": [ @@ -31859,7 +41198,11 @@ 0.0, 0.0 ], - "limit": 512 + "knowledge": "2024-10", + "limit": 512, + "max_output": 2, + "open": true, + "released": "2025-04-29" }, "mistral-large-2411": { "cost": [ @@ -31868,7 +41211,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-07", + "limit": 128000, + "max_output": 32768, + "open": true, + "released": "2024-11-18" }, "mistral-nemo": { "cost": [ @@ -31877,7 +41224,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-07", + "limit": 128000, + "max_output": 16400, + "open": true, + "released": "2024-07-18" }, "mistral-small": { "cost": [ @@ -31886,7 +41237,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2025-03", + "limit": 128000, + "max_output": 16384, + "open": true, + "released": "2025-06-20" }, "o1": { "cost": [ @@ -31895,7 +41250,10 @@ 7.5, 0.0 ], - "limit": 200000 + "knowledge": "2025-01", + "limit": 200000, + "max_output": 100000, + "released": "2024-12-05" }, "o1-mini": { "cost": [ @@ -31904,7 +41262,10 @@ 0.55, 0.0 ], - "limit": 128000 + "knowledge": "2025-01", + "limit": 128000, + "max_output": 65536, + "released": "2025-01-01" }, "o3": { "cost": [ @@ -31913,7 +41274,10 @@ 0.5, 0.0 ], - "limit": 200000 + "knowledge": "2024-06", + "limit": 200000, + "max_output": 100000, + "released": "2025-04-16" }, "o3-mini": { "cost": [ @@ -31922,7 +41286,10 @@ 0.55, 0.0 ], - "limit": 200000 + "knowledge": "2023-10", + "limit": 200000, + "max_output": 100000, + "released": "2024-12-20" }, "o3-pro": { "cost": [ @@ -31931,7 +41298,10 @@ 0.0, 0.0 ], - "limit": 200000 + "knowledge": "2024-06", + "limit": 200000, + "max_output": 100000, + "released": "2025-06-10" }, "o4-mini": { "cost": [ @@ -31940,7 +41310,10 @@ 0.275, 0.0 ], - "limit": 200000 + "knowledge": "2024-06", + "limit": 200000, + "max_output": 100000, + "released": "2025-04-16" }, "qwen2.5-coder-7b-fast": { "cost": [ @@ -31949,7 +41322,10 @@ 0.0, 0.0 ], - "limit": 32000 + "knowledge": "2024-09", + "limit": 32000, + "max_output": 8192, + "released": "2024-09-15" }, "qwen3-235b-a22b-thinking": { "cost": [ @@ -31958,7 +41334,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-07", + "limit": 262144, + "max_output": 81920, + "open": true, + "released": "2025-07-25" }, "qwen3-30b-a3b": { "cost": [ @@ -31967,7 +41347,11 @@ 0.0, 0.0 ], - "limit": 41000 + "knowledge": "2025-06", + "limit": 41000, + "max_output": 41000, + "open": true, + "released": "2025-04-28" }, "qwen3-32b": { "cost": [ @@ -31976,7 +41360,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2025-04", + "limit": 131072, + "max_output": 40960, + "open": true, + "released": "2025-04-28" }, "qwen3-coder": { "cost": [ @@ -31985,7 +41373,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-07", + "limit": 262144, + "max_output": 16384, + "open": true, + "released": "2025-07-22" }, "qwen3-coder-30b-a3b-instruct": { "cost": [ @@ -31994,7 +41386,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-07", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2025-07-31" }, "qwen3-next-80b-a3b-instruct": { "cost": [ @@ -32003,7 +41399,11 @@ 0.0, 0.0 ], - "limit": 262000 + "knowledge": "2025-01", + "limit": 262000, + "max_output": 16384, + "open": true, + "released": "2025-09" }, "qwen3-vl-235b-a22b-instruct": { "cost": [ @@ -32012,7 +41412,11 @@ 0.0, 0.0 ], - "limit": 256000 + "knowledge": "2025-09", + "limit": 256000, + "max_output": 16384, + "open": true, + "released": "2025-09-23" }, "sonar": { "cost": [ @@ -32021,7 +41425,10 @@ 0.0, 0.0 ], - "limit": 127000 + "knowledge": "2025-01", + "limit": 127000, + "max_output": 4096, + "released": "2024-01-01" }, "sonar-deep-research": { "cost": [ @@ -32030,7 +41437,10 @@ 0.0, 0.0 ], - "limit": 127000 + "knowledge": "2025-01", + "limit": 127000, + "max_output": 4096, + "released": "2025-02-01" }, "sonar-pro": { "cost": [ @@ -32039,7 +41449,10 @@ 0.0, 0.0 ], - "limit": 200000 + "knowledge": "2025-01", + "limit": 200000, + "max_output": 4096, + "released": "2024-01-01" }, "sonar-reasoning": { "cost": [ @@ -32048,7 +41461,10 @@ 0.0, 0.0 ], - "limit": 127000 + "knowledge": "2025-01", + "limit": 127000, + "max_output": 4096, + "released": "2025-01-27" }, "sonar-reasoning-pro": { "cost": [ @@ -32057,7 +41473,10 @@ 0.0, 0.0 ], - "limit": 127000 + "knowledge": "2025-01", + "limit": 127000, + "max_output": 4096, + "released": "2024-01-01" } }, "name": "Helicone" @@ -32072,6 +41491,9 @@ 0.0 ], "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-17", "status": "beta" }, "Qwen3.8-27B": { @@ -32082,6 +41504,9 @@ 0.0 ], "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-08-14", "status": "beta" } }, @@ -32096,7 +41521,10 @@ 0.5, 0.0 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-16" }, "deepseek/deepseek-v4-flash": { "cost": [ @@ -32105,7 +41533,11 @@ 0.028, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 128000, + "open": true, + "released": "2026-04-24" }, "deepseek/deepseek-v4-pro": { "cost": [ @@ -32114,7 +41546,11 @@ 0.145, 0.0 ], - "limit": 1002000 + "knowledge": "2025-05", + "limit": 1002000, + "max_output": 128000, + "open": true, + "released": "2026-04-24" }, "minimax/minimax-m2.5": { "cost": [ @@ -32123,7 +41559,10 @@ 0.03, 0.0 ], - "limit": 196000 + "limit": 196000, + "max_output": 195000, + "open": true, + "released": "2026-02-12" }, "moonshotai/kimi-k2.5": { "cost": [ @@ -32132,7 +41571,11 @@ 0.1, 0.0 ], - "limit": 256000 + "knowledge": "2025-01", + "limit": 256000, + "max_output": 256000, + "open": true, + "released": "2026-01-27" }, "moonshotai/kimi-k2.7-code": { "cost": [ @@ -32141,7 +41584,11 @@ 0.19, 0.0 ], - "limit": 256000 + "knowledge": "2025-01", + "limit": 256000, + "max_output": 256000, + "open": true, + "released": "2026-06-12" }, "openai/gpt-5.5": { "cost": [ @@ -32150,7 +41597,10 @@ 0.5, 0.0 ], + "knowledge": "2025-12-01", "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23", "tiers": [ { "cost": [ @@ -32173,7 +41623,10 @@ 0.133, 0.0 ], - "limit": 202000 + "limit": 202000, + "max_output": 202000, + "open": true, + "released": "2026-04-07" }, "zai-org/glm-5.2": { "cost": [ @@ -32182,7 +41635,10 @@ 0.26, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-06-13" } }, "name": "HPC-AI" @@ -32196,7 +41652,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 80000, + "open": true, + "released": "2025-06-17" }, "MiniMaxAI/MiniMax-M2": { "cost": [ @@ -32205,7 +41664,10 @@ 0.0, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-10-27" }, "MiniMaxAI/MiniMax-M2.1": { "cost": [ @@ -32214,7 +41676,11 @@ 0.0, 0.0 ], - "limit": 204800 + "knowledge": "2025-10", + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-12-23" }, "MiniMaxAI/MiniMax-M2.5": { "cost": [ @@ -32223,7 +41689,10 @@ 0.03, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-02-12" }, "MiniMaxAI/MiniMax-M2.7": { "cost": [ @@ -32232,7 +41701,10 @@ 0.06, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-03-18" }, "MiniMaxAI/MiniMax-M3": { "cost": [ @@ -32241,7 +41713,21 @@ 0.0, 0.0 ], - "limit": 524288 + "limit": 524288, + "max_output": 512000, + "open": true, + "released": "2026-06-01" + }, + "MiniMaxAI/MiniMax-M3.1-Flash": { + "cost": [ + 0.15, + 0.6, + 0.0, + 0.0 + ], + "limit": 1000000, + "max_output": 512000, + "released": "2026-10-19" }, "Qwen/Qwen2.5-Coder-32B-Instruct": { "cost": [ @@ -32250,7 +41736,10 @@ 0.0, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 8192, + "open": true, + "released": "2024-11-12" }, "Qwen/Qwen3-235B-A22B": { "cost": [ @@ -32259,7 +41748,11 @@ 0.0, 0.0 ], - "limit": 40960 + "knowledge": "2025-04", + "limit": 40960, + "max_output": 16384, + "open": true, + "released": "2025-04-28" }, "Qwen/Qwen3-235B-A22B-Instruct-2507": { "cost": [ @@ -32268,7 +41761,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 16384, + "open": true, + "released": "2025-07-21" }, "Qwen/Qwen3-235B-A22B-Thinking-2507": { "cost": [ @@ -32277,7 +41773,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-04", + "limit": 262144, + "max_output": 81920, + "open": true, + "released": "2025-07-25" }, "Qwen/Qwen3-30B-A3B": { "cost": [ @@ -32286,7 +41786,10 @@ 0.0, 0.0 ], - "limit": 40960 + "limit": 40960, + "max_output": 16384, + "open": true, + "released": "2025-04-28" }, "Qwen/Qwen3-32B": { "cost": [ @@ -32295,7 +41798,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2025-04", + "limit": 131072, + "max_output": 16384, + "open": true, + "released": "2025-04-28" }, "Qwen/Qwen3-8B": { "cost": [ @@ -32304,7 +41811,10 @@ 0.0, 0.0 ], - "limit": 40960 + "limit": 40960, + "max_output": 32768, + "open": true, + "released": "2025-04-29" }, "Qwen/Qwen3-Coder-30B-A3B-Instruct": { "cost": [ @@ -32313,7 +41823,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-04", + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2025-07-31" }, "Qwen/Qwen3-Coder-480B-A35B-Instruct": { "cost": [ @@ -32322,7 +41836,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-04", + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2025-07-22" }, "Qwen/Qwen3-Coder-Next": { "cost": [ @@ -32331,7 +41849,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-09", + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-03" }, "Qwen/Qwen3-Embedding-4B": { "cost": [ @@ -32340,7 +41862,11 @@ 0.0, 0.0 ], - "limit": 32768 + "knowledge": "2024-12", + "limit": 32768, + "open": true, + "released": "2025-06-05", + "type": "embedding" }, "Qwen/Qwen3-Embedding-8B": { "cost": [ @@ -32349,7 +41875,11 @@ 0.0, 0.0 ], - "limit": 32768 + "knowledge": "2024-12", + "limit": 32768, + "open": true, + "released": "2025-06-05", + "type": "embedding" }, "Qwen/Qwen3-Next-80B-A3B-Instruct": { "cost": [ @@ -32358,7 +41888,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-04", + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2025-09" }, "Qwen/Qwen3-VL-235B-A22B-Instruct": { "cost": [ @@ -32367,7 +41901,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2025-03-31", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-09-23" }, "Qwen/Qwen3-VL-235B-A22B-Thinking": { "cost": [ @@ -32376,7 +41914,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2025-03-31", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-09-23" }, "Qwen/Qwen3-VL-30B-A3B-Instruct": { "cost": [ @@ -32385,7 +41927,10 @@ 0.0, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-10-04" }, "Qwen/Qwen3.5-122B-A10B": { "cost": [ @@ -32394,7 +41939,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-23" }, "Qwen/Qwen3.5-27B": { "cost": [ @@ -32403,7 +41951,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-23" }, "Qwen/Qwen3.5-35B-A3B": { "cost": [ @@ -32412,7 +41963,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-23" }, "Qwen/Qwen3.5-397B-A17B": { "cost": [ @@ -32421,7 +41975,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-04", + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-02-15" }, "Qwen/Qwen3.5-9B": { "cost": [ @@ -32430,7 +41988,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-23" }, "Qwen/Qwen3.6-27B": { "cost": [ @@ -32439,7 +42000,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-04-22" }, "Qwen/Qwen3.6-35B-A3B": { "cost": [ @@ -32448,7 +42012,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-04-17" }, "Qwen/Qwen3.8-2.4T-A95B": { "cost": [ @@ -32457,7 +42024,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 131072, + "open": true, + "released": "2026-08-12" }, "Qwen/Qwen3.8-27B": { "cost": [ @@ -32466,7 +42036,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-08-14" }, "XiaomiMiMo/MiMo-V2.5": { "cost": [ @@ -32475,7 +42048,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2024-12", + "limit": 262144, + "max_output": 131072, + "open": true, + "released": "2026-04-22" }, "XiaomiMiMo/MiMo-V2.5-Pro": { "cost": [ @@ -32484,7 +42061,11 @@ 0.0, 0.0 ], - "limit": 1048576 + "knowledge": "2024-12", + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-04-22" }, "deepseek-ai/DeepSeek-R1": { "cost": [ @@ -32493,7 +42074,11 @@ 0.0, 0.0 ], - "limit": 64000 + "knowledge": "2024-07", + "limit": 64000, + "max_output": 32768, + "open": true, + "released": "2025-01-20" }, "deepseek-ai/DeepSeek-R1-0528": { "cost": [ @@ -32502,7 +42087,11 @@ 0.0, 0.0 ], - "limit": 163840 + "knowledge": "2025-05", + "limit": 163840, + "max_output": 32768, + "open": true, + "released": "2025-05-28" }, "deepseek-ai/DeepSeek-V3": { "cost": [ @@ -32511,7 +42100,10 @@ 0.0, 0.0 ], - "limit": 64000 + "limit": 64000, + "max_output": 8192, + "open": true, + "released": "2024-12-26" }, "deepseek-ai/DeepSeek-V3-0324": { "cost": [ @@ -32520,7 +42112,10 @@ 0.0, 0.0 ], - "limit": 163840 + "limit": 163840, + "max_output": 163840, + "open": true, + "released": "2025-03-24" }, "deepseek-ai/DeepSeek-V3.1": { "cost": [ @@ -32529,7 +42124,10 @@ 0.0, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 8192, + "open": true, + "released": "2025-08-21" }, "deepseek-ai/DeepSeek-V3.2": { "cost": [ @@ -32538,7 +42136,11 @@ 0.0, 0.0 ], - "limit": 163840 + "knowledge": "2024-07", + "limit": 163840, + "max_output": 65536, + "open": true, + "released": "2025-12-01" }, "deepseek-ai/DeepSeek-V4-Flash": { "cost": [ @@ -32547,7 +42149,11 @@ 0.0, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "deepseek-ai/DeepSeek-V4-Flash-0731": { "cost": [ @@ -32556,7 +42162,11 @@ 0.0, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-07-31" }, "deepseek-ai/DeepSeek-V4-Flash-Vision-Exp": { "cost": [ @@ -32565,7 +42175,10 @@ 0.0, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-08-21" }, "deepseek-ai/DeepSeek-V4-Pro": { "cost": [ @@ -32574,7 +42187,11 @@ 0.003625, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 393216, + "open": true, + "released": "2026-04-24" }, "deepseek-ai/DeepSeek-V4-Pro-0813": { "cost": [ @@ -32583,7 +42200,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-08-13" }, "deepseek-ai/DeepSeek-V4.1-Flash": { "cost": [ @@ -32592,7 +42212,11 @@ 0.0, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-09-10" }, "deepseek-ai/DeepSeek-V4.1-Flash-1017": { "cost": [ @@ -32601,7 +42225,11 @@ 0.0, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-10-17" }, "google/gemma-3-12b-it": { "cost": [ @@ -32610,7 +42238,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-08", + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2025-03-12" }, "google/gemma-3-27b-it": { "cost": [ @@ -32619,7 +42251,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-08", + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2025-03-12" }, "google/gemma-3-4b-it": { "cost": [ @@ -32628,7 +42264,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-08", + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2025-03-12" }, "google/gemma-4-26B-A4B-it": { "cost": [ @@ -32637,7 +42277,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-04-02" }, "google/gemma-4-31B-it": { "cost": [ @@ -32646,7 +42289,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-04-02" }, "meta-llama/Llama-3.1-8B-Instruct": { "cost": [ @@ -32655,7 +42302,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2023-12", + "limit": 131072, + "max_output": 4096, + "open": true, + "released": "2024-07-23" }, "meta-llama/Llama-3.3-70B-Instruct": { "cost": [ @@ -32664,7 +42315,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2023-12", + "limit": 131072, + "max_output": 4096, + "open": true, + "released": "2024-12-06" }, "meta-llama/Llama-Guard-4-12B": { "cost": [ @@ -32673,7 +42328,10 @@ 0.0, 0.0 ], - "limit": 163840 + "limit": 163840, + "max_output": 163840, + "open": true, + "released": "2025-04-29" }, "moonshotai/Kimi-K2-Instruct": { "cost": [ @@ -32682,7 +42340,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-10", + "limit": 131072, + "max_output": 16384, + "open": true, + "released": "2025-07-11" }, "moonshotai/Kimi-K2-Instruct-0905": { "cost": [ @@ -32691,7 +42353,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2024-10", + "limit": 262144, + "max_output": 16384, + "open": true, + "released": "2025-09-05" }, "moonshotai/Kimi-K2-Thinking": { "cost": [ @@ -32700,7 +42366,11 @@ 0.15, 0.0 ], - "limit": 262144 + "knowledge": "2024-08", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2025-11-06" }, "moonshotai/Kimi-K2.5": { "cost": [ @@ -32709,7 +42379,11 @@ 0.1, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-01-27" }, "moonshotai/Kimi-K2.6": { "cost": [ @@ -32718,7 +42392,11 @@ 0.16, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-20" }, "moonshotai/Kimi-K2.7-Code": { "cost": [ @@ -32727,7 +42405,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-06-12" }, "moonshotai/Kimi-K3": { "cost": [ @@ -32736,7 +42418,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-07-16" }, "openai/gpt-oss-120b": { "cost": [ @@ -32745,7 +42430,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "openai/gpt-oss-20b": { "cost": [ @@ -32754,7 +42443,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "stepfun-ai/Step-3.5-Flash": { "cost": [ @@ -32763,7 +42456,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 256000, + "open": true, + "released": "2026-01-29" }, "stepfun-ai/Step-3.7-Flash": { "cost": [ @@ -32772,7 +42469,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2026-03-01", + "limit": 262144, + "max_output": 256000, + "open": true, + "released": "2026-05-29" }, "tencent/Hy3": { "cost": [ @@ -32781,7 +42482,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 128000, + "open": true, + "released": "2026-07-06" }, "tencent/Hy4-preview": { "cost": [ @@ -32790,7 +42494,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 64000, + "open": true, + "released": "2026-08-28" }, "thinkingmachines/Inkling": { "cost": [ @@ -32799,7 +42506,10 @@ 0.0, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-07-15" }, "thinkingmachines/Inkling-Small": { "cost": [ @@ -32808,7 +42518,10 @@ 0.0, 0.0 ], - "limit": 524288 + "limit": 524288, + "max_output": 1048576, + "open": true, + "released": "2026-07-30" }, "zai-org/AutoGLM-Phone-9B-Multilingual": { "cost": [ @@ -32817,7 +42530,10 @@ 0.0, 0.0 ], - "limit": 65536 + "limit": 65536, + "max_output": 65536, + "open": true, + "released": "2025-12-10" }, "zai-org/GLM-4.5-Air": { "cost": [ @@ -32826,7 +42542,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2025-04", + "limit": 131072, + "max_output": 98304, + "open": true, + "released": "2025-07-28" }, "zai-org/GLM-4.5V": { "cost": [ @@ -32835,7 +42555,11 @@ 0.0, 0.0 ], - "limit": 65536 + "knowledge": "2025-04", + "limit": 65536, + "max_output": 16384, + "open": true, + "released": "2025-08-11" }, "zai-org/GLM-4.6": { "cost": [ @@ -32844,7 +42568,11 @@ 0.0, 0.0 ], - "limit": 204800 + "knowledge": "2025-04", + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-09-30" }, "zai-org/GLM-4.6V-Flash": { "cost": [ @@ -32853,7 +42581,10 @@ 0.0, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-12-08" }, "zai-org/GLM-4.7": { "cost": [ @@ -32862,7 +42593,11 @@ 0.11, 0.0 ], - "limit": 204800 + "knowledge": "2025-04", + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-12-22" }, "zai-org/GLM-4.7-Flash": { "cost": [ @@ -32871,7 +42606,11 @@ 0.0, 0.0 ], - "limit": 200000 + "knowledge": "2025-04", + "limit": 200000, + "max_output": 128000, + "open": true, + "released": "2026-01-19" }, "zai-org/GLM-5": { "cost": [ @@ -32880,7 +42619,10 @@ 0.2, 0.0 ], - "limit": 202752 + "limit": 202752, + "max_output": 131072, + "open": true, + "released": "2026-02-12" }, "zai-org/GLM-5.1": { "cost": [ @@ -32889,7 +42631,10 @@ 0.2, 0.0 ], - "limit": 202752 + "limit": 202752, + "max_output": 131072, + "open": true, + "released": "2026-04-07" }, "zai-org/GLM-5.2": { "cost": [ @@ -32898,7 +42643,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "zai-org/GLM-5.3": { "cost": [ @@ -32907,7 +42655,10 @@ 0.0, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "zai-org/GLM-5.3-Flash": { "cost": [ @@ -32916,7 +42667,10 @@ 0.0, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-08-26" } }, "name": "Hugging Face" @@ -32930,7 +42684,11 @@ 0.044, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-07-31" }, "deepseek-v4-pro-0813": { "cost": [ @@ -32939,7 +42697,10 @@ 0.047907, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 262144, + "open": true, + "released": "2026-08-13" }, "deepseek-v4.1-flash": { "cost": [ @@ -32948,7 +42709,11 @@ 0.03, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 262144, + "open": true, + "released": "2026-09-10" }, "deepseek-v4.1-flash-1017": { "cost": [ @@ -32957,7 +42722,11 @@ 0.03, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 262144, + "open": true, + "released": "2026-10-17" }, "gemma-4-26b-a4b-it": { "cost": [ @@ -32966,7 +42735,10 @@ 0.049, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 25600, + "open": true, + "released": "2026-04-02" }, "glm-5.2": { "cost": [ @@ -32975,7 +42747,10 @@ 0.152432, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 32768, + "open": true, + "released": "2026-06-13" }, "glm-5.3": { "cost": [ @@ -32984,7 +42759,10 @@ 0.283088, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 128000, + "open": true, + "released": "2026-08-14" }, "glm-5.3-flash": { "cost": [ @@ -32993,7 +42771,10 @@ 0.031575, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-08-26" }, "gpt-oss-120b": { "cost": [ @@ -33002,7 +42783,11 @@ 0.089, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 13107, + "open": true, + "released": "2025-08-05" }, "inkling": { "cost": [ @@ -33011,7 +42796,10 @@ 0.185096, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65536, + "open": true, + "released": "2026-07-15" }, "kimi-k2-thinking": { "cost": [ @@ -33020,7 +42808,11 @@ 0.3, 0.0 ], - "limit": 262144 + "knowledge": "2024-08", + "limit": 262144, + "max_output": 26214, + "open": true, + "released": "2025-11-06" }, "kimi-k2.7-code": { "cost": [ @@ -33029,7 +42821,11 @@ 0.206872, 0.0 ], - "limit": 256000 + "knowledge": "2025-01", + "limit": 256000, + "max_output": 16000, + "open": true, + "released": "2026-06-12" }, "kimi-k3": { "cost": [ @@ -33038,7 +42834,10 @@ 0.32664, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 16000, + "open": true, + "released": "2026-07-16" }, "minimax-m2.7": { "cost": [ @@ -33047,7 +42846,10 @@ 0.242, 0.0 ], - "limit": 262100 + "limit": 262100, + "max_output": 6553, + "open": true, + "released": "2026-03-18" }, "minimax-m3": { "cost": [ @@ -33056,7 +42858,10 @@ 0.064239, 0.0 ], - "limit": 512000 + "limit": 512000, + "max_output": 512000, + "open": true, + "released": "2026-06-01" }, "prism": { "cost": [ @@ -33065,7 +42870,9 @@ 0.32664, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 16000, + "released": "1970-01-01" }, "qwen3.7-flash": { "cost": [ @@ -33074,7 +42881,9 @@ 0.04, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 64000, + "released": "2026-07-15" }, "qwen3.7-max": { "cost": [ @@ -33083,7 +42892,9 @@ 0.5, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 64000, + "released": "2026-05-21" }, "qwen3.7-plus": { "cost": [ @@ -33092,7 +42903,10 @@ 0.24, 0.0 ], - "limit": 1000000 + "knowledge": "2025-04", + "limit": 1000000, + "max_output": 64000, + "released": "2026-06-02" }, "qwen3.8-2.4t-a95b": { "cost": [ @@ -33101,7 +42915,10 @@ 0.25, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 128000, + "open": true, + "released": "2026-08-12" }, "qwen3.8-27b": { "cost": [ @@ -33110,7 +42927,10 @@ 0.1, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 128000, + "open": true, + "released": "2026-08-14" }, "qwen3.8-flash": { "cost": [ @@ -33119,7 +42939,9 @@ 0.016, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 128000, + "released": "2026-08-26" }, "qwen3.8-max": { "cost": [ @@ -33128,7 +42950,9 @@ 0.25, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 65536, + "released": "2026-07-19" } }, "name": "Charm Hyper" @@ -33142,7 +42966,10 @@ 1.0, 12.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-09" }, "anthropic/claude-haiku-4-5": { "cost": [ @@ -33151,7 +42978,10 @@ 0.1, 1.25 ], - "limit": 200000 + "knowledge": "2025-02-28", + "limit": 200000, + "max_output": 64000, + "released": "2025-10-15" }, "anthropic/claude-opus-4-5": { "cost": [ @@ -33160,7 +42990,10 @@ 0.5, 6.25 ], - "limit": 200000 + "knowledge": "2025-05", + "limit": 200000, + "max_output": 64000, + "released": "2025-11-24" }, "anthropic/claude-opus-4-6": { "cost": [ @@ -33169,7 +43002,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2025-05-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-05" }, "anthropic/claude-opus-4-7": { "cost": [ @@ -33178,7 +43014,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-16" }, "anthropic/claude-opus-4-8": { "cost": [ @@ -33187,7 +43026,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-28" }, "anthropic/claude-sonnet-4-5": { "cost": [ @@ -33196,7 +43038,10 @@ 0.3, 3.75 ], - "limit": 200000 + "knowledge": "2025-07-31", + "limit": 200000, + "max_output": 64000, + "released": "2025-09-29" }, "anthropic/claude-sonnet-4-6": { "cost": [ @@ -33205,7 +43050,10 @@ 0.3, 3.75 ], - "limit": 1000000 + "knowledge": "2025-08-31", + "limit": 1000000, + "max_output": 64000, + "released": "2026-02-17" }, "anthropic/claude-sonnet-5": { "cost": [ @@ -33214,7 +43062,10 @@ 0.2, 2.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-30" }, "cerebras/gpt-oss-120b": { "cost": [ @@ -33223,7 +43074,11 @@ 0.0, 0.0 ], + "knowledge": "2024-06", "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05", "status": "deprecated" }, "deepseek/deepseek-v4-flash": { @@ -33233,7 +43088,11 @@ 0.028, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "deepseek/deepseek-v4-pro": { "cost": [ @@ -33242,7 +43101,11 @@ 0.145, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "fireworks/glm-5.2": { "cost": [ @@ -33252,6 +43115,9 @@ 0.0 ], "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-13", "status": "deprecated" }, "fireworks/gpt-oss-120b": { @@ -33261,7 +43127,11 @@ 0.015, 0.0 ], + "knowledge": "2024-06", "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05", "status": "deprecated" }, "fireworks/gpt-oss-20b": { @@ -33271,7 +43141,11 @@ 0.035, 0.0 ], + "knowledge": "2024-06", "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05", "status": "deprecated" }, "google/gemini-2.5-flash": { @@ -33281,7 +43155,10 @@ 0.03, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2025-06-17" }, "google/gemini-2.5-flash-lite": { "cost": [ @@ -33290,7 +43167,10 @@ 0.01, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2025-06-17" }, "google/gemini-2.5-pro": { "cost": [ @@ -33299,7 +43179,10 @@ 0.125, 0.0 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2025-06-17", "tiers": [ { "cost": [ @@ -33322,7 +43205,10 @@ 0.025, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-05-07" }, "google/gemini-3.1-pro-preview": { "cost": [ @@ -33331,7 +43217,10 @@ 0.2, 0.0 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2026-02-19", "tiers": [ { "cost": [ @@ -33354,7 +43243,10 @@ 0.15, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-05-19" }, "google/gemini-3.5-flash-lite": { "cost": [ @@ -33363,7 +43255,10 @@ 0.03, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-07-21" }, "google/gemini-3.6-flash": { "cost": [ @@ -33372,7 +43267,10 @@ 0.075, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-07-21" }, "groq/gpt-oss-120b": { "cost": [ @@ -33381,7 +43279,11 @@ 0.075, 0.0 ], + "knowledge": "2024-06", "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05", "status": "deprecated" }, "groq/gpt-oss-20b": { @@ -33391,7 +43293,11 @@ 0.0375, 0.0 ], + "knowledge": "2024-06", "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05", "status": "deprecated" }, "moonshotai/kimi-k3": { @@ -33401,7 +43307,10 @@ 0.3, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-16" }, "openai/gpt-3.5-turbo": { "cost": [ @@ -33410,7 +43319,10 @@ 0.0, 0.0 ], - "limit": 16385 + "knowledge": "2021-09-01", + "limit": 16385, + "max_output": 4096, + "released": "2023-03-01" }, "openai/gpt-4-turbo": { "cost": [ @@ -33419,7 +43331,10 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2023-12", + "limit": 128000, + "max_output": 4096, + "released": "2023-11-06" }, "openai/gpt-4.1": { "cost": [ @@ -33428,7 +43343,10 @@ 0.5, 0.0 ], - "limit": 1047576 + "knowledge": "2024-04", + "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14" }, "openai/gpt-4.1-mini": { "cost": [ @@ -33437,7 +43355,10 @@ 0.1, 0.0 ], - "limit": 1047576 + "knowledge": "2024-04", + "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14" }, "openai/gpt-4.1-nano": { "cost": [ @@ -33446,7 +43367,10 @@ 0.025, 0.0 ], - "limit": 1047576 + "knowledge": "2024-04", + "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14" }, "openai/gpt-4o": { "cost": [ @@ -33455,7 +43379,10 @@ 1.25, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-05-13" }, "openai/gpt-4o-mini": { "cost": [ @@ -33464,7 +43391,10 @@ 0.075, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-07-18" }, "openai/gpt-5": { "cost": [ @@ -33473,7 +43403,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "openai/gpt-5-codex": { "cost": [ @@ -33482,7 +43415,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-09-15" }, "openai/gpt-5-mini": { "cost": [ @@ -33491,7 +43427,10 @@ 0.025, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "openai/gpt-5-nano": { "cost": [ @@ -33500,7 +43439,10 @@ 0.005, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "openai/gpt-5-pro": { "cost": [ @@ -33509,7 +43451,10 @@ 0.0, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 272000, + "released": "2025-10-06" }, "openai/gpt-5.1": { "cost": [ @@ -33518,7 +43463,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "openai/gpt-5.1-codex": { "cost": [ @@ -33527,7 +43475,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "openai/gpt-5.1-codex-mini": { "cost": [ @@ -33536,7 +43487,10 @@ 0.025, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "openai/gpt-5.2": { "cost": [ @@ -33545,7 +43499,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "openai/gpt-5.2-codex": { "cost": [ @@ -33554,7 +43511,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "openai/gpt-5.3-codex": { "cost": [ @@ -33563,7 +43523,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-02-05" }, "openai/gpt-5.4": { "cost": [ @@ -33572,7 +43535,10 @@ 0.25, 0.0 ], + "knowledge": "2025-08-31", "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05", "tiers": [ { "cost": [ @@ -33595,7 +43561,10 @@ 0.075, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "openai/gpt-5.4-nano": { "cost": [ @@ -33604,7 +43573,10 @@ 0.02, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "openai/gpt-5.4-pro": { "cost": [ @@ -33613,7 +43585,10 @@ 3.0, 0.0 ], + "knowledge": "2025-08-31", "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05", "tiers": [ { "cost": [ @@ -33636,7 +43611,10 @@ 0.5, 0.0 ], + "knowledge": "2025-12-01", "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23", "tiers": [ { "cost": [ @@ -33659,7 +43637,10 @@ 3.0, 0.0 ], + "knowledge": "2025-12-01", "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23", "tiers": [ { "cost": [ @@ -33682,7 +43663,10 @@ 0.02, 0.25 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -33705,7 +43689,10 @@ 0.4, 5.0 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -33728,7 +43715,10 @@ 0.2, 2.5 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -33751,7 +43741,10 @@ 7.5, 0.0 ], - "limit": 200000 + "knowledge": "2023-09", + "limit": 200000, + "max_output": 100000, + "released": "2024-12-05" }, "openai/o3": { "cost": [ @@ -33760,7 +43753,10 @@ 0.5, 0.0 ], - "limit": 200000 + "knowledge": "2024-05", + "limit": 200000, + "max_output": 100000, + "released": "2025-04-16" }, "openai/o3-mini": { "cost": [ @@ -33769,7 +43765,10 @@ 0.55, 0.0 ], - "limit": 200000 + "knowledge": "2024-05", + "limit": 200000, + "max_output": 100000, + "released": "2024-12-20" }, "openai/o4-mini": { "cost": [ @@ -33778,7 +43777,10 @@ 0.275, 0.0 ], - "limit": 200000 + "knowledge": "2024-05", + "limit": 200000, + "max_output": 100000, + "released": "2025-04-16" }, "qwen/qwen3.6-flash": { "cost": [ @@ -33788,6 +43790,8 @@ 0.0 ], "limit": 1000000, + "max_output": 65536, + "released": "2026-04-27", "tiers": [ { "cost": [ @@ -33810,7 +43814,9 @@ 0.5, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-05-21" }, "qwen/qwen3.7-plus": { "cost": [ @@ -33819,7 +43825,10 @@ 0.08, 0.0 ], + "knowledge": "2025-04", "limit": 1000000, + "max_output": 64000, + "released": "2026-06-02", "tiers": [ { "cost": [ @@ -33843,6 +43852,8 @@ 0.0 ], "limit": 1000000, + "max_output": 131072, + "released": "2026-07-19", "status": "deprecated" }, "thinkingmachines/inkling": { @@ -33852,7 +43863,10 @@ 0.374, 0.0 ], - "limit": 65536 + "limit": 65536, + "max_output": 65536, + "open": true, + "released": "2026-07-15" }, "xai/grok-4.20-0309-non-reasoning": { "cost": [ @@ -33862,6 +43876,8 @@ 0.0 ], "limit": 1000000, + "max_output": 30000, + "released": "2026-03-09", "tiers": [ { "cost": [ @@ -33885,6 +43901,8 @@ 0.0 ], "limit": 1000000, + "max_output": 30000, + "released": "2026-03-09", "tiers": [ { "cost": [ @@ -33908,6 +43926,8 @@ 0.0 ], "limit": 1000000, + "max_output": 30000, + "released": "2026-04-17", "tiers": [ { "cost": [ @@ -33931,6 +43951,8 @@ 0.0 ], "limit": 500000, + "max_output": 500000, + "released": "2026-07-08", "tiers": [ { "cost": [ @@ -33954,6 +43976,8 @@ 0.0 ], "limit": 256000, + "max_output": 256000, + "released": "2026-04-16", "tiers": [ { "cost": [ @@ -33976,7 +44000,11 @@ 0.003, 0.0 ], - "limit": 1048576 + "knowledge": "2024-12", + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-04-22" }, "zai/glm-4.5": { "cost": [ @@ -33985,7 +44013,11 @@ 0.11, 0.0 ], - "limit": 131072 + "knowledge": "2025-04", + "limit": 131072, + "max_output": 98304, + "open": true, + "released": "2025-07-28" }, "zai/glm-4.5-air": { "cost": [ @@ -33994,7 +44026,11 @@ 0.03, 0.0 ], - "limit": 131072 + "knowledge": "2025-04", + "limit": 131072, + "max_output": 98304, + "open": true, + "released": "2025-07-28" }, "zai/glm-4.6": { "cost": [ @@ -34003,7 +44039,11 @@ 0.11, 0.0 ], - "limit": 204800 + "knowledge": "2025-04", + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-09-30" }, "zai/glm-4.7": { "cost": [ @@ -34012,7 +44052,11 @@ 0.11, 0.0 ], - "limit": 204800 + "knowledge": "2025-04", + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-12-22" }, "zai/glm-5": { "cost": [ @@ -34021,7 +44065,10 @@ 0.2, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-02-12" }, "zai/glm-5-turbo": { "cost": [ @@ -34030,7 +44077,9 @@ 0.24, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 131072, + "released": "2026-03-16" }, "zai/glm-5.1": { "cost": [ @@ -34039,7 +44088,10 @@ 0.26, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 131072, + "open": true, + "released": "2026-04-07" }, "zai/glm-5.2": { "cost": [ @@ -34048,7 +44100,10 @@ 0.26, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-13" } }, "name": "Impossibl" @@ -34062,7 +44117,10 @@ 0.025, 0.0 ], - "limit": 128000 + "knowledge": "2025-01-01", + "limit": 128000, + "max_output": 50000, + "released": "2026-02-24" }, "mercury-2.5": { "cost": [ @@ -34071,7 +44129,10 @@ 0.02, 0.0 ], - "limit": 260000 + "knowledge": "2025-11-01", + "limit": 260000, + "max_output": 65536, + "released": "2026-09-08" }, "mercury-3": { "cost": [ @@ -34080,7 +44141,9 @@ 0.01, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-10-16" }, "mercury-edit-2": { "cost": [ @@ -34089,7 +44152,9 @@ 0.025, 0.0 ], - "limit": 32000 + "limit": 32000, + "max_output": 8192, + "released": "2026-03-30" } }, "name": "Inception" @@ -34098,57 +44163,78 @@ "models": { "deepseek-ai/DeepSeek-V4-Flash-0731": { "cost": [ - 0.11, - 0.3884, + 0.13, + 0.3666, 0.027, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-07-31" }, "moonshotai/Kimi-K2.6": { "cost": [ - 0.6026, - 3.2, - 0.169, + 0.6236, + 3.5, + 0.1674, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-20" }, "moonshotai/Kimi-K2.7-Code": { "cost": [ - 0.6712, - 3.35, + 0.56, + 3.1, 0.15, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-06-12" }, "zai-org/GLM-5.2": { "cost": [ - 0.9, - 2.88, - 0.14, + 0.99, + 4.4, + 0.16, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-06-13" }, "zai-org/GLM-5.3": { "cost": [ - 0.4, - 1.96, - 0.12, + 1.2, + 2.2, + 0.14, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-08-14" }, "zai-org/GLM-5.3-Flash": { "cost": [ - 0.18, - 0.69, - 0.075, + 0.17, + 0.6, + 0.06, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-08-26" } }, "name": "Inceptron" @@ -34162,7 +44248,11 @@ 0.012, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-09-10" }, "glm-5.3": { "cost": [ @@ -34171,7 +44261,10 @@ 0.26, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "glm-5.3-flash:fast": { "cost": [ @@ -34180,7 +44273,10 @@ 0.06, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-26" }, "glm-5.3:fast": { "cost": [ @@ -34189,7 +44285,10 @@ 0.52, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "kimi-k3:fast": { "cost": [ @@ -34198,7 +44297,10 @@ 0.6, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-16" }, "minimax-m3": { "cost": [ @@ -34207,7 +44309,10 @@ 0.06, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 512000, + "open": true, + "released": "2026-06-01" }, "minimax-m3:fast": { "cost": [ @@ -34216,7 +44321,10 @@ 0.12, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 512000, + "open": true, + "released": "2026-06-01" } }, "name": "Inco" @@ -34230,7 +44338,10 @@ 0.25, 3.125 ], - "limit": 271999 + "knowledge": "2026-02-16", + "limit": 271999, + "max_output": 128000, + "released": "2026-07-09" }, "infer/gpt-6-astra:official": { "cost": [ @@ -34239,7 +44350,10 @@ 1.25, 15.625 ], - "limit": 271999 + "knowledge": "2026-04-30", + "limit": 271999, + "max_output": 128000, + "released": "2026-09-04" } }, "name": "Infer by Flow7" @@ -34253,7 +44367,11 @@ 0.0, 0.0 ], - "limit": 125000 + "knowledge": "2024-12", + "limit": 125000, + "max_output": 4096, + "open": true, + "released": "2025-01-01" }, "meta/llama-3.1-8b-instruct": { "cost": [ @@ -34262,7 +44380,11 @@ 0.0, 0.0 ], + "knowledge": "2023-12", "limit": 16000, + "max_output": 4096, + "open": true, + "released": "2024-07-23", "status": "deprecated" }, "meta/llama-3.2-11b-vision-instruct": { @@ -34272,7 +44394,11 @@ 0.0, 0.0 ], + "knowledge": "2023-12", "limit": 16000, + "max_output": 4096, + "open": true, + "released": "2024-09-25", "status": "deprecated" }, "meta/llama-3.2-1b-instruct": { @@ -34282,7 +44408,11 @@ 0.0, 0.0 ], - "limit": 16000 + "knowledge": "2023-12", + "limit": 16000, + "max_output": 4096, + "open": true, + "released": "2024-09-25" }, "meta/llama-3.2-3b-instruct": { "cost": [ @@ -34291,7 +44421,11 @@ 0.0, 0.0 ], - "limit": 16000 + "knowledge": "2023-12", + "limit": 16000, + "max_output": 4096, + "open": true, + "released": "2025-01-01" }, "mistral/mistral-nemo-12b-instruct": { "cost": [ @@ -34300,7 +44434,11 @@ 0.0, 0.0 ], + "knowledge": "2024-12", "limit": 16000, + "max_output": 4096, + "open": true, + "released": "2024-07-18", "status": "deprecated" }, "osmosis/osmosis-structure-0.6b": { @@ -34310,7 +44448,11 @@ 0.0, 0.0 ], + "knowledge": "2024-12", "limit": 4000, + "max_output": 2048, + "open": true, + "released": "2025-01-01", "status": "deprecated" }, "qwen/qwen-2.5-7b-vision-instruct": { @@ -34320,7 +44462,11 @@ 0.0, 0.0 ], + "knowledge": "2024-12", "limit": 125000, + "max_output": 4096, + "open": true, + "released": "2025-01-01", "status": "deprecated" }, "qwen/qwen3-embedding-4b": { @@ -34330,8 +44476,13 @@ 0.0, 0.0 ], + "knowledge": "2024-12", "limit": 32000, - "status": "deprecated" + "max_output": 2048, + "open": true, + "released": "2025-06-05", + "status": "deprecated", + "type": "embedding" } }, "name": "Inference" @@ -34345,7 +44496,10 @@ 0.0, 0.0 ], - "limit": 262000 + "limit": 262000, + "max_output": 100000, + "open": true, + "released": "2026-06-26" }, "Devstral-2-123B-Instruct-2512-int4-AutoRound": { "cost": [ @@ -34354,7 +44508,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2025-12", + "limit": 128000, + "max_output": 128000, + "open": true, + "released": "2025-12-09" }, "Ornith-1.0-35B-FP8": { "cost": [ @@ -34363,7 +44521,10 @@ 0.0, 0.0 ], - "limit": 262000 + "limit": 262000, + "max_output": 100000, + "open": true, + "released": "2026-06-25" }, "Qwen3-Coder-Next-FP8": { "cost": [ @@ -34372,7 +44533,11 @@ 0.0, 0.0 ], - "limit": 256144 + "knowledge": "2025-04", + "limit": 256144, + "max_output": 65536, + "open": true, + "released": "2026-02-03" }, "Qwen3-Coder-Next-FP8-no-thinking": { "cost": [ @@ -34381,7 +44546,11 @@ 0.0, 0.0 ], - "limit": 260000 + "knowledge": "2025-04", + "limit": 260000, + "max_output": 65536, + "open": true, + "released": "2026-02-03" }, "Qwen3-Embedding-8B": { "cost": [ @@ -34390,7 +44559,10 @@ 0.0, 0.0 ], - "limit": 32768 + "limit": 32768, + "open": true, + "released": "2025-06-05", + "type": "embedding" }, "Qwen3.6-27B-FP8": { "cost": [ @@ -34399,7 +44571,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-04-22" }, "Qwen3.6-35B-A3B-FP8": { "cost": [ @@ -34408,7 +44583,10 @@ 0.0, 0.0 ], - "limit": 262000 + "limit": 262000, + "max_output": 65536, + "open": true, + "released": "2026-04-17" }, "Qwen3.6-35B-A3B-fp8-no-thinking": { "cost": [ @@ -34417,7 +44595,10 @@ 0.0, 0.0 ], - "limit": 262000 + "limit": 262000, + "max_output": 65536, + "open": true, + "released": "2026-04-17" }, "deepseek-v4-flash": { "cost": [ @@ -34426,7 +44607,11 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 100000, + "open": true, + "released": "2026-04-24" }, "gemma-4-31B-it-fp8": { "cost": [ @@ -34435,7 +44620,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-04-02" }, "mimo-v25": { "cost": [ @@ -34444,7 +44633,11 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2024-12", + "limit": 1000000, + "max_output": 100000, + "open": true, + "released": "2026-04-22" } }, "name": "InferX" @@ -34459,6 +44652,9 @@ 0.0 ], "limit": 200000, + "max_output": 65536, + "open": true, + "released": "2026-02-23", "status": "deprecated" }, "Qwen/Qwen3.5-397B-A17B-FP8": { @@ -34469,6 +44665,9 @@ 0.0 ], "limit": 200000, + "max_output": 65536, + "open": true, + "released": "2026-02-15", "status": "beta" }, "bge_multilingual_gemma2": { @@ -34478,7 +44677,11 @@ 0.0, 0.0 ], - "limit": 8000 + "limit": 8000, + "max_output": 3584, + "open": true, + "released": "2024-07-25", + "type": "embedding" }, "google/gemma-4-31B-it": { "cost": [ @@ -34487,7 +44690,11 @@ 0.0, 0.0 ], - "limit": 100000 + "knowledge": "2025-01", + "limit": 100000, + "max_output": 32768, + "open": true, + "released": "2026-04-02" }, "mini_lm_l12_v2": { "cost": [ @@ -34496,7 +44703,11 @@ 0.0, 0.0 ], - "limit": 128 + "limit": 128, + "max_output": 384, + "open": true, + "released": "2021-08-30", + "type": "embedding" }, "mistralai/Ministral-3-14B-Instruct-2512": { "cost": [ @@ -34506,6 +44717,9 @@ 0.0 ], "limit": 100000, + "max_output": 25600, + "open": true, + "released": "2025-12-02", "status": "beta" }, "mistralai/Mistral-Small-4-119B-2603": { @@ -34515,7 +44729,11 @@ 0.0, 0.0 ], - "limit": 256000 + "knowledge": "2025-06", + "limit": 256000, + "max_output": 256000, + "open": true, + "released": "2026-03-16" }, "moonshotai/Kimi-K2.6": { "cost": [ @@ -34524,7 +44742,11 @@ 0.0, 0.0 ], + "knowledge": "2025-01", "limit": 256000, + "max_output": 256000, + "open": true, + "released": "2026-04-20", "status": "beta" }, "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8": { @@ -34534,7 +44756,11 @@ 0.0, 0.0 ], + "knowledge": "2025-06-25", "limit": 1000000, + "max_output": 262144, + "open": true, + "released": "2025-12-15", "status": "deprecated" }, "swiss-ai/Apertus-v1.5-70B": { @@ -34545,6 +44771,9 @@ 0.0 ], "limit": 100000, + "max_output": 8192, + "open": true, + "released": "2026-07-24", "status": "beta" } }, @@ -34559,7 +44788,11 @@ 0.230625, 0.0 ], - "limit": 106000 + "knowledge": "2024-12", + "limit": 106000, + "max_output": 4096, + "open": true, + "released": "2025-07-22" }, "Qwen/Qwen2.5-VL-32B-Instruct": { "cost": [ @@ -34568,7 +44801,11 @@ 0.025, 0.1 ], + "knowledge": "2024-09", "limit": 32000, + "max_output": 4096, + "open": true, + "released": "2024-11-01", "status": "deprecated" }, "Qwen/Qwen3-235B-A22B-Thinking-2507": { @@ -34578,7 +44815,11 @@ 0.055, 0.22 ], + "knowledge": "2024-12", "limit": 262144, + "max_output": 4096, + "open": true, + "released": "2025-07-25", "status": "deprecated" }, "Qwen/Qwen3-Next-80B-A3B-Instruct": { @@ -34588,7 +44829,11 @@ 0.059375, 0.0 ], - "limit": 262144 + "knowledge": "2024-12", + "limit": 262144, + "max_output": 4096, + "open": true, + "released": "2025-09" }, "deepseek-ai/DeepSeek-R1-0528": { "cost": [ @@ -34597,7 +44842,11 @@ 0.261834, 0.0 ], - "limit": 128000 + "knowledge": "2024-07", + "limit": 128000, + "max_output": 4096, + "open": true, + "released": "2025-05-28" }, "meta-llama/Llama-3.2-90B-Vision-Instruct": { "cost": [ @@ -34606,7 +44855,11 @@ 0.175, 0.7 ], + "knowledge": "2023-12", "limit": 16000, + "max_output": 4096, + "open": true, + "released": "2024-09-25", "status": "deprecated" }, "meta-llama/Llama-3.3-70B-Instruct": { @@ -34616,7 +44869,11 @@ 0.2733, 0.0 ], - "limit": 128000 + "knowledge": "2023-12", + "limit": 128000, + "max_output": 4096, + "open": true, + "released": "2024-12-06" }, "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8": { "cost": [ @@ -34625,7 +44882,11 @@ 0.134375, 0.0 ], - "limit": 430000 + "knowledge": "2024-12", + "limit": 430000, + "max_output": 4096, + "open": true, + "released": "2025-04-05" }, "mistralai/Devstral-Small-2505": { "cost": [ @@ -34634,7 +44895,10 @@ 0.025, 0.1 ], + "knowledge": "2024-12", "limit": 128000, + "max_output": 4096, + "released": "2025-05-01", "status": "deprecated" }, "mistralai/Magistral-Small-2506": { @@ -34644,7 +44908,11 @@ 0.25, 1.0 ], + "knowledge": "2025-01", "limit": 128000, + "max_output": 4096, + "open": true, + "released": "2025-06-10", "status": "deprecated" }, "mistralai/Mistral-Large-Instruct-2411": { @@ -34654,7 +44922,11 @@ 1.0, 4.0 ], + "knowledge": "2024-10", "limit": 128000, + "max_output": 4096, + "open": true, + "released": "2024-11-18", "status": "deprecated" }, "mistralai/Mistral-Nemo-Instruct-2407": { @@ -34664,7 +44936,11 @@ 0.0257, 0.0 ], - "limit": 128000 + "knowledge": "2024-05", + "limit": 128000, + "max_output": 4096, + "open": true, + "released": "2024-07-18" }, "moonshotai/Kimi-K2-Instruct-0905": { "cost": [ @@ -34673,7 +44949,11 @@ 0.285, 0.0 ], - "limit": 32768 + "knowledge": "2024-08", + "limit": 32768, + "max_output": 4096, + "open": true, + "released": "2025-09-05" }, "moonshotai/Kimi-K2-Thinking": { "cost": [ @@ -34682,7 +44962,11 @@ 0.3, 0.0 ], - "limit": 32768 + "knowledge": "2024-08", + "limit": 32768, + "max_output": 4096, + "open": true, + "released": "2025-11-06" }, "openai/gpt-oss-120b": { "cost": [ @@ -34691,7 +44975,11 @@ 0.094, 0.0 ], - "limit": 131072 + "knowledge": "2024-10", + "limit": 131072, + "max_output": 4096, + "open": true, + "released": "2025-08-05" }, "openai/gpt-oss-20b": { "cost": [ @@ -34700,7 +44988,11 @@ 0.0275, 0.0 ], - "limit": 64000 + "knowledge": "2024-10", + "limit": 64000, + "max_output": 4096, + "open": true, + "released": "2025-08-05" }, "zai-org/GLM-4.6": { "cost": [ @@ -34709,7 +45001,11 @@ 0.26, 0.0 ], - "limit": 200000 + "knowledge": "2024-10", + "limit": 200000, + "max_output": 4096, + "open": true, + "released": "2025-09-30" } }, "name": "IO.NET" @@ -34723,7 +45019,11 @@ 0.005, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 393216, + "open": true, + "released": "2026-09-10" }, "deepseek/deepseek-v4-pro-0813": { "cost": [ @@ -34732,7 +45032,10 @@ 0.026, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 393216, + "open": true, + "released": "2026-08-13" }, "deepseek/deepseek-v4.1-flash": { "cost": [ @@ -34741,7 +45044,11 @@ 0.005, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 393216, + "open": true, + "released": "2026-09-10" }, "minimax/minimax-m3": { "cost": [ @@ -34750,7 +45057,10 @@ 0.05, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 524288, + "open": true, + "released": "2026-06-01" }, "moonshotai/kimi-k2.7-code": { "cost": [ @@ -34759,7 +45069,11 @@ 0.15, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 235929, + "open": true, + "released": "2026-06-12" }, "moonshotai/kimi-k3": { "cost": [ @@ -34768,7 +45082,10 @@ 0.23, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 999999, + "open": true, + "released": "2026-07-16" }, "qwen/qwen3.8-2.4t-a95b": { "cost": [ @@ -34777,7 +45094,10 @@ 0.25, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-08-12" }, "qwen/qwen3.8-27b": { "cost": [ @@ -34786,7 +45106,10 @@ 0.0, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 8192, + "open": true, + "released": "2026-08-14" }, "z-ai/glm-5.3": { "cost": [ @@ -34795,7 +45118,10 @@ 0.2, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "z-ai/glm-5.3-flash": { "cost": [ @@ -34804,7 +45130,10 @@ 0.023, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-08-26" } }, "name": "IteraCompute" @@ -34818,7 +45147,11 @@ 0.028, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "DeepSeek-V4-Pro": { "cost": [ @@ -34827,7 +45160,11 @@ 0.14, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "GLM-5.1": { "cost": [ @@ -34836,7 +45173,10 @@ 0.26, 0.0 ], - "limit": 202752 + "limit": 202752, + "max_output": 131072, + "open": true, + "released": "2026-04-07" }, "GLM-5.2": { "cost": [ @@ -34845,7 +45185,10 @@ 0.26, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "Hy3": { "cost": [ @@ -34855,6 +45198,9 @@ 0.0 ], "limit": 202752, + "max_output": 128000, + "open": true, + "released": "2026-07-06", "status": "deprecated" }, "Kimi-K2.5": { @@ -34864,7 +45210,11 @@ 0.1, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 180224, + "open": true, + "released": "2026-01-27" }, "Kimi-K2.7-Code": { "cost": [ @@ -34873,7 +45223,11 @@ 0.19, 0.0 ], - "limit": 271360 + "knowledge": "2025-01", + "limit": 271360, + "max_output": 262144, + "open": true, + "released": "2026-06-12" }, "Kimi-K3": { "cost": [ @@ -34882,7 +45236,10 @@ 0.3, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-16" }, "MiniMax-M3": { "cost": [ @@ -34891,7 +45248,10 @@ 0.06, 0.0 ], - "limit": 524288 + "limit": 524288, + "max_output": 512000, + "open": true, + "released": "2026-06-01" }, "Qwen3-Next-80B-A3B-Instruct": { "cost": [ @@ -34900,7 +45260,11 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 129024, + "max_output": 32768, + "open": true, + "released": "2025-09", "status": "deprecated" }, "Qwen3-Next-80B-A3B-Thinking": { @@ -34910,7 +45274,11 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2025-09", "status": "deprecated" }, "Qwen3-VL-235B-A22B-Instruct": { @@ -34920,7 +45288,11 @@ 0.0, 0.0 ], + "knowledge": "2025-03-31", "limit": 129024, + "max_output": 32768, + "open": true, + "released": "2025-09-23", "status": "deprecated" }, "Qwen3-VL-235B-A22B-Thinking": { @@ -34930,7 +45302,11 @@ 0.0, 0.0 ], + "knowledge": "2025-03-31", "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-09-23", "status": "deprecated" }, "Qwen3.5-122B-A10B": { @@ -34940,7 +45316,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-23" }, "Qwen3.5-27B": { "cost": [ @@ -34949,7 +45328,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-23" }, "Qwen3.5-35B-A3B": { "cost": [ @@ -34958,7 +45340,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-23" }, "Qwen3.5-397B-A17B": { "cost": [ @@ -34967,7 +45352,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-15" } }, "name": "Jalapeno Cloud" @@ -34981,7 +45369,10 @@ 0.0, 0.0 ], - "limit": 123000 + "limit": 123000, + "max_output": 12000, + "open": true, + "released": "2025-06-30" }, "baidu/ernie-4.5-vl-424b-a47b": { "cost": [ @@ -34990,7 +45381,11 @@ 0.0, 0.0 ], - "limit": 123000 + "knowledge": "2025-03-31", + "limit": 123000, + "max_output": 16000, + "open": true, + "released": "2025-06-30" }, "claude-haiku-4-5-20251001": { "cost": [ @@ -34999,7 +45394,10 @@ 0.1, 1.25 ], - "limit": 200000 + "knowledge": "2025-02-28", + "limit": 200000, + "max_output": 64000, + "released": "2025-10-15" }, "claude-opus-4-1-20250805": { "cost": [ @@ -35008,7 +45406,10 @@ 0.0, 0.0 ], + "knowledge": "2025-03-31", "limit": 200000, + "max_output": 32000, + "released": "2025-08-05", "status": "deprecated" }, "claude-opus-4-20250514": { @@ -35018,7 +45419,10 @@ 0.0, 0.0 ], + "knowledge": "2025-03-31", "limit": 200000, + "max_output": 32000, + "released": "2025-05-22", "status": "deprecated" }, "claude-opus-4-5-20251101": { @@ -35028,7 +45432,10 @@ 0.475, 5.9375 ], - "limit": 200000 + "knowledge": "2025-05", + "limit": 200000, + "max_output": 65536, + "released": "2025-11-24" }, "claude-opus-4-6": { "cost": [ @@ -35037,7 +45444,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2025-05-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-05" }, "claude-sonnet-4-20250514": { "cost": [ @@ -35046,7 +45456,10 @@ 0.0, 0.0 ], + "knowledge": "2025-03-31", "limit": 200000, + "max_output": 64000, + "released": "2025-05-22", "status": "deprecated" }, "claude-sonnet-4-5-20250929": { @@ -35056,7 +45469,10 @@ 0.3, 3.75 ], + "knowledge": "2025-07-31", "limit": 200000, + "max_output": 64000, + "released": "2025-09-29", "tiers": [ { "cost": [ @@ -35079,7 +45495,10 @@ 0.35, 0.0 ], - "limit": 163840 + "limit": 163840, + "max_output": 32768, + "open": true, + "released": "2025-05-28" }, "deepseek/deepseek-v3-0324": { "cost": [ @@ -35088,7 +45507,10 @@ 0.14, 0.0 ], - "limit": 163840 + "limit": 163840, + "max_output": 163840, + "open": true, + "released": "2025-03-24" }, "deepseek/deepseek-v3.1": { "cost": [ @@ -35097,7 +45519,10 @@ 0.0, 0.0 ], - "limit": 163840 + "limit": 163840, + "max_output": 32768, + "open": true, + "released": "2025-08-21" }, "gemini-2.5-flash": { "cost": [ @@ -35106,7 +45531,10 @@ 0.0285, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65535, + "released": "2025-06-17" }, "gemini-2.5-flash-lite": { "cost": [ @@ -35115,7 +45543,10 @@ 0.0095, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65535, + "released": "2025-06-17" }, "gemini-2.5-flash-lite-preview-06-17": { "cost": [ @@ -35124,7 +45555,10 @@ 0.0, 0.0 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65535, + "released": "2025-06-17", "status": "deprecated" }, "gemini-2.5-flash-lite-preview-09-2025": { @@ -35134,7 +45568,10 @@ 0.0, 0.0 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2025-09-25", "status": "deprecated" }, "gemini-2.5-flash-preview-05-20": { @@ -35144,7 +45581,10 @@ 0.0285, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2025-05-20" }, "gemini-2.5-pro": { "cost": [ @@ -35153,7 +45593,10 @@ 0.1187, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65535, + "released": "2025-06-17" }, "gemini-2.5-pro-preview-06-05": { "cost": [ @@ -35162,7 +45605,10 @@ 0.1187, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01-31", + "limit": 1048576, + "max_output": 65536, + "released": "2025-06-05" }, "gemini-3-flash-preview": { "cost": [ @@ -35171,7 +45617,10 @@ 0.0475, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2025-12-17" }, "gemini-3-pro-preview": { "cost": [ @@ -35180,7 +45629,10 @@ 0.0, 0.0 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2025-11-18", "status": "deprecated" }, "gpt-5-chat-latest": { @@ -35190,7 +45642,10 @@ 0.0, 0.0 ], + "knowledge": "2024-09-30", "limit": 400000, + "max_output": 128000, + "released": "2025-08-07", "status": "deprecated" }, "gpt-5-codex": { @@ -35200,7 +45655,10 @@ 0.1187, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-09-15" }, "gpt-5-mini": { "cost": [ @@ -35209,7 +45667,10 @@ 0.0237, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "gpt-5-nano": { "cost": [ @@ -35218,7 +45679,10 @@ 0.0047, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "gpt-5-pro": { "cost": [ @@ -35227,7 +45691,10 @@ 0.0, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 272000, + "released": "2025-10-06" }, "gpt-5.1": { "cost": [ @@ -35236,7 +45703,10 @@ 0.1187, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "gpt-5.1-codex": { "cost": [ @@ -35245,7 +45715,10 @@ 0.1187, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "gpt-5.1-codex-max": { "cost": [ @@ -35254,7 +45727,10 @@ 0.1187, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "gpt-5.1-codex-mini": { "cost": [ @@ -35263,7 +45739,10 @@ 0.0237, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "gpt-5.2": { "cost": [ @@ -35272,7 +45751,10 @@ 0.1662, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "gpt-5.2-codex": { "cost": [ @@ -35281,7 +45763,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "gpt-5.2-pro": { "cost": [ @@ -35290,7 +45775,10 @@ 0.0, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "grok-4-0709": { "cost": [ @@ -35299,7 +45787,9 @@ 0.0, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 8192, + "released": "2026-01" }, "grok-4-1-fast-non-reasoning": { "cost": [ @@ -35308,7 +45798,9 @@ 0.0, 0.0 ], - "limit": 2000000 + "limit": 2000000, + "max_output": 30000, + "released": "2025-11-19" }, "grok-4-1-fast-reasoning": { "cost": [ @@ -35317,7 +45809,9 @@ 0.0, 0.0 ], - "limit": 2000000 + "limit": 2000000, + "max_output": 30000, + "released": "2025-11-19" }, "grok-4-fast-non-reasoning": { "cost": [ @@ -35327,6 +45821,8 @@ 0.0 ], "limit": 2000000, + "max_output": 2000000, + "released": "2025-12-18", "status": "deprecated" }, "grok-4-fast-reasoning": { @@ -35337,6 +45833,8 @@ 0.0 ], "limit": 2000000, + "max_output": 2000000, + "released": "2025-12-18", "status": "deprecated" }, "grok-code-fast-1": { @@ -35346,7 +45844,9 @@ 0.019, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 10000, + "released": "2025-09-02" }, "minimax/minimax-m2.1": { "cost": [ @@ -35355,7 +45855,10 @@ 0.03, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-12-23" }, "minimaxai/minimax-m1-80k": { "cost": [ @@ -35364,7 +45867,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 40000, + "open": true, + "released": "2025-06-17" }, "moonshotai/kimi-k2-0905": { "cost": [ @@ -35373,7 +45879,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 100352, + "open": true, + "released": "2025-09-05" }, "moonshotai/kimi-k2-instruct": { "cost": [ @@ -35382,7 +45891,10 @@ 0.0, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 100352, + "open": true, + "released": "2025-07-11" }, "moonshotai/kimi-k2.5": { "cost": [ @@ -35391,7 +45903,11 @@ 0.1, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-01-27" }, "o3": { "cost": [ @@ -35400,7 +45916,10 @@ 0.475, 0.0 ], - "limit": 200000 + "knowledge": "2024-05", + "limit": 200000, + "max_output": 100000, + "released": "2025-04-16" }, "o3-mini": { "cost": [ @@ -35409,7 +45928,10 @@ 0.5225, 0.0 ], - "limit": 200000 + "knowledge": "2024-05", + "limit": 200000, + "max_output": 100000, + "released": "2024-12-20" }, "o4-mini": { "cost": [ @@ -35418,7 +45940,10 @@ 0.0, 0.0 ], + "knowledge": "2024-05", "limit": 200000, + "max_output": 100000, + "released": "2025-04-16", "status": "deprecated" }, "qwen/qwen3-235b-a22b-fp8": { @@ -35428,7 +45953,11 @@ 0.0, 0.0 ], - "limit": 40960 + "knowledge": "2025-04", + "limit": 40960, + "max_output": 20000, + "open": true, + "released": "2025-04-28" }, "qwen/qwen3-235b-a22b-instruct-2507": { "cost": [ @@ -35437,7 +45966,10 @@ 0.0, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 16384, + "open": true, + "released": "2025-07-21" }, "qwen/qwen3-235b-a22b-thinking-2507": { "cost": [ @@ -35446,7 +45978,10 @@ 0.0, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2025-07-25" }, "qwen/qwen3-30b-a3b-fp8": { "cost": [ @@ -35455,7 +45990,10 @@ 0.0, 0.0 ], - "limit": 40960 + "limit": 40960, + "max_output": 20000, + "open": true, + "released": "2025-04-28" }, "qwen/qwen3-32b-fp8": { "cost": [ @@ -35464,7 +46002,11 @@ 0.0, 0.0 ], - "limit": 40960 + "knowledge": "2025-04", + "limit": 40960, + "max_output": 20000, + "open": true, + "released": "2025-04-28" }, "qwen/qwen3-coder-480b-a35b-instruct": { "cost": [ @@ -35473,7 +46015,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-04", + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2025-07-22" }, "qwen/qwen3-coder-next": { "cost": [ @@ -35482,7 +46028,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-09", + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-03" }, "qwen/qwen3-next-80b-a3b-instruct": { "cost": [ @@ -35491,7 +46041,11 @@ 0.0, 0.0 ], - "limit": 65536 + "knowledge": "2025-04", + "limit": 65536, + "max_output": 65536, + "open": true, + "released": "2025-09" }, "qwen/qwen3-next-80b-a3b-thinking": { "cost": [ @@ -35500,7 +46054,11 @@ 0.0, 0.0 ], - "limit": 65536 + "knowledge": "2025-04", + "limit": 65536, + "max_output": 65536, + "open": true, + "released": "2025-09" }, "xiaomimimo/mimo-v2-flash": { "cost": [ @@ -35509,7 +46067,11 @@ 0.02, 0.0 ], - "limit": 262144 + "knowledge": "2024-12-01", + "limit": 262144, + "max_output": 131072, + "open": true, + "released": "2025-12-16" }, "zai-org/glm-4.5": { "cost": [ @@ -35518,7 +46080,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2025-04", + "limit": 131072, + "max_output": 98304, + "open": true, + "released": "2025-07-28" }, "zai-org/glm-4.5v": { "cost": [ @@ -35527,7 +46093,11 @@ 0.0, 0.0 ], - "limit": 65536 + "knowledge": "2025-04", + "limit": 65536, + "max_output": 16384, + "open": true, + "released": "2025-08-11" }, "zai-org/glm-4.7": { "cost": [ @@ -35536,7 +46106,11 @@ 0.0, 0.0 ], - "limit": 204800 + "knowledge": "2025-04", + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-12-22" }, "zai-org/glm-4.7-flash": { "cost": [ @@ -35545,7 +46119,11 @@ 0.01, 0.0 ], - "limit": 200000 + "knowledge": "2025-04", + "limit": 200000, + "max_output": 128000, + "open": true, + "released": "2026-01-19" } }, "name": "Jiekou.AI" @@ -35559,7 +46137,10 @@ 1.2, 14.85714286 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-09" }, "claude-opus-4-7": { "cost": [ @@ -35568,7 +46149,10 @@ 0.57142857, 7.42857143 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-16" }, "claude-opus-4-8": { "cost": [ @@ -35577,7 +46161,10 @@ 0.57142857, 7.42857143 ], - "limit": 1000000 + "knowledge": "2026-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-28" }, "claude-opus-5": { "cost": [ @@ -35586,7 +46173,10 @@ 2.28571429, 5.71428571 ], - "limit": 1000000 + "knowledge": "2026-05", + "limit": 1000000, + "max_output": 128000, + "released": "2026-07-24" }, "claude-sonnet-4-6": { "cost": [ @@ -35595,7 +46185,10 @@ 0.36, 4.45714286 ], - "limit": 1000000 + "knowledge": "2025-08-31", + "limit": 1000000, + "max_output": 64000, + "released": "2026-02-17" }, "claude-sonnet-5": { "cost": [ @@ -35604,7 +46197,10 @@ 0.57142857, 1.71428571 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-30" }, "deepseek-v4-1-flash": { "cost": [ @@ -35613,7 +46209,11 @@ 0.00371429, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-09-10" }, "deepseek-v4-flash": { "cost": [ @@ -35622,7 +46222,11 @@ 0.00371429, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "deepseek-v4-flash:free": { "cost": [ @@ -35631,7 +46235,11 @@ 0.0, 0.0 ], + "knowledge": "2025-05", "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24", "status": "deprecated" }, "deepseek-v4-pro": { @@ -35641,7 +46249,11 @@ 0.00571429, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "gemini-3-1-flash-lite": { "cost": [ @@ -35650,7 +46262,10 @@ 0.02857143, 0.08571429 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-05-07" }, "gemini-3-1-pro": { "cost": [ @@ -35659,7 +46274,10 @@ 0.12, 0.22285714 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-02-19" }, "gemini-3-6-flash": { "cost": [ @@ -35668,7 +46286,10 @@ 0.03428571, 0.01714286 ], + "knowledge": "2026-03", "limit": 1048576, + "max_output": 65536, + "released": "2026-07-21", "status": "deprecated" }, "gemini-3-7-flash": { @@ -35678,7 +46299,10 @@ 0.03428571, 0.01714286 ], + "knowledge": "2026-03", "limit": 1048576, + "max_output": 65536, + "released": "2026-08-13", "status": "deprecated" }, "gemma-4-31b-it": { @@ -35688,7 +46312,11 @@ 0.04114286, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-04-02" }, "glm-4-7-flash:free": { "cost": [ @@ -35697,7 +46325,11 @@ 0.0, 0.0 ], - "limit": 200000 + "knowledge": "2025-04", + "limit": 200000, + "max_output": 131072, + "open": true, + "released": "2026-01-19" }, "glm-5-2": { "cost": [ @@ -35706,7 +46338,10 @@ 0.05314286, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "glm-5-3": { "cost": [ @@ -35715,7 +46350,10 @@ 0.05314286, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "glm-5-3-flash": { "cost": [ @@ -35724,7 +46362,10 @@ 0.02285714, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-26" }, "gpt-5-4-mini": { "cost": [ @@ -35733,7 +46374,10 @@ 0.0, 0.0 ], + "knowledge": "2025-08-31", "limit": 400000, + "max_output": 128000, + "released": "2026-03-17", "status": "deprecated" }, "gpt-5-5": { @@ -35743,7 +46387,10 @@ 0.57142857, 0.0 ], - "limit": 1050000 + "knowledge": "2025-12-01", + "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23" }, "gpt-5-6-luna": { "cost": [ @@ -35752,7 +46399,10 @@ 0.02, 0.25714286 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "gpt-5-6-sol": { "cost": [ @@ -35761,7 +46411,10 @@ 1.18857143, 3.71428571 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "gpt-5-6-terra": { "cost": [ @@ -35770,7 +46423,10 @@ 0.0, 0.0 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "status": "deprecated" }, "gpt-oss-120b": { @@ -35780,7 +46436,11 @@ 0.0036, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "gpt-oss-20b": { "cost": [ @@ -35789,7 +46449,11 @@ 0.00371429, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "grok-4-5": { "cost": [ @@ -35798,7 +46462,9 @@ 0.34285714, 0.0 ], - "limit": 500000 + "limit": 500000, + "max_output": 500000, + "released": "2026-07-08" }, "grok-4-6": { "cost": [ @@ -35807,7 +46473,10 @@ 0.34285714, 0.0 ], - "limit": 500000 + "knowledge": "2026-02-01", + "limit": 500000, + "max_output": 500000, + "released": "2026-08-12" }, "hy3": { "cost": [ @@ -35816,7 +46485,10 @@ 0.01542857, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 128000, + "open": true, + "released": "2026-07-06" }, "hy3:free": { "cost": [ @@ -35825,7 +46497,10 @@ 0.0, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 128000, + "open": true, + "released": "2026-07-06" }, "kimi-k2-6": { "cost": [ @@ -35834,7 +46509,11 @@ 0.28571429, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-20" }, "kimi-k2-6:free": { "cost": [ @@ -35843,7 +46522,11 @@ 0.0, 0.0 ], + "knowledge": "2025-01", "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-20", "status": "deprecated" }, "kimi-k2-7-code": { @@ -35853,7 +46536,11 @@ 0.11428571, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-06-12" }, "kimi-k2-7-code:free": { "cost": [ @@ -35862,7 +46549,11 @@ 0.0, 0.0 ], + "knowledge": "2025-01", "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-06-12", "status": "deprecated" }, "kimi-k3": { @@ -35872,7 +46563,10 @@ 0.11428571, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-16" }, "mimo-v2-5": { "cost": [ @@ -35881,7 +46575,11 @@ 0.0, 0.0 ], + "knowledge": "2024-12", "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-04-22", "status": "deprecated" }, "mimo-v2-5-pro": { @@ -35891,7 +46589,11 @@ 0.0, 0.0 ], + "knowledge": "2024-12", "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-04-22", "status": "deprecated" }, "mimo-v2-5:free": { @@ -35901,7 +46603,11 @@ 0.0, 0.0 ], + "knowledge": "2024-12", "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-04-22", "status": "deprecated" }, "minimax-m2-7": { @@ -35911,7 +46617,10 @@ 0.06857143, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-03-18" }, "minimax-m2-7-highspeed": { "cost": [ @@ -35920,7 +46629,10 @@ 0.11428571, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-03-18" }, "minimax-m3": { "cost": [ @@ -35929,7 +46641,10 @@ 0.06857143, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 512000, + "open": true, + "released": "2026-06-01" }, "mistral-large:free": { "cost": [ @@ -35938,7 +46653,11 @@ 0.0, 0.0 ], + "knowledge": "2024-11", "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2024-11-01", "status": "deprecated" }, "mistral-medium-3-5:free": { @@ -35949,6 +46668,9 @@ 0.0 ], "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-29", "status": "deprecated" }, "nemotron-3-super-120b-a12b": { @@ -35958,7 +46680,11 @@ 0.00971429, 0.0 ], - "limit": 262144 + "knowledge": "2025-06", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-03-11" }, "nemotron-3-super-120b-a12b:free": { "cost": [ @@ -35967,7 +46693,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-06", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-03-11" }, "nemotron-3-ultra-550b-a55b": { "cost": [ @@ -35976,7 +46706,11 @@ 0.06857143, 0.0 ], - "limit": 1000000 + "knowledge": "2025-09", + "limit": 1000000, + "max_output": 128000, + "open": true, + "released": "2026-06-04" }, "qwen3-7-plus": { "cost": [ @@ -35985,7 +46719,10 @@ 0.07428571, 0.48 ], - "limit": 1000000 + "knowledge": "2025-04", + "limit": 1000000, + "max_output": 64000, + "released": "2026-06-02" }, "qwen3-8-max": { "cost": [ @@ -35994,7 +46731,9 @@ 0.29714286, 2.97142857 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-08-03" }, "step-3-7-flash": { "cost": [ @@ -36003,7 +46742,11 @@ 0.048, 0.0 ], - "limit": 256000 + "knowledge": "2026-03-01", + "limit": 256000, + "max_output": 256000, + "open": true, + "released": "2026-05-29" }, "step-3-7-flash:free": { "cost": [ @@ -36012,7 +46755,11 @@ 0.0, 0.0 ], + "knowledge": "2026-03-01", "limit": 256000, + "max_output": 256000, + "open": true, + "released": "2026-05-29", "status": "deprecated" } }, @@ -36027,7 +46774,9 @@ 0.2, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 32768, + "released": "2025-12-21" }, "aion-labs/aion-3.0": { "cost": [ @@ -36036,7 +46785,9 @@ 0.75, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 32768, + "released": "2026-05-05" }, "aion-labs/aion-3.0-mini": { "cost": [ @@ -36045,7 +46796,9 @@ 0.18, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 32768, + "released": "2026-05-14" }, "aion-labs/aion-3.5": { "cost": [ @@ -36054,7 +46807,9 @@ 0.75, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "released": "2026-09-23" }, "aion-labs/aion-3.5-mini": { "cost": [ @@ -36063,7 +46818,9 @@ 0.18, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "released": "2026-09-23" }, "aion-labs/aion-rp-llama-3.1-8b": { "cost": [ @@ -36072,7 +46829,11 @@ 0.0, 0.0 ], - "limit": 32768 + "knowledge": "2023-12-31", + "limit": 32768, + "max_output": 29491, + "open": true, + "released": "2025-02-04" }, "amazon/nova-2-lite-v1": { "cost": [ @@ -36081,7 +46842,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-10", + "limit": 1000000, + "max_output": 65535, + "released": "2025-12-02" }, "amazon/nova-lite-v1": { "cost": [ @@ -36090,7 +46854,10 @@ 0.0, 0.0 ], - "limit": 300000 + "knowledge": "2024-10-31", + "limit": 300000, + "max_output": 5120, + "released": "2024-12-05" }, "amazon/nova-micro-v1": { "cost": [ @@ -36099,7 +46866,10 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-10-31", + "limit": 128000, + "max_output": 5120, + "released": "2024-12-05" }, "amazon/nova-premier-v1": { "cost": [ @@ -36108,7 +46878,10 @@ 0.625, 0.0 ], + "knowledge": "2024-10", "limit": 1000000, + "max_output": 32000, + "released": "2025-04-30", "status": "deprecated" }, "amazon/nova-pro-v1": { @@ -36118,7 +46891,10 @@ 0.0, 0.0 ], - "limit": 300000 + "knowledge": "2024-10-31", + "limit": 300000, + "max_output": 5120, + "released": "2024-12-05" }, "anthracite-org/magnum-v4-72b": { "cost": [ @@ -36127,7 +46903,11 @@ 0.0, 0.0 ], - "limit": 32768 + "knowledge": "2024-06-30", + "limit": 32768, + "max_output": 4096, + "open": true, + "released": "2024-10-22" }, "anthropic/claude-fable-5": { "cost": [ @@ -36136,7 +46916,10 @@ 1.0, 12.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-09" }, "anthropic/claude-fable-5.1": { "cost": [ @@ -36145,7 +46928,10 @@ 0.25, 12.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-01" }, "anthropic/claude-haiku-4.5": { "cost": [ @@ -36154,7 +46940,10 @@ 0.1, 1.25 ], - "limit": 200000 + "knowledge": "2025-02-28", + "limit": 200000, + "max_output": 64000, + "released": "2025-10-15" }, "anthropic/claude-haiku-5.5": { "cost": [ @@ -36163,7 +46952,10 @@ 0.01, 0.125 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-10-07" }, "anthropic/claude-opus-4.1": { "cost": [ @@ -36172,7 +46964,10 @@ 1.5, 18.75 ], - "limit": 200000 + "knowledge": "2025-03-31", + "limit": 200000, + "max_output": 32000, + "released": "2025-08-05" }, "anthropic/claude-opus-4.5": { "cost": [ @@ -36181,7 +46976,10 @@ 0.5, 6.25 ], - "limit": 200000 + "knowledge": "2025-05", + "limit": 200000, + "max_output": 64000, + "released": "2025-11-24" }, "anthropic/claude-opus-4.6": { "cost": [ @@ -36190,7 +46988,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2025-05-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-05" }, "anthropic/claude-opus-4.7": { "cost": [ @@ -36199,7 +47000,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-16" }, "anthropic/claude-opus-4.8": { "cost": [ @@ -36208,7 +47012,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-28" }, "anthropic/claude-opus-5": { "cost": [ @@ -36217,7 +47024,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-05", + "limit": 1000000, + "max_output": 128000, + "released": "2026-07-24" }, "anthropic/claude-opus-5.5": { "cost": [ @@ -36226,7 +47036,10 @@ 0.2, 5.0 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-22" }, "anthropic/claude-sonnet-4.5": { "cost": [ @@ -36235,7 +47048,10 @@ 0.3, 3.75 ], - "limit": 1000000 + "knowledge": "2025-07-31", + "limit": 1000000, + "max_output": 64000, + "released": "2025-09-29" }, "anthropic/claude-sonnet-4.6": { "cost": [ @@ -36244,7 +47060,10 @@ 0.3, 3.75 ], - "limit": 1000000 + "knowledge": "2025-08-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-17" }, "anthropic/claude-sonnet-5": { "cost": [ @@ -36253,7 +47072,10 @@ 0.2, 2.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-30" }, "anthropic/claude-sonnet-5.5": { "cost": [ @@ -36262,16 +47084,10 @@ 0.1, 2.5 ], - "limit": 1000000 - }, - "arcee-ai/trinity-large-thinking": { - "cost": [ - 0.25, - 0.8, - 0.06, - 0.0 - ], - "limit": 262144 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-28" }, "bytedance-seed/seed-1.6": { "cost": [ @@ -36281,6 +47097,8 @@ 0.0 ], "limit": 262144, + "max_output": 32768, + "released": "2025-10-15", "status": "deprecated" }, "bytedance-seed/seed-1.6-flash": { @@ -36291,6 +47109,8 @@ 0.0 ], "limit": 262144, + "max_output": 32768, + "released": "2025-08-28", "status": "deprecated" }, "bytedance-seed/seed-2-1-turbo": { @@ -36300,7 +47120,9 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 235929, + "released": "2026-06-23" }, "bytedance-seed/seed-2.0-code": { "cost": [ @@ -36310,6 +47132,8 @@ 0.0 ], "limit": 262144, + "max_output": 131072, + "released": "2026-02-14", "status": "deprecated" }, "bytedance-seed/seed-2.0-lite": { @@ -36319,7 +47143,9 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 131072, + "released": "2026-02-14" }, "bytedance-seed/seed-2.0-mini": { "cost": [ @@ -36328,7 +47154,9 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 131072, + "released": "2026-02-14" }, "bytedance/ui-tars-1.5-7b": { "cost": [ @@ -36337,7 +47165,9 @@ 0.1, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 2048, + "released": "2025-07-22" }, "cognitivecomputations/dolphin-mistral-24b-venice-edition": { "cost": [ @@ -36346,7 +47176,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-04-30", + "limit": 128000, + "max_output": 8192, + "open": true, + "released": "2025-07-09" }, "cohere/command-a": { "cost": [ @@ -36355,7 +47189,11 @@ 0.0, 0.0 ], - "limit": 256000 + "knowledge": "2024-08-31", + "limit": 256000, + "max_output": 8192, + "open": true, + "released": "2025-03-13" }, "cohere/command-a-plus": { "cost": [ @@ -36364,7 +47202,11 @@ 0.15, 0.0 ], - "limit": 192000 + "knowledge": "2025-04-01", + "limit": 192000, + "max_output": 64000, + "open": true, + "released": "2026-05-20" }, "cohere/command-r-08-2024": { "cost": [ @@ -36373,7 +47215,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-06-01", + "limit": 128000, + "max_output": 4000, + "open": true, + "released": "2024-08-30" }, "cohere/command-r-plus-08-2024": { "cost": [ @@ -36382,7 +47228,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-06-01", + "limit": 128000, + "max_output": 4000, + "open": true, + "released": "2024-08-30" }, "cohere/command-r7b-12-2024": { "cost": [ @@ -36391,7 +47241,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-06-01", + "limit": 128000, + "max_output": 4000, + "open": true, + "released": "2024-12-13" }, "cohere/north-mini-code:free": { "cost": [ @@ -36400,7 +47254,11 @@ 0.0, 0.0 ], - "limit": 256000 + "knowledge": "2025-09-23", + "limit": 256000, + "max_output": 64000, + "open": true, + "released": "2026-06-09" }, "deepseek/deepseek-chat": { "cost": [ @@ -36409,7 +47267,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2025-09", + "limit": 128000, + "max_output": 16000, + "open": true, + "released": "2025-12-01" }, "deepseek/deepseek-chat-v3-0324": { "cost": [ @@ -36418,7 +47280,11 @@ 0.11, 0.0 ], - "limit": 128000 + "knowledge": "2024-07-31", + "limit": 128000, + "max_output": 115200, + "open": true, + "released": "2025-03-24" }, "deepseek/deepseek-chat-v3.1": { "cost": [ @@ -36427,7 +47293,11 @@ 0.13, 0.0 ], - "limit": 163840 + "knowledge": "2025-03-31", + "limit": 163840, + "max_output": 32768, + "open": true, + "released": "2025-08-21" }, "deepseek/deepseek-r1-0528": { "cost": [ @@ -36436,7 +47306,10 @@ 0.35, 0.0 ], - "limit": 163840 + "limit": 163840, + "max_output": 32768, + "open": true, + "released": "2025-05-28" }, "deepseek/deepseek-v3.1-terminus": { "cost": [ @@ -36445,7 +47318,9 @@ 0.0, 0.0 ], - "limit": 163840 + "limit": 163840, + "max_output": 147456, + "released": "2025-09-22" }, "deepseek/deepseek-v3.2": { "cost": [ @@ -36454,7 +47329,11 @@ 0.028, 0.0 ], - "limit": 131072 + "knowledge": "2024-07", + "limit": 131072, + "max_output": 65536, + "open": true, + "released": "2025-12-01" }, "deepseek/deepseek-v3.2-exp": { "cost": [ @@ -36463,7 +47342,9 @@ 0.0, 0.0 ], - "limit": 163840 + "limit": 163840, + "max_output": 147456, + "released": "2025-09-29" }, "deepseek/deepseek-v4-flash": { "cost": [ @@ -36472,7 +47353,11 @@ 0.0182, 0.0 ], - "limit": 1048575 + "knowledge": "2025-05", + "limit": 1048575, + "max_output": 943717, + "open": true, + "released": "2026-04-24" }, "deepseek/deepseek-v4-flash-0731": { "cost": [ @@ -36481,7 +47366,11 @@ 0.028, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 943718, + "open": true, + "released": "2026-07-31" }, "deepseek/deepseek-v4-flash-vision-exp": { "cost": [ @@ -36490,7 +47379,10 @@ 0.00686, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 262144, + "open": true, + "released": "2026-08-21" }, "deepseek/deepseek-v4-pro": { "cost": [ @@ -36499,7 +47391,11 @@ 0.135, 0.0 ], - "limit": 1024000 + "knowledge": "2025-05", + "limit": 1024000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "deepseek/deepseek-v4-pro-0813": { "cost": [ @@ -36508,7 +47404,10 @@ 0.044, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 393216, + "open": true, + "released": "2026-08-13" }, "deepseek/deepseek-v4.1-flash": { "cost": [ @@ -36517,7 +47416,11 @@ 0.006, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-09-10" }, "deepseek/deepseek-v4.1-flash-1017": { "cost": [ @@ -36526,7 +47429,11 @@ 0.006, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 393216, + "open": true, + "released": "2026-10-17" }, "dots-studio/dots-3-note-preview:free": { "cost": [ @@ -36535,7 +47442,9 @@ 0.0, 0.0 ], - "limit": 512000 + "limit": 512000, + "max_output": 460800, + "released": "2026-08-14" }, "elorian/glimpse": { "cost": [ @@ -36544,7 +47453,9 @@ 0.06, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 256000, + "released": "2026-10-17" }, "fireworks/ember-1": { "cost": [ @@ -36553,7 +47464,9 @@ 0.3, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 943718, + "released": "2026-09-22" }, "google/gemini-2.5-flash": { "cost": [ @@ -36562,7 +47475,10 @@ 0.015, 0.041667 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65535, + "released": "2025-06-17", "status": "deprecated" }, "google/gemini-2.5-flash-image": { @@ -36572,7 +47488,11 @@ 0.03, 0.083333 ], - "limit": 32768 + "knowledge": "2024-06", + "limit": 32768, + "max_output": 8192, + "released": "2025-08-26", + "type": "image" }, "google/gemini-2.5-flash-lite": { "cost": [ @@ -36581,7 +47501,10 @@ 0.005, 0.041667 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65535, + "released": "2025-06-17", "status": "deprecated" }, "google/gemini-2.5-pro": { @@ -36591,7 +47514,10 @@ 0.0625, 0.1875 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2025-06-17", "status": "deprecated" }, "google/gemini-2.5-pro-preview": { @@ -36601,7 +47527,10 @@ 0.0625, 0.1875 ], - "limit": 1048576 + "knowledge": "2025-01-31", + "limit": 1048576, + "max_output": 65536, + "released": "2025-06-05" }, "google/gemini-3-flash-preview": { "cost": [ @@ -36610,7 +47539,10 @@ 0.025, 0.041667 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2025-12-17" }, "google/gemini-3-pro-image": { "cost": [ @@ -36619,7 +47551,11 @@ 0.2, 0.375 ], - "limit": 65536 + "knowledge": "2025-01", + "limit": 65536, + "max_output": 32768, + "released": "2026-05-28", + "type": "image" }, "google/gemini-3-pro-image-preview": { "cost": [ @@ -36628,7 +47564,11 @@ 0.1, 0.1875 ], - "limit": 65536 + "knowledge": "2025-01", + "limit": 65536, + "max_output": 32768, + "released": "2025-11-20", + "type": "image" }, "google/gemini-3.1-flash-image": { "cost": [ @@ -36637,7 +47577,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2025-01", + "limit": 131072, + "max_output": 32768, + "released": "2026-05-28", + "type": "image" }, "google/gemini-3.1-flash-image-preview": { "cost": [ @@ -36646,7 +47590,11 @@ 0.0, 0.0 ], - "limit": 65536 + "knowledge": "2025-01", + "limit": 65536, + "max_output": 58982, + "released": "2026-02-26", + "type": "image" }, "google/gemini-3.1-flash-lite": { "cost": [ @@ -36655,7 +47603,10 @@ 0.0125, 0.041667 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-05-07" }, "google/gemini-3.1-flash-lite-image": { "cost": [ @@ -36664,7 +47615,11 @@ 0.0, 0.0 ], - "limit": 65536 + "knowledge": "2025-01", + "limit": 65536, + "max_output": 58982, + "released": "2026-06-30", + "type": "image" }, "google/gemini-3.1-flash-lite-preview": { "cost": [ @@ -36673,7 +47628,10 @@ 0.0125, 0.041667 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-03-03" }, "google/gemini-3.1-pro-preview": { "cost": [ @@ -36682,7 +47640,10 @@ 0.1, 0.1875 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-02-19" }, "google/gemini-3.1-pro-preview-customtools": { "cost": [ @@ -36691,7 +47652,10 @@ 0.2, 0.375 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-02-19" }, "google/gemini-3.5-flash": { "cost": [ @@ -36700,7 +47664,10 @@ 0.075, 0.041667 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-05-19" }, "google/gemini-3.5-flash-lite": { "cost": [ @@ -36709,7 +47676,10 @@ 0.015, 0.041667 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-07-21" }, "google/gemini-3.6-flash": { "cost": [ @@ -36718,7 +47688,10 @@ 0.0375, 0.020833 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-07-21" }, "google/gemini-3.7-flash": { "cost": [ @@ -36727,7 +47700,10 @@ 0.075, 0.041667 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-08-13" }, "google/gemini-3.8-flash": { "cost": [ @@ -36736,7 +47712,9 @@ 0.075, 0.041667 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65536, + "released": "2026-09-02" }, "google/gemini-4-argon": { "cost": [ @@ -36745,7 +47723,10 @@ 0.1, 0.1875 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 943718, + "released": "2026-10-13" }, "google/gemini-nano-banana-2.1": { "cost": [ @@ -36754,7 +47735,10 @@ 0.0, 0.0 ], - "limit": 65536 + "limit": 65536, + "max_output": 58982, + "released": "2026-10-06", + "type": "image" }, "google/gemma-2-27b-it": { "cost": [ @@ -36763,7 +47747,11 @@ 0.0, 0.0 ], - "limit": 8192 + "knowledge": "2024-06-30", + "limit": 8192, + "max_output": 2048, + "open": true, + "released": "2024-07-13" }, "google/gemma-3-12b-it": { "cost": [ @@ -36772,7 +47760,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-08", + "limit": 131072, + "max_output": 16384, + "open": true, + "released": "2025-03-12" }, "google/gemma-3-27b-it": { "cost": [ @@ -36781,7 +47773,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-08", + "limit": 131072, + "max_output": 117964, + "open": true, + "released": "2025-03-12" }, "google/gemma-3-4b-it": { "cost": [ @@ -36790,7 +47786,11 @@ 0.02, 0.0 ], - "limit": 131072 + "knowledge": "2024-08", + "limit": 131072, + "max_output": 16384, + "open": true, + "released": "2025-03-12" }, "google/gemma-4-26b-a4b-it": { "cost": [ @@ -36799,7 +47799,10 @@ 0.021, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 235929, + "open": true, + "released": "2026-04-02" }, "google/gemma-4-31b-it": { "cost": [ @@ -36808,7 +47811,11 @@ 0.1, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 16384, + "open": true, + "released": "2026-04-02" }, "google/lyria-3-clip-preview": { "cost": [ @@ -36817,7 +47824,9 @@ 0.0, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65536, + "released": "2026-03-25" }, "google/lyria-3-pro-preview": { "cost": [ @@ -36826,7 +47835,9 @@ 0.0, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65536, + "released": "2026-03-25" }, "gryphe/mythomax-l2-13b": { "cost": [ @@ -36835,25 +47846,22 @@ 0.0, 0.0 ], - "limit": 4096 - }, - "ibm-granite/granite-4.0-h-micro": { - "cost": [ - 0.017, - 0.112, - 0.0, - 0.0 - ], - "limit": 131000 + "limit": 4096, + "max_output": 3686, + "open": true, + "released": "2023-08-10" }, "ibm-granite/granite-4.2-8b": { "cost": [ 0.06, - 0.25, + 0.15, 0.015, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 117964, + "open": true, + "released": "2026-08-25" }, "inception/mercury-2": { "cost": [ @@ -36862,7 +47870,9 @@ 0.025, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 50000, + "released": "2026-02-24" }, "inception/mercury-2.5": { "cost": [ @@ -36871,7 +47881,9 @@ 0.02, 0.0 ], - "limit": 260000 + "limit": 260000, + "max_output": 65536, + "released": "2026-09-08" }, "inception/mercury-3": { "cost": [ @@ -36880,7 +47892,9 @@ 0.02, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-10-16" }, "inclusionai/ling-3.0-flash": { "cost": [ @@ -36889,7 +47903,10 @@ 0.012, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-07-23" }, "inclusionai/ling-3.0-flash-vl": { "cost": [ @@ -36898,7 +47915,10 @@ 0.012, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2026-09-10" }, "inclusionai/ling-3.1-flash": { "cost": [ @@ -36907,7 +47927,10 @@ 0.06, 0.0 ], - "limit": 262144 + "limit": 1000000, + "max_output": 262144, + "open": true, + "released": "2026-09-29" }, "inference-net/schematron-v2-small": { "cost": [ @@ -36916,7 +47939,9 @@ 0.05, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 4096, + "released": "2026-04-16" }, "inference-net/schematron-v2-turbo": { "cost": [ @@ -36925,7 +47950,9 @@ 0.03, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 8192, + "released": "2026-04-16" }, "kilo-auto/balanced": { "cost": [ @@ -36934,7 +47961,10 @@ 0.0325, 0.40625 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 65536, + "reasoning": 0.0, + "released": "1970-01-01" }, "kilo-auto/efficient": { "cost": [ @@ -36943,7 +47973,10 @@ 0.0325, 0.40625 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 65536, + "reasoning": 0.0, + "released": "1970-01-01" }, "kilo-auto/free": { "cost": [ @@ -36952,7 +47985,9 @@ 0.0, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 32768, + "released": "1970-01-01" }, "kilo-auto/frontier": { "cost": [ @@ -36961,7 +47996,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 128000, + "reasoning": 0.0, + "released": "1970-01-01" }, "kilo-auto/small": { "cost": [ @@ -36970,7 +48008,21 @@ 0.005, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "reasoning": 0.0, + "released": "1970-01-01" + }, + "liquid/lfm-2.5-2.6b": { + "cost": [ + 0.35, + 0.5, + 0.04, + 0.0 + ], + "limit": 128000, + "max_output": 8192, + "released": "2026-08-11" }, "liquid/lfm-2.5-2.6b:free": { "cost": [ @@ -36979,7 +48031,9 @@ 0.0, 0.0 ], - "limit": 65536 + "limit": 65536, + "max_output": 8192, + "released": "2026-08-11" }, "liquid/lfm-2.5-24b-a2b": { "cost": [ @@ -36988,7 +48042,9 @@ 0.025, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 8192, + "released": "2026-10-13" }, "mancer/weaver": { "cost": [ @@ -36997,7 +48053,10 @@ 0.0, 0.0 ], - "limit": 8000 + "knowledge": "2023-06-30", + "limit": 8000, + "max_output": 6000, + "released": "2023-08-02" }, "meituan/longcat-2.0": { "cost": [ @@ -37006,7 +48065,10 @@ 0.015, 0.0 ], - "limit": 1048756 + "limit": 1048756, + "max_output": 262144, + "open": true, + "released": "2026-06-30" }, "meta-llama/llama-3.1-70b-instruct": { "cost": [ @@ -37015,7 +48077,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2023-12", + "limit": 131072, + "max_output": 16384, + "open": true, + "released": "2024-07-23" }, "meta-llama/llama-3.1-8b-instruct": { "cost": [ @@ -37024,7 +48090,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2023-12", + "limit": 131072, + "max_output": 16384, + "open": true, + "released": "2024-07-23" }, "meta-llama/llama-3.2-1b-instruct": { "cost": [ @@ -37033,7 +48103,11 @@ 0.0, 0.0 ], - "limit": 60000 + "knowledge": "2023-12", + "limit": 60000, + "max_output": 54000, + "open": true, + "released": "2024-09-25" }, "meta-llama/llama-3.2-3b-instruct": { "cost": [ @@ -37042,7 +48116,11 @@ 0.0, 0.0 ], - "limit": 80000 + "knowledge": "2023-12", + "limit": 131072, + "max_output": 117964, + "open": true, + "released": "2024-09-25" }, "meta-llama/llama-3.3-70b-instruct": { "cost": [ @@ -37051,7 +48129,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2023-12", + "limit": 131072, + "max_output": 16384, + "open": true, + "released": "2024-12-06" }, "meta-llama/llama-4-maverick": { "cost": [ @@ -37060,7 +48142,11 @@ 0.05, 0.0 ], - "limit": 128000 + "knowledge": "2024-08", + "limit": 128000, + "max_output": 16384, + "open": true, + "released": "2025-04-05" }, "meta-llama/llama-4-scout": { "cost": [ @@ -37069,7 +48155,11 @@ 0.0, 0.0 ], - "limit": 327680 + "knowledge": "2024-08", + "limit": 327680, + "max_output": 16384, + "open": true, + "released": "2025-04-05" }, "meta-llama/llama-guard-4-12b": { "cost": [ @@ -37078,7 +48168,10 @@ 0.0, 0.0 ], - "limit": 163840 + "limit": 163840, + "max_output": 16384, + "open": true, + "released": "2025-04-29" }, "meta/muse-glimmer-30b": { "cost": [ @@ -37087,7 +48180,11 @@ 0.04, 0.0 ], - "limit": 131072 + "knowledge": "2026-01-04", + "limit": 131072, + "max_output": 16384, + "open": true, + "released": "2026-08-10" }, "meta/muse-spark-1.1": { "cost": [ @@ -37096,7 +48193,9 @@ 0.15, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 943718, + "released": "2026-04-08" }, "meta/muse-spark-1.2": { "cost": [ @@ -37105,7 +48204,9 @@ 0.15, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 943718, + "released": "2026-08-05" }, "meta/muse-spark-1.2-contributor": { "cost": [ @@ -37114,7 +48215,9 @@ 0.002, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 943718, + "released": "2026-08-21" }, "meta/muse-spark-1.3": { "cost": [ @@ -37123,7 +48226,9 @@ 0.15, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 943718, + "released": "2026-09-02" }, "meta/muse-spark-1.3-contributor": { "cost": [ @@ -37132,7 +48237,9 @@ 0.002, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 943718, + "released": "2026-09-02" }, "meta/muse-spark-open": { "cost": [ @@ -37141,7 +48248,11 @@ 0.15, 0.0 ], - "limit": 1048576 + "knowledge": "2026-01-04", + "limit": 1048576, + "max_output": 943718, + "open": true, + "released": "2026-10-15" }, "meta/muse-wonder": { "cost": [ @@ -37150,7 +48261,9 @@ 0.2, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 943718, + "released": "2026-10-12" }, "microsoft/phi-4": { "cost": [ @@ -37159,7 +48272,9 @@ 0.0, 0.0 ], - "limit": 16384 + "limit": 16384, + "max_output": 14745, + "released": "2025-01-10" }, "minimax/minimax-01": { "cost": [ @@ -37168,25 +48283,32 @@ 0.0, 0.0 ], - "limit": 1000192 + "limit": 1000192, + "max_output": 900172, + "released": "2025-01-15" }, "minimax/minimax-m1": { "cost": [ - 0.4, + 0.55, 2.2, 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 40000, + "released": "2025-06-17" }, "minimax/minimax-m2": { "cost": [ - 0.3, - 1.2, + 0.255, + 1.02, 0.0, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-10-27" }, "minimax/minimax-m2-her": { "cost": [ @@ -37195,7 +48317,9 @@ 0.03, 0.0 ], - "limit": 65536 + "limit": 65536, + "max_output": 2048, + "released": "2026-01-23" }, "minimax/minimax-m2.1": { "cost": [ @@ -37204,16 +48328,22 @@ 0.03, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-12-23" }, "minimax/minimax-m2.5": { "cost": [ - 0.27, - 0.95, + 0.3, + 1.2, 0.03, 0.0 ], - "limit": 198000 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-02-12" }, "minimax/minimax-m2.7": { "cost": [ @@ -37222,25 +48352,33 @@ 0.06, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-03-18" }, "minimax/minimax-m3": { "cost": [ - 0.224, - 0.88, - 0.0448, + 0.3, + 1.2, + 0.06, 0.0 ], - "limit": 524288 + "limit": 524288, + "max_output": 512000, + "open": true, + "released": "2026-06-01" }, "minimax/minimax-m3.1-flash": { "cost": [ - 0.1, - 0.55, - 0.01, + 0.15, + 0.6, + 0.015, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 524288, + "released": "2026-10-19" }, "mistralai/codestral-2508": { "cost": [ @@ -37249,7 +48387,9 @@ 0.03, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 204800, + "released": "2025-07-30" }, "mistralai/devstral-2512": { "cost": [ @@ -37258,7 +48398,11 @@ 0.04, 0.0 ], - "limit": 262144 + "knowledge": "2025-12", + "limit": 262144, + "max_output": 209715, + "open": true, + "released": "2025-12-09" }, "mistralai/ministral-14b-2512": { "cost": [ @@ -37267,7 +48411,10 @@ 0.02, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 209715, + "open": true, + "released": "2025-12-02" }, "mistralai/ministral-3b-2512": { "cost": [ @@ -37276,7 +48423,10 @@ 0.01, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 104857, + "open": true, + "released": "2025-12-02" }, "mistralai/ministral-8b-2512": { "cost": [ @@ -37285,7 +48435,10 @@ 0.015, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 209715, + "open": true, + "released": "2025-12-02" }, "mistralai/mistral-large": { "cost": [ @@ -37294,7 +48447,10 @@ 0.2, 0.0 ], - "limit": 128000 + "knowledge": "2024-11-30", + "limit": 128000, + "max_output": 102400, + "released": "2024-02-26" }, "mistralai/mistral-large-2407": { "cost": [ @@ -37303,7 +48459,11 @@ 0.2, 0.0 ], - "limit": 131072 + "knowledge": "2024-03-31", + "limit": 131072, + "max_output": 104857, + "open": true, + "released": "2024-07-24" }, "mistralai/mistral-large-2512": { "cost": [ @@ -37312,7 +48472,11 @@ 0.05, 0.0 ], - "limit": 262144 + "knowledge": "2024-11", + "limit": 262144, + "max_output": 209715, + "open": true, + "released": "2025-12-02" }, "mistralai/mistral-large-4-0": { "cost": [ @@ -37321,7 +48485,9 @@ 0.14, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 262144, + "released": "2026-10-06" }, "mistralai/mistral-medium-3": { "cost": [ @@ -37330,7 +48496,10 @@ 0.04, 0.0 ], - "limit": 131072 + "knowledge": "2025-03-31", + "limit": 131072, + "max_output": 104857, + "released": "2025-05-07" }, "mistralai/mistral-medium-3-5": { "cost": [ @@ -37339,7 +48508,9 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 209715, + "released": "2026-04-30" }, "mistralai/mistral-medium-3.1": { "cost": [ @@ -37348,7 +48519,10 @@ 0.04, 0.0 ], - "limit": 131072 + "knowledge": "2025-06-30", + "limit": 131072, + "max_output": 104857, + "released": "2025-08-12" }, "mistralai/mistral-nemo": { "cost": [ @@ -37357,7 +48531,11 @@ 0.015, 0.0 ], - "limit": 131072 + "knowledge": "2024-07", + "limit": 131072, + "max_output": 16384, + "open": true, + "released": "2024-07-18" }, "mistralai/mistral-saba": { "cost": [ @@ -37366,7 +48544,10 @@ 0.02, 0.0 ], - "limit": 32768 + "knowledge": "2024-09-30", + "limit": 32768, + "max_output": 26214, + "released": "2025-02-17" }, "mistralai/mistral-small-24b-instruct-2501": { "cost": [ @@ -37375,7 +48556,11 @@ 0.0, 0.0 ], - "limit": 32768 + "knowledge": "2023-10-31", + "limit": 32768, + "max_output": 16384, + "open": true, + "released": "2025-01-30" }, "mistralai/mistral-small-2603": { "cost": [ @@ -37384,7 +48569,11 @@ 0.015, 0.0 ], - "limit": 262144 + "knowledge": "2025-06", + "limit": 262144, + "max_output": 209715, + "open": true, + "released": "2026-03-16" }, "mistralai/mistral-small-3.1-24b-instruct": { "cost": [ @@ -37393,7 +48582,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2023-10-31", + "limit": 128000, + "max_output": 102400, + "open": true, + "released": "2025-03-17" }, "mistralai/mistral-small-3.2-24b-instruct": { "cost": [ @@ -37402,7 +48595,11 @@ 0.01, 0.0 ], - "limit": 128000 + "knowledge": "2023-10-31", + "limit": 128000, + "max_output": 16384, + "open": true, + "released": "2025-06-20" }, "mistralai/mixtral-8x22b-instruct": { "cost": [ @@ -37411,7 +48608,11 @@ 0.2, 0.0 ], - "limit": 65536 + "knowledge": "2024-01-31", + "limit": 65536, + "max_output": 52428, + "open": true, + "released": "2024-04-17" }, "mistralai/voxtral-small-24b-2507": { "cost": [ @@ -37420,7 +48621,10 @@ 0.01, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 26214, + "open": true, + "released": "2025-07-15" }, "moondream/moondream3-preview": { "cost": [ @@ -37429,7 +48633,9 @@ 0.0, 0.0 ], - "limit": 32000 + "limit": 32000, + "max_output": 4096, + "released": "2026-10-15" }, "moondream/moondream3.1-9b-a2b": { "cost": [ @@ -37438,7 +48644,9 @@ 0.0, 0.0 ], - "limit": 32000 + "limit": 32000, + "max_output": 4096, + "released": "2026-10-15" }, "moonshotai/kimi-k2": { "cost": [ @@ -37447,7 +48655,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-12-31", + "limit": 131072, + "max_output": 98304, + "open": true, + "released": "2025-07-11" }, "moonshotai/kimi-k2-0905": { "cost": [ @@ -37456,7 +48668,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 98304, + "open": true, + "released": "2025-09-05" }, "moonshotai/kimi-k2-thinking": { "cost": [ @@ -37465,7 +48680,11 @@ 0.15, 0.0 ], - "limit": 262144 + "knowledge": "2024-08", + "limit": 262144, + "max_output": 98304, + "open": true, + "released": "2025-11-06" }, "moonshotai/kimi-k2.5": { "cost": [ @@ -37474,7 +48693,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 235929, + "open": true, + "released": "2026-01-27" }, "moonshotai/kimi-k2.6": { "cost": [ @@ -37483,16 +48706,24 @@ 0.15, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 235929, + "open": true, + "released": "2026-04-20" }, "moonshotai/kimi-k2.7-code": { "cost": [ - 0.6712, - 3.35, + 0.56, + 3.1, 0.15, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 235929, + "open": true, + "released": "2026-06-12" }, "moonshotai/kimi-k3": { "cost": [ @@ -37501,7 +48732,21 @@ 0.3, 3.75 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 943718, + "open": true, + "released": "2026-07-16" + }, + "moonshotai/kimi-k3.1-pro": { + "cost": [ + 2.0, + 10.0, + 0.2, + 0.0 + ], + "limit": 1048576, + "max_output": 943718, + "released": "2026-10-23" }, "morph/morph-v3-fast": { "cost": [ @@ -37510,7 +48755,9 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 131072, + "released": "2025-07-07" }, "morph/morph-v3-large": { "cost": [ @@ -37519,7 +48766,9 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 131072, + "released": "2025-07-07" }, "nex-agi/nex-n2.5-mini": { "cost": [ @@ -37528,7 +48777,9 @@ 0.0025, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 235929, + "released": "2026-09-08" }, "nex-agi/nex-n2.5-pro": { "cost": [ @@ -37537,7 +48788,9 @@ 0.015, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 235929, + "released": "2026-09-08" }, "nousresearch/hermes-3-llama-3.1-405b": { "cost": [ @@ -37546,7 +48799,11 @@ 0.0, 0.0 ], + "knowledge": "2023-12-31", "limit": 131072, + "max_output": 16384, + "open": true, + "released": "2024-08-16", "status": "deprecated" }, "nousresearch/hermes-3-llama-3.1-70b": { @@ -37556,17 +48813,25 @@ 0.0, 0.0 ], + "knowledge": "2023-12-31", "limit": 131072, + "max_output": 16384, + "open": true, + "released": "2024-08-18", "status": "deprecated" }, "nousresearch/hermes-4-405b": { "cost": [ 1.0, 3.0, - 0.0, + 0.2, 0.0 ], - "limit": 131072 + "knowledge": "2024-08-31", + "limit": 131072, + "max_output": 117964, + "open": true, + "released": "2025-08-26" }, "nvidia/nemotron-3-nano-30b-a3b": { "cost": [ @@ -37575,7 +48840,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-06-25", + "limit": 262144, + "max_output": 235929, + "open": true, + "released": "2025-12-15" }, "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free": { "cost": [ @@ -37584,7 +48853,10 @@ 0.0, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 65536, + "open": true, + "released": "2026-04-28" }, "nvidia/nemotron-3-super-120b-a12b": { "cost": [ @@ -37593,16 +48865,11 @@ 0.0, 0.0 ], - "limit": 262144 - }, - "nvidia/nemotron-3-super-120b-a12b:free": { - "cost": [ - 0.0, - 0.0, - 0.0, - 0.0 - ], - "limit": 262144 + "knowledge": "2025-06", + "limit": 262144, + "max_output": 235929, + "open": true, + "released": "2026-03-11" }, "nvidia/nemotron-3-ultra-550b-a55b": { "cost": [ @@ -37611,7 +48878,11 @@ 0.08, 0.0 ], - "limit": 202800 + "knowledge": "2025-09", + "limit": 202800, + "max_output": 182520, + "open": true, + "released": "2026-06-04" }, "nvidia/nemotron-3-ultra-550b-a55b:free": { "cost": [ @@ -37620,7 +48891,11 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-09", + "limit": 1000000, + "max_output": 65536, + "open": true, + "released": "2026-06-04" }, "nvidia/nemotron-3.5-content-safety": { "cost": [ @@ -37629,7 +48904,10 @@ 0.0, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 117964, + "open": true, + "released": "2026-06-02" }, "nvidia/nemotron-3.5-content-safety:free": { "cost": [ @@ -37638,7 +48916,10 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 8192, + "open": true, + "released": "2026-06-02" }, "nvidia/nemotron-3.5-lightning": { "cost": [ @@ -37647,7 +48928,11 @@ 0.0125, 0.0 ], - "limit": 262144 + "knowledge": "2025-09", + "limit": 262144, + "max_output": 235929, + "open": true, + "released": "2026-08-11" }, "nvidia/nemotron-3.5-lightning:free": { "cost": [ @@ -37656,16 +48941,23 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-09", + "limit": 1000000, + "max_output": 65536, + "open": true, + "released": "2026-08-11" }, "nvidia/nemotron-3.5-super-vl": { "cost": [ - 0.1, - 0.4, - 0.08, + 0.06, + 0.35, + 0.01, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 235929, + "open": true, + "released": "2026-10-15" }, "nvidia/nemotron-3.5-super-vl:free": { "cost": [ @@ -37674,16 +48966,10 @@ 0.0, 0.0 ], - "limit": 1000000 - }, - "openai/gpt-3.5-turbo": { - "cost": [ - 0.5, - 1.5, - 0.0, - 0.0 - ], - "limit": 16385 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-10-15" }, "openai/gpt-3.5-turbo-0613": { "cost": [ @@ -37692,7 +48978,9 @@ 0.0, 0.0 ], - "limit": 4095 + "limit": 4095, + "max_output": 3685, + "released": "2024-01-25" }, "openai/gpt-3.5-turbo-16k": { "cost": [ @@ -37701,16 +48989,9 @@ 0.0, 0.0 ], - "limit": 16385 - }, - "openai/gpt-3.5-turbo-instruct": { - "cost": [ - 1.5, - 2.0, - 0.0, - 0.0 - ], - "limit": 4095 + "limit": 16385, + "max_output": 4096, + "released": "2023-08-28" }, "openai/gpt-4": { "cost": [ @@ -37719,16 +49000,10 @@ 0.0, 0.0 ], - "limit": 8191 - }, - "openai/gpt-4-turbo": { - "cost": [ - 10.0, - 30.0, - 0.0, - 0.0 - ], - "limit": 128000 + "knowledge": "2023-11", + "limit": 8191, + "max_output": 4096, + "released": "2023-11-06" }, "openai/gpt-4.1": { "cost": [ @@ -37737,7 +49012,10 @@ 0.5, 0.0 ], - "limit": 1047576 + "knowledge": "2024-04", + "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14" }, "openai/gpt-4.1-mini": { "cost": [ @@ -37746,16 +49024,22 @@ 0.1, 0.0 ], - "limit": 1047576 + "knowledge": "2024-04", + "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14" }, "openai/gpt-4.1-nano": { "cost": [ 0.1, 0.4, - 0.025, + 0.03, 0.0 ], - "limit": 1047576 + "knowledge": "2024-04", + "limit": 1047576, + "max_output": 942818, + "released": "2025-04-14" }, "openai/gpt-4o": { "cost": [ @@ -37764,7 +49048,10 @@ 1.25, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-05-13" }, "openai/gpt-4o-2024-05-13": { "cost": [ @@ -37773,7 +49060,10 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 4096, + "released": "2024-05-13" }, "openai/gpt-4o-2024-08-06": { "cost": [ @@ -37782,7 +49072,10 @@ 1.25, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-08-06" }, "openai/gpt-4o-2024-11-20": { "cost": [ @@ -37791,7 +49084,10 @@ 1.25, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-11-20" }, "openai/gpt-4o-mini": { "cost": [ @@ -37800,7 +49096,10 @@ 0.075, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-07-18" }, "openai/gpt-4o-mini-2024-07-18": { "cost": [ @@ -37809,7 +49108,10 @@ 0.075, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-07-18" }, "openai/gpt-5": { "cost": [ @@ -37818,7 +49120,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "openai/gpt-5-image": { "cost": [ @@ -37827,7 +49132,11 @@ 1.25, 0.0 ], - "limit": 400000 + "knowledge": "2024-10-01", + "limit": 400000, + "max_output": 128000, + "released": "2025-10-14", + "type": "image" }, "openai/gpt-5-image-mini": { "cost": [ @@ -37836,7 +49145,10 @@ 0.25, 0.0 ], - "limit": 400000 + "limit": 400000, + "max_output": 128000, + "released": "2025-10-16", + "type": "image" }, "openai/gpt-5-mini": { "cost": [ @@ -37845,7 +49157,10 @@ 0.025, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "openai/gpt-5-nano": { "cost": [ @@ -37854,7 +49169,10 @@ 0.005, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "openai/gpt-5-pro": { "cost": [ @@ -37863,7 +49181,10 @@ 0.0, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-10-06" }, "openai/gpt-5.1": { "cost": [ @@ -37872,7 +49193,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "openai/gpt-5.1-codex": { "cost": [ @@ -37881,7 +49205,10 @@ 0.13, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "openai/gpt-5.1-codex-max": { "cost": [ @@ -37890,7 +49217,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "openai/gpt-5.1-codex-mini": { "cost": [ @@ -37899,7 +49229,10 @@ 0.03, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "openai/gpt-5.2": { "cost": [ @@ -37908,7 +49241,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "openai/gpt-5.2-chat": { "cost": [ @@ -37917,7 +49253,10 @@ 0.175, 0.0 ], - "limit": 128000 + "knowledge": "2025-08-31", + "limit": 128000, + "max_output": 32000, + "released": "2025-12-11" }, "openai/gpt-5.2-codex": { "cost": [ @@ -37926,7 +49265,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "openai/gpt-5.2-pro": { "cost": [ @@ -37935,7 +49277,10 @@ 0.0, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "openai/gpt-5.3-codex": { "cost": [ @@ -37944,7 +49289,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-02-05" }, "openai/gpt-5.4": { "cost": [ @@ -37953,7 +49301,10 @@ 0.25, 0.0 ], - "limit": 1050000 + "knowledge": "2025-08-31", + "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05" }, "openai/gpt-5.4-image-2": { "cost": [ @@ -37962,7 +49313,10 @@ 2.0, 0.0 ], - "limit": 272000 + "limit": 272000, + "max_output": 128000, + "released": "2026-04-21", + "type": "image" }, "openai/gpt-5.4-mini": { "cost": [ @@ -37971,7 +49325,10 @@ 0.075, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "openai/gpt-5.4-nano": { "cost": [ @@ -37980,7 +49337,10 @@ 0.02, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "openai/gpt-5.4-pro": { "cost": [ @@ -37989,7 +49349,10 @@ 0.0, 0.0 ], - "limit": 1050000 + "knowledge": "2025-08-31", + "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05" }, "openai/gpt-5.5": { "cost": [ @@ -37998,7 +49361,10 @@ 0.5, 0.0 ], - "limit": 1050000 + "knowledge": "2025-12-01", + "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23" }, "openai/gpt-5.5-pro": { "cost": [ @@ -38007,7 +49373,10 @@ 0.0, 0.0 ], - "limit": 1050000 + "knowledge": "2025-12-01", + "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23" }, "openai/gpt-5.6-luna": { "cost": [ @@ -38016,7 +49385,10 @@ 0.02, 0.25 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "openai/gpt-5.6-luna-pro": { "cost": [ @@ -38025,7 +49397,10 @@ 0.02, 0.25 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "openai/gpt-5.6-sol": { "cost": [ @@ -38034,7 +49409,10 @@ 0.4, 5.0 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "openai/gpt-5.6-sol-pro": { "cost": [ @@ -38043,7 +49421,10 @@ 0.4, 5.0 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "openai/gpt-5.6-terra": { "cost": [ @@ -38052,7 +49433,10 @@ 0.2, 2.5 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "openai/gpt-5.6-terra-pro": { "cost": [ @@ -38061,7 +49445,10 @@ 0.2, 2.5 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "openai/gpt-6-astra": { "cost": [ @@ -38070,7 +49457,10 @@ 1.0, 12.5 ], - "limit": 1050000 + "knowledge": "2026-04-30", + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-04" }, "openai/gpt-6-astra-pro": { "cost": [ @@ -38079,7 +49469,9 @@ 1.0, 12.5 ], - "limit": 1050000 + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-04" }, "openai/gpt-6-luna": { "cost": [ @@ -38088,7 +49480,10 @@ 0.01, 0.125 ], - "limit": 1050000 + "knowledge": "2026-05-18", + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22" }, "openai/gpt-6-luna-pro": { "cost": [ @@ -38097,7 +49492,9 @@ 0.01, 0.125 ], - "limit": 1050000 + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22" }, "openai/gpt-6-sol": { "cost": [ @@ -38106,7 +49503,10 @@ 0.2, 2.5 ], - "limit": 1050000 + "knowledge": "2026-04-20", + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22" }, "openai/gpt-6-sol-pro": { "cost": [ @@ -38115,7 +49515,9 @@ 0.2, 2.5 ], - "limit": 1050000 + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22" }, "openai/gpt-6.1-sol": { "cost": [ @@ -38124,7 +49526,10 @@ 0.1, 2.5 ], - "limit": 1050000 + "knowledge": "2026-04-30", + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-29" }, "openai/gpt-6.1-sol-pro": { "cost": [ @@ -38133,7 +49538,32 @@ 0.1, 2.5 ], - "limit": 1050000 + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-29" + }, + "openai/gpt-6.1-terra": { + "cost": [ + 1.0, + 5.0, + 0.05, + 1.25 + ], + "knowledge": "2026-06-01", + "limit": 1050000, + "max_output": 128000, + "released": "2026-10-26" + }, + "openai/gpt-6.1-terra-pro": { + "cost": [ + 1.0, + 5.0, + 0.05, + 1.25 + ], + "limit": 1050000, + "max_output": 128000, + "released": "2026-10-26" }, "openai/gpt-audio": { "cost": [ @@ -38142,7 +49572,10 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2023-10-01", + "limit": 128000, + "max_output": 16384, + "released": "2025-08-28" }, "openai/gpt-audio-mini": { "cost": [ @@ -38151,7 +49584,10 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2023-10-01", + "limit": 128000, + "max_output": 16384, + "released": "2025-10-06" }, "openai/gpt-chat-latest": { "cost": [ @@ -38160,7 +49596,9 @@ 0.5, 0.0 ], - "limit": 400000 + "limit": 400000, + "max_output": 128000, + "released": "2026-05-05" }, "openai/gpt-oss-120b": { "cost": [ @@ -38169,7 +49607,11 @@ 0.015, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 65536, + "open": true, + "released": "2025-08-05" }, "openai/gpt-oss-20b": { "cost": [ @@ -38178,7 +49620,11 @@ 0.009, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "openai/gpt-oss-safeguard-20b": { "cost": [ @@ -38187,25 +49633,10 @@ 0.0375, 0.0 ], - "limit": 131072 - }, - "openai/o1": { - "cost": [ - 15.0, - 60.0, - 7.5, - 0.0 - ], - "limit": 200000 - }, - "openai/o1-pro": { - "cost": [ - 150.0, - 600.0, - 0.0, - 0.0 - ], - "limit": 200000 + "limit": 131072, + "max_output": 65536, + "open": true, + "released": "2025-10-29" }, "openai/o3": { "cost": [ @@ -38214,25 +49645,10 @@ 0.5, 0.0 ], - "limit": 200000 - }, - "openai/o3-mini": { - "cost": [ - 1.1, - 4.4, - 0.55, - 0.0 - ], - "limit": 200000 - }, - "openai/o3-mini-high": { - "cost": [ - 1.1, - 4.4, - 0.55, - 0.0 - ], - "limit": 200000 + "knowledge": "2024-05", + "limit": 200000, + "max_output": 100000, + "released": "2025-04-16" }, "openai/o3-pro": { "cost": [ @@ -38241,25 +49657,10 @@ 0.0, 0.0 ], - "limit": 200000 - }, - "openai/o4-mini": { - "cost": [ - 1.1, - 4.4, - 0.275, - 0.0 - ], - "limit": 200000 - }, - "openai/o4-mini-high": { - "cost": [ - 1.1, - 4.4, - 0.275, - 0.0 - ], - "limit": 200000 + "knowledge": "2024-05", + "limit": 200000, + "max_output": 100000, + "released": "2025-06-10" }, "openrouter/auto": { "cost": [ @@ -38268,7 +49669,9 @@ 0.0, 0.0 ], - "limit": 2000000 + "limit": 2000000, + "max_output": 32768, + "released": "2026-03-15" }, "openrouter/bodybuilder": { "cost": [ @@ -38278,6 +49681,8 @@ 0.0 ], "limit": 128000, + "max_output": 32768, + "released": "2026-03-15", "status": "beta" }, "openrouter/free": { @@ -38287,7 +49692,9 @@ 0.0, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 32768, + "released": "2026-02-01" }, "openrouter/pareto-code": { "cost": [ @@ -38296,7 +49703,9 @@ 0.0, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 65536, + "released": "2026-04-21" }, "perceptron/perceptron-mk1": { "cost": [ @@ -38305,7 +49714,9 @@ 0.0, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 8192, + "released": "2026-05-12" }, "perceptron/perceptron-mk1.5": { "cost": [ @@ -38314,7 +49725,9 @@ 0.0, 0.0 ], - "limit": 36864 + "limit": 36864, + "max_output": 8192, + "released": "2026-09-25" }, "perplexity/sonar": { "cost": [ @@ -38323,7 +49736,9 @@ 0.0, 0.0 ], - "limit": 127072 + "limit": 127072, + "max_output": 114364, + "released": "2025-01-27" }, "perplexity/sonar-deep-research": { "cost": [ @@ -38332,7 +49747,10 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 115200, + "reasoning": 3.0, + "released": "2025-03-07" }, "perplexity/sonar-pro": { "cost": [ @@ -38341,7 +49759,9 @@ 0.0, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 8000, + "released": "2025-03-07" }, "perplexity/sonar-pro-search": { "cost": [ @@ -38350,7 +49770,9 @@ 0.0, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 8000, + "released": "2025-10-30" }, "perplexity/sonar-reasoning-pro": { "cost": [ @@ -38359,7 +49781,9 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 115200, + "released": "2025-03-07" }, "poolside/laguna-s-2.1": { "cost": [ @@ -38369,6 +49793,9 @@ 0.0 ], "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-21", "status": "deprecated" }, "poolside/laguna-s-2.1:free": { @@ -38378,7 +49805,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-07-21" }, "poolside/laguna-xs-2.1": { "cost": [ @@ -38388,6 +49818,9 @@ 0.0 ], "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-07-02", "status": "deprecated" }, "poolside/laguna-xs-2.1:free": { @@ -38397,7 +49830,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-07-02" }, "prism-ml/ternary-bonsai-2-27b": { "cost": [ @@ -38406,7 +49842,20 @@ 0.0375, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "released": "2026-09-18" + }, + "prism-ml/ternary-bonsai-2-9b": { + "cost": [ + 0.08, + 0.13, + 0.04, + 0.0 + ], + "limit": 262144, + "max_output": 65536, + "released": "2026-10-16" }, "qwen/qwen-2.5-72b-instruct": { "cost": [ @@ -38415,7 +49864,9 @@ 0.0, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 16384, + "released": "2024-09-19" }, "qwen/qwen-2.5-7b-instruct": { "cost": [ @@ -38424,7 +49875,9 @@ 0.0, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 29491, + "released": "2024-10-16" }, "qwen/qwen-2.5-coder-32b-instruct": { "cost": [ @@ -38433,7 +49886,10 @@ 0.0, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 29491, + "open": true, + "released": "2024-11-12" }, "qwen/qwen-plus": { "cost": [ @@ -38442,7 +49898,10 @@ 0.052, 0.325 ], - "limit": 1000000 + "knowledge": "2024-04", + "limit": 1000000, + "max_output": 32768, + "released": "2024-01-25" }, "qwen/qwen2.5-vl-72b-instruct": { "cost": [ @@ -38451,7 +49910,11 @@ 0.4, 0.0 ], - "limit": 128000 + "knowledge": "2024-04", + "limit": 128000, + "max_output": 115200, + "open": true, + "released": "2025-01-26" }, "qwen/qwen3-14b": { "cost": [ @@ -38460,7 +49923,9 @@ 0.0, 0.0 ], - "limit": 40960 + "limit": 40960, + "max_output": 16384, + "released": "2025-04-28" }, "qwen/qwen3-235b-a22b-2507": { "cost": [ @@ -38469,7 +49934,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 16384, + "open": true, + "released": "2025-07-21" }, "qwen/qwen3-235b-a22b-thinking-2507": { "cost": [ @@ -38478,7 +49946,10 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 16384, + "open": true, + "released": "2025-07-25" }, "qwen/qwen3-30b-a3b": { "cost": [ @@ -38487,16 +49958,22 @@ 0.0, 0.0 ], - "limit": 40960 + "limit": 40960, + "max_output": 16384, + "open": true, + "released": "2025-04-28" }, "qwen/qwen3-30b-a3b-instruct-2507": { "cost": [ - 0.09, + 0.1, 0.3, - 0.0, + 0.1, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 235929, + "open": true, + "released": "2025-07-28" }, "qwen/qwen3-32b": { "cost": [ @@ -38505,7 +49982,11 @@ 0.0, 0.0 ], - "limit": 40960 + "knowledge": "2025-04", + "limit": 40960, + "max_output": 16384, + "open": true, + "released": "2025-04-28" }, "qwen/qwen3-coder": { "cost": [ @@ -38514,7 +49995,11 @@ 0.1, 0.0 ], - "limit": 262144 + "knowledge": "2025-04", + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2025-07-22" }, "qwen/qwen3-coder-30b-a3b-instruct": { "cost": [ @@ -38523,7 +50008,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-04", + "limit": 262144, + "max_output": 235929, + "open": true, + "released": "2025-07-31" }, "qwen/qwen3-coder-flash": { "cost": [ @@ -38532,7 +50021,10 @@ 0.039, 0.24375 ], - "limit": 1000000 + "knowledge": "2025-04", + "limit": 1000000, + "max_output": 65536, + "released": "2025-07-28" }, "qwen/qwen3-coder-next": { "cost": [ @@ -38541,7 +50033,11 @@ 0.07, 0.0 ], - "limit": 262144 + "knowledge": "2025-09", + "limit": 262144, + "max_output": 235929, + "open": true, + "released": "2026-02-03" }, "qwen/qwen3-next-80b-a3b-instruct": { "cost": [ @@ -38550,16 +50046,11 @@ 0.0, 0.0 ], - "limit": 262144 - }, - "qwen/qwen3-next-80b-a3b-thinking": { - "cost": [ - 0.15, - 1.2, - 0.0, - 0.0 - ], - "limit": 262144 + "knowledge": "2025-04", + "limit": 262144, + "max_output": 16384, + "open": true, + "released": "2025-09" }, "qwen/qwen3-vl-235b-a22b-instruct": { "cost": [ @@ -38568,7 +50059,11 @@ 0.1, 0.0 ], - "limit": 131072 + "knowledge": "2025-03-31", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-09-23" }, "qwen/qwen3-vl-30b-a3b-instruct": { "cost": [ @@ -38577,7 +50072,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 16384, + "open": true, + "released": "2025-10-04" }, "qwen/qwen3-vl-30b-a3b-thinking": { "cost": [ @@ -38586,7 +50084,9 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 235929, + "released": "2025-10-06" }, "qwen/qwen3-vl-8b-instruct": { "cost": [ @@ -38595,7 +50095,9 @@ 0.12, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 235929, + "released": "2025-10-14" }, "qwen/qwen3.5-122b-a10b": { "cost": [ @@ -38604,7 +50106,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-23" }, "qwen/qwen3.5-27b": { "cost": [ @@ -38613,7 +50118,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 81920, + "open": true, + "released": "2026-02-23" }, "qwen/qwen3.5-35b-a3b": { "cost": [ @@ -38622,7 +50130,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 81920, + "open": true, + "released": "2026-02-23" }, "qwen/qwen3.5-397b-a17b": { "cost": [ @@ -38631,7 +50142,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 235929, + "open": true, + "released": "2026-02-15" }, "qwen/qwen3.5-9b": { "cost": [ @@ -38641,6 +50155,9 @@ 0.0 ], "limit": 262144, + "max_output": 235929, + "open": true, + "released": "2026-02-23", "status": "deprecated" }, "qwen/qwen3.5-flash-02-23": { @@ -38650,7 +50167,9 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 65536, + "released": "2026-02-25" }, "qwen/qwen3.5-plus-02-15": { "cost": [ @@ -38659,7 +50178,9 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 65536, + "released": "2026-02-16" }, "qwen/qwen3.5-plus-20260420": { "cost": [ @@ -38668,7 +50189,9 @@ 0.0, 0.375 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 65536, + "released": "2026-04-27" }, "qwen/qwen3.6-27b": { "cost": [ @@ -38677,16 +50200,22 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-04-22" }, "qwen/qwen3.6-35b-a3b": { "cost": [ 0.1, - 0.95, - 0.05, + 0.9, + 0.025, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 235929, + "open": true, + "released": "2026-04-17" }, "qwen/qwen3.6-flash": { "cost": [ @@ -38695,7 +50224,9 @@ 0.0, 0.234375 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 65536, + "released": "2026-04-27" }, "qwen/qwen3.6-plus": { "cost": [ @@ -38704,7 +50235,10 @@ 0.0, 0.40625 ], - "limit": 1000000 + "knowledge": "2025-04", + "limit": 1000000, + "max_output": 65536, + "released": "2026-04-02" }, "qwen/qwen3.7-flash": { "cost": [ @@ -38713,7 +50247,9 @@ 0.006, 0.038 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 65536, + "released": "2026-07-15" }, "qwen/qwen3.7-max": { "cost": [ @@ -38722,7 +50258,9 @@ 0.295, 1.84375 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-05-21" }, "qwen/qwen3.7-plus": { "cost": [ @@ -38731,7 +50269,10 @@ 0.064, 0.4 ], - "limit": 1000000 + "knowledge": "2025-04", + "limit": 1000000, + "max_output": 131072, + "released": "2026-06-02" }, "qwen/qwen3.8-2.4t-a95b": { "cost": [ @@ -38740,7 +50281,10 @@ 0.25, 2.5 ], - "limit": 1010000 + "limit": 1010000, + "max_output": 909000, + "open": true, + "released": "2026-08-12" }, "qwen/qwen3.8-27b": { "cost": [ @@ -38749,7 +50293,10 @@ 0.085, 0.53125 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-08-14" }, "qwen/qwen3.8-flash": { "cost": [ @@ -38758,7 +50305,9 @@ 0.016, 0.2 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-08-26" }, "qwen/qwen3.8-max-0902": { "cost": [ @@ -38767,7 +50316,9 @@ 0.25, 2.5 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-09-02" }, "qwen/qwen3.8-max-prime": { "cost": [ @@ -38776,7 +50327,9 @@ 0.5, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-09-23" }, "qwen/qwen3.8-omni-flash": { "cost": [ @@ -38785,7 +50338,9 @@ 0.016, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-09-17" }, "recursive/flint-v1.0:free": { "cost": [ @@ -38794,16 +50349,22 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 235929, + "released": "2026-10-21" }, "reflection/beam-1.0-501b-a23b": { "cost": [ - 0.24, - 0.98, - 0.035, + 0.25, + 1.0, + 0.05, 0.0 ], - "limit": 1048576 + "knowledge": "2026-06-30", + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-10-05" }, "reflection/beam-free": { "cost": [ @@ -38812,7 +50373,9 @@ 0.0, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2025-08-26" }, "rekaai/reka-edge": { "cost": [ @@ -38821,7 +50384,10 @@ 0.0, 0.0 ], - "limit": 16384 + "limit": 16384, + "max_output": 14745, + "open": true, + "released": "2026-03-11" }, "rekaai/reka-flash-3": { "cost": [ @@ -38830,7 +50396,11 @@ 0.0, 0.0 ], - "limit": 65536 + "knowledge": "2025-01-31", + "limit": 65536, + "max_output": 58982, + "open": true, + "released": "2025-03-10" }, "relace/relace-apply-3": { "cost": [ @@ -38839,7 +50409,9 @@ 0.0, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 128000, + "released": "2025-09-26" }, "relace/relace-search": { "cost": [ @@ -38848,7 +50420,9 @@ 0.0, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 128000, + "released": "2025-12-08" }, "sakana/fugu-max": { "cost": [ @@ -38857,7 +50431,9 @@ 0.25, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-11" }, "sakana/fugu-ultra": { "cost": [ @@ -38866,7 +50442,9 @@ 0.5, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-15" }, "sakana/fugu-ultra-v2": { "cost": [ @@ -38875,7 +50453,10 @@ 0.5, 0.0 ], - "limit": 1000000 + "knowledge": "2026-08-28", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-11" }, "sakana/sakana-namazu": { "cost": [ @@ -38884,7 +50465,9 @@ 0.15, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "released": "2026-08-03" }, "sao10k/l3-lunaris-8b": { "cost": [ @@ -38893,7 +50476,11 @@ 0.0, 0.0 ], - "limit": 8192 + "knowledge": "2023-12-31", + "limit": 8192, + "max_output": 7372, + "open": true, + "released": "2024-08-13" }, "sao10k/l3.1-euryale-70b": { "cost": [ @@ -38902,7 +50489,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2023-12-31", + "limit": 131072, + "max_output": 16384, + "open": true, + "released": "2024-08-28" }, "scaledown/extract": { "cost": [ @@ -38911,7 +50502,9 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 900000, + "released": "2026-10-13" }, "scaledown/summarize": { "cost": [ @@ -38920,7 +50513,9 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 4000, + "released": "2026-10-13" }, "stealth/claude-opus-4.6": { "cost": [ @@ -38929,7 +50524,10 @@ 0.4, 5.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 128000, + "reasoning": 0.0, + "released": "2025-08-26" }, "stealth/claude-opus-4.7": { "cost": [ @@ -38938,7 +50536,10 @@ 0.4, 5.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 128000, + "reasoning": 0.0, + "released": "2025-08-26" }, "stealth/claude-opus-4.8": { "cost": [ @@ -38947,7 +50548,10 @@ 0.4, 5.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 128000, + "reasoning": 0.0, + "released": "2025-08-26" }, "stealth/claude-sonnet-4.6": { "cost": [ @@ -38956,7 +50560,10 @@ 0.24, 3.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 64000, + "reasoning": 0.0, + "released": "2025-08-26" }, "stealth/glyph-cluster": { "cost": [ @@ -38965,7 +50572,9 @@ 0.0, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 256000, + "released": "2025-08-26" }, "stealth/qwen3.6-plus": { "cost": [ @@ -38974,7 +50583,10 @@ 0.025, 0.3125 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 65536, + "reasoning": 0.0, + "released": "2025-08-26" }, "stepfun/step-3.5-flash": { "cost": [ @@ -38983,7 +50595,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-01-29" }, "stepfun/step-3.7-flash": { "cost": [ @@ -38992,7 +50608,11 @@ 0.04, 0.0 ], - "limit": 256000 + "knowledge": "2026-03-01", + "limit": 256000, + "max_output": 230400, + "open": true, + "released": "2026-05-29" }, "stepfun/step-5-preview": { "cost": [ @@ -39001,7 +50621,10 @@ 0.1, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 64000, + "open": true, + "released": "2026-09-16" }, "tencent/hunyuan-a13b-instruct": { "cost": [ @@ -39010,7 +50633,9 @@ 0.0, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 117964, + "released": "2025-07-08" }, "tencent/hy-mt2-1.8b": { "cost": [ @@ -39019,7 +50644,10 @@ 0.0, 0.0 ], - "limit": 8192 + "limit": 8192, + "max_output": 4096, + "open": true, + "released": "2026-05-21" }, "tencent/hy-mt2-30b-a3b": { "cost": [ @@ -39028,7 +50656,10 @@ 0.0, 0.0 ], - "limit": 8192 + "limit": 8192, + "max_output": 4096, + "open": true, + "released": "2026-05-21" }, "tencent/hy-mt2-7b": { "cost": [ @@ -39037,7 +50668,10 @@ 0.0, 0.0 ], - "limit": 8192 + "limit": 8192, + "max_output": 4096, + "open": true, + "released": "2026-05-21" }, "tencent/hy3": { "cost": [ @@ -39046,7 +50680,10 @@ 0.033, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 128000, + "open": true, + "released": "2026-07-06" }, "tencent/hy3-preview": { "cost": [ @@ -39055,7 +50692,10 @@ 0.06, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 235929, + "open": true, + "released": "2026-04-20" }, "tencent/hy4-preview": { "cost": [ @@ -39064,7 +50704,10 @@ 0.042, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 64000, + "open": true, + "released": "2026-08-28" }, "thedrummer/cydonia-24b-v4.1": { "cost": [ @@ -39073,7 +50716,11 @@ 0.15, 0.0 ], - "limit": 131072 + "knowledge": "2024-04-30", + "limit": 131072, + "max_output": 117964, + "open": true, + "released": "2025-09-27" }, "thedrummer/skyfall-36b-v2": { "cost": [ @@ -39082,7 +50729,11 @@ 0.25, 0.0 ], - "limit": 32768 + "knowledge": "2024-06-30", + "limit": 32768, + "max_output": 29491, + "open": true, + "released": "2025-03-10" }, "thedrummer/unslopnemo-12b": { "cost": [ @@ -39091,7 +50742,11 @@ 0.0, 0.0 ], - "limit": 1024000 + "knowledge": "2024-04-30", + "limit": 1024000, + "max_output": 819200, + "open": true, + "released": "2024-11-08" }, "thinkingmachines/inkling": { "cost": [ @@ -39100,7 +50755,10 @@ 0.17, 0.0 ], - "limit": 524288 + "limit": 524288, + "max_output": 471859, + "open": true, + "released": "2026-07-15" }, "thinkingmachines/inkling-small": { "cost": [ @@ -39109,7 +50767,10 @@ 0.1, 0.0 ], - "limit": 524288 + "limit": 524288, + "max_output": 262144, + "open": true, + "released": "2026-07-30" }, "unbiased/pareto-26.10": { "cost": [ @@ -39118,7 +50779,9 @@ 0.03, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-10-15" }, "unbiased/pareto-26.9": { "cost": [ @@ -39127,7 +50790,9 @@ 0.25, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 131072, + "released": "2026-10-13" }, "undi95/remm-slerp-l2-13b": { "cost": [ @@ -39136,7 +50801,11 @@ 0.0, 0.0 ], - "limit": 6144 + "knowledge": "2023-06-30", + "limit": 6144, + "max_output": 5529, + "open": true, + "released": "2023-07-22" }, "upstage/solar-mini4": { "cost": [ @@ -39145,7 +50814,10 @@ 0.01, 0.0 ], - "limit": 524288 + "knowledge": "2026-02", + "limit": 524288, + "max_output": 131072, + "released": "2026-09-22" }, "upstage/solar-pro-3": { "cost": [ @@ -39154,7 +50826,10 @@ 0.015, 0.0 ], - "limit": 131072 + "knowledge": "2025-07", + "limit": 131072, + "max_output": 117964, + "released": "2026-01-26" }, "upstage/solar-pro4": { "cost": [ @@ -39163,7 +50838,10 @@ 0.06, 0.0 ], - "limit": 524288 + "knowledge": "2026-02", + "limit": 524288, + "max_output": 131072, + "released": "2026-08-06" }, "writer/palmyra-x5": { "cost": [ @@ -39172,7 +50850,9 @@ 0.0, 0.0 ], - "limit": 1040000 + "limit": 1040000, + "max_output": 8192, + "released": "2025-04-28" }, "x-ai/grok-4.20": { "cost": [ @@ -39181,7 +50861,9 @@ 0.2, 0.0 ], - "limit": 2000000 + "limit": 2000000, + "max_output": 1800000, + "released": "2026-03-31" }, "x-ai/grok-4.20-multi-agent": { "cost": [ @@ -39190,7 +50872,9 @@ 0.2, 0.0 ], - "limit": 2000000 + "limit": 2000000, + "max_output": 1800000, + "released": "2026-03-31" }, "x-ai/grok-4.3": { "cost": [ @@ -39199,7 +50883,9 @@ 0.2, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 900000, + "released": "2026-04-17" }, "x-ai/grok-4.5": { "cost": [ @@ -39208,7 +50894,9 @@ 0.3, 0.0 ], - "limit": 500000 + "limit": 500000, + "max_output": 450000, + "released": "2026-07-08" }, "x-ai/grok-4.6": { "cost": [ @@ -39217,7 +50905,10 @@ 0.5, 0.0 ], - "limit": 500000 + "knowledge": "2026-02-01", + "limit": 500000, + "max_output": 450000, + "released": "2026-08-12" }, "x-ai/grok-4.7": { "cost": [ @@ -39226,7 +50917,10 @@ 0.5, 0.0 ], - "limit": 500000 + "knowledge": "2026-05", + "limit": 500000, + "max_output": 450000, + "released": "2026-09-21" }, "x-ai/grok-build-0.1": { "cost": [ @@ -39235,7 +50929,9 @@ 0.2, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 230400, + "released": "2026-04-16" }, "xiaomi/mimo-v2.5": { "cost": [ @@ -39244,7 +50940,11 @@ 0.003, 0.0 ], - "limit": 1050000, + "knowledge": "2024-12", + "limit": 1000000, + "max_output": 65536, + "open": true, + "released": "2026-04-22", "status": "deprecated", "tiers": [ { @@ -39268,7 +50968,11 @@ 0.004, 0.0 ], - "limit": 1050000, + "knowledge": "2024-12", + "limit": 262144, + "max_output": 235929, + "open": true, + "released": "2026-04-22", "status": "deprecated", "tiers": [ { @@ -39292,16 +50996,22 @@ 0.003, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-09-22" }, "xiaomi/mimo-v2.6-pro": { "cost": [ - 0.43, + 0.435, 0.87, - 0.0036, + 0.004, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-09-22" }, "xiaomi/mimo-v2.6-pro-ultraspeed": { "cost": [ @@ -39310,7 +51020,10 @@ 0.036, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-09-21" }, "xingchen-agi/xing4.0-29b-a4b:free": { "cost": [ @@ -39319,7 +51032,9 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 235929, + "released": "2026-10-16" }, "z-ai/glm-4.5": { "cost": [ @@ -39328,7 +51043,11 @@ 0.11, 0.0 ], - "limit": 131072 + "knowledge": "2025-04", + "limit": 131072, + "max_output": 98304, + "open": true, + "released": "2025-07-28" }, "z-ai/glm-4.5-air": { "cost": [ @@ -39337,7 +51056,11 @@ 0.025, 0.0 ], - "limit": 131072 + "knowledge": "2025-04", + "limit": 131072, + "max_output": 98304, + "open": true, + "released": "2025-07-28" }, "z-ai/glm-4.5v": { "cost": [ @@ -39346,7 +51069,11 @@ 0.11, 0.0 ], - "limit": 65536 + "knowledge": "2025-04", + "limit": 65536, + "max_output": 16384, + "open": true, + "released": "2025-08-11" }, "z-ai/glm-4.6": { "cost": [ @@ -39355,16 +51082,24 @@ 0.11, 0.0 ], - "limit": 204800 + "knowledge": "2025-04", + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-09-30" }, "z-ai/glm-4.6v": { "cost": [ 0.3, 0.9, - 0.055, + 0.05, 0.0 ], - "limit": 131072 + "knowledge": "2025-04", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-12-08" }, "z-ai/glm-4.7": { "cost": [ @@ -39373,7 +51108,11 @@ 0.099, 0.0 ], - "limit": 204800 + "knowledge": "2025-04", + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-12-22" }, "z-ai/glm-4.7-flash": { "cost": [ @@ -39382,7 +51121,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2025-04", + "limit": 131072, + "max_output": 117964, + "open": true, + "released": "2026-01-19" }, "z-ai/glm-5": { "cost": [ @@ -39391,7 +51134,10 @@ 0.2, 0.0 ], - "limit": 202752 + "limit": 202752, + "max_output": 131072, + "open": true, + "released": "2026-02-12" }, "z-ai/glm-5-turbo": { "cost": [ @@ -39400,7 +51146,9 @@ 0.24, 0.0 ], - "limit": 202752 + "limit": 202752, + "max_output": 131072, + "released": "2026-03-16" }, "z-ai/glm-5.1": { "cost": [ @@ -39409,7 +51157,10 @@ 0.26, 0.0 ], - "limit": 202752 + "limit": 202752, + "max_output": 131072, + "open": true, + "released": "2026-04-07" }, "z-ai/glm-5.2": { "cost": [ @@ -39418,7 +51169,10 @@ 0.26, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 943718, + "open": true, + "released": "2026-06-13" }, "z-ai/glm-5.3": { "cost": [ @@ -39427,7 +51181,10 @@ 0.26, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 943718, + "open": true, + "released": "2026-08-14" }, "z-ai/glm-5.3-flash": { "cost": [ @@ -39436,7 +51193,10 @@ 0.03, 0.0 ], - "limit": 1048576 + "limit": 1048575, + "max_output": 943717, + "open": true, + "released": "2026-08-26" }, "z-ai/glm-5.3-flashx": { "cost": [ @@ -39445,7 +51205,9 @@ 0.09, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-09-18" }, "z-ai/glm-5.3-prime": { "cost": [ @@ -39454,7 +51216,9 @@ 0.56, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-09-23" }, "z-ai/glm-5v-turbo": { "cost": [ @@ -39463,7 +51227,9 @@ 0.24, 0.0 ], - "limit": 202752 + "limit": 202752, + "max_output": 131072, + "released": "2026-04-01" }, "~anthropic/claude-fable-latest": { "cost": [ @@ -39472,7 +51238,9 @@ 0.25, 12.5 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-09" }, "~anthropic/claude-haiku-latest": { "cost": [ @@ -39481,7 +51249,9 @@ 0.01, 0.125 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-27" }, "~anthropic/claude-opus-latest": { "cost": [ @@ -39490,7 +51260,9 @@ 0.2, 5.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-21" }, "~anthropic/claude-sonnet-latest": { "cost": [ @@ -39499,34 +51271,43 @@ 0.1, 2.5 ], - "limit": 1000000 + "knowledge": "2025-08-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-27" }, "~deepseek/deepseek-flash-latest": { "cost": [ - 0.045, - 0.6, - 0.006, + 0.0115, + 1.8, + 0.0114, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 943718, + "released": "2026-09-14" }, "~deepseek/deepseek-pro-latest": { "cost": [ - 0.20592, - 0.61776, - 0.006552, + 0.2043, + 8.0, + 0.2, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 393216, + "released": "2026-09-14" }, "~deepseek/deepseek-v4-flash-latest": { "cost": [ - 0.04708, - 0.14124, - 0.001498, + 0.0422, + 0.1637, + 0.028, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 943718, + "released": "2026-08-01" }, "~google/gemini-flash-latest": { "cost": [ @@ -39535,7 +51316,9 @@ 0.075, 0.041667 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65536, + "released": "2026-04-27" }, "~google/gemini-pro-latest": { "cost": [ @@ -39544,16 +51327,20 @@ 0.1, 0.1875 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 943718, + "released": "2026-04-27" }, "~moonshotai/kimi-latest": { "cost": [ - 0.238, - 16.0, - 0.228, + 0.19, + 10.5634, + 0.19, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 943718, + "released": "2026-04-27" }, "~openai/gpt-astra-latest": { "cost": [ @@ -39562,7 +51349,9 @@ 1.0, 12.5 ], - "limit": 1050000 + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-11" }, "~openai/gpt-luna-latest": { "cost": [ @@ -39571,7 +51360,9 @@ 0.01, 0.125 ], - "limit": 1050000 + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-11" }, "~openai/gpt-mini-latest": { "cost": [ @@ -39580,7 +51371,9 @@ 0.075, 0.0 ], - "limit": 400000 + "limit": 400000, + "max_output": 128000, + "released": "2026-04-27" }, "~openai/gpt-sol-latest": { "cost": [ @@ -39589,16 +51382,20 @@ 0.1, 2.5 ], - "limit": 1050000 + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-11" }, "~openai/gpt-terra-latest": { "cost": [ - 2.0, - 12.0, - 0.2, - 2.5 + 1.0, + 5.0, + 0.05, + 1.25 ], - "limit": 1050000 + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-11" }, "~unbiased/pareto-latest": { "cost": [ @@ -39607,7 +51404,9 @@ 0.03, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-10-13" }, "~x-ai/grok-latest": { "cost": [ @@ -39616,25 +51415,31 @@ 0.5, 0.0 ], - "limit": 500000 + "limit": 500000, + "max_output": 450000, + "released": "2026-07-08" }, "~z-ai/glm-flash-latest": { "cost": [ - 0.0052, - 0.1985, - 0.0052, + 0.0237, + 0.1142, + 0.0237, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-08-27" }, "~z-ai/glm-latest": { "cost": [ - 0.079, + 0.0699, 1.4, - 0.078, + 0.0689, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 943718, + "released": "2026-08-19" } }, "name": "Kilo Gateway" @@ -39648,7 +51453,10 @@ 0.0, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-16" }, "k3-256k": { "cost": [ @@ -39657,7 +51465,32 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 131072, + "open": true, + "released": "2026-07-16" + }, + "k3.1-pro": { + "cost": [ + 0.0, + 0.0, + 0.0, + 0.0 + ], + "limit": 1048576, + "max_output": 131072, + "released": "2026-10-23" + }, + "k3.1-pro-highspeed": { + "cost": [ + 0.0, + 0.0, + 0.0, + 0.0 + ], + "limit": 1048576, + "max_output": 131072, + "released": "2026-10-23" }, "kimi-for-coding": { "cost": [ @@ -39666,7 +51499,9 @@ 0.0, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 32768, + "released": "2026-09-11" }, "kimi-for-coding-highspeed": { "cost": [ @@ -39675,7 +51510,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-06-12" } }, "name": "Kimi For Coding (kimi.com)" @@ -39689,7 +51528,10 @@ 0.0, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-16" }, "k3-256k": { "cost": [ @@ -39698,7 +51540,32 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 131072, + "open": true, + "released": "2026-07-16" + }, + "k3.1-pro": { + "cost": [ + 0.0, + 0.0, + 0.0, + 0.0 + ], + "limit": 1048576, + "max_output": 131072, + "released": "2026-10-23" + }, + "k3.1-pro-highspeed": { + "cost": [ + 0.0, + 0.0, + 0.0, + 0.0 + ], + "limit": 1048576, + "max_output": 131072, + "released": "2026-10-23" }, "kimi-for-coding": { "cost": [ @@ -39707,7 +51574,9 @@ 0.0, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 32768, + "released": "2026-09-11" }, "kimi-for-coding-highspeed": { "cost": [ @@ -39716,7 +51585,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-06-12" } }, "name": "Kimi For Coding (kimi.ai)" @@ -39731,6 +51604,8 @@ 0.0 ], "limit": 200000, + "max_output": 50000, + "released": "2026-08-29", "status": "beta" }, "Kloker-Integration-Architect": { @@ -39741,6 +51616,8 @@ 0.0 ], "limit": 200000, + "max_output": 50000, + "released": "2026-08-29", "status": "beta" }, "Kloker-Integration-Developer": { @@ -39751,6 +51628,8 @@ 0.0 ], "limit": 200000, + "max_output": 50000, + "released": "2026-08-29", "status": "beta" } }, @@ -39765,7 +51644,10 @@ 0.09, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-08-14" } }, "name": "Kosmik Compute" @@ -39779,7 +51661,11 @@ 0.0, 0.0 ], - "limit": 204800 + "knowledge": "2025-04", + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-12-22" } }, "name": "KUAE Cloud Coding Plan" @@ -39793,7 +51679,11 @@ 0.0, 0.0 ], + "knowledge": "2025-01", "limit": 262100, + "max_output": 262100, + "open": true, + "released": "2026-04-02", "status": "deprecated" }, "minimaxai/minimax-m3": { @@ -39804,6 +51694,9 @@ 0.0 ], "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-06-01", "status": "deprecated" }, "moonshotai/kimi-k2.6": { @@ -39813,7 +51706,11 @@ 0.2, 0.0 ], + "knowledge": "2025-01", "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-20", "status": "deprecated" }, "zai-org/glm-5.2": { @@ -39824,6 +51721,9 @@ 0.0 ], "limit": 524288, + "max_output": 524288, + "open": true, + "released": "2026-06-13", "status": "deprecated" } }, @@ -39838,7 +51738,10 @@ 0.05, 0.0 ], - "limit": 262000 + "limit": 262000, + "max_output": 32768, + "open": true, + "released": "2026-08-14" }, "auto": { "cost": [ @@ -39847,7 +51750,9 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 16384, + "released": "2024-01-01" }, "claude-fable-5": { "cost": [ @@ -39856,7 +51761,10 @@ 1.0, 12.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-09" }, "claude-fable-5-1": { "cost": [ @@ -39865,7 +51773,10 @@ 0.25, 12.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-01" }, "claude-haiku-4-5": { "cost": [ @@ -39874,7 +51785,10 @@ 0.1, 1.25 ], - "limit": 200000 + "knowledge": "2025-02-28", + "limit": 200000, + "max_output": 64000, + "released": "2025-10-15" }, "claude-haiku-4-5-20251001": { "cost": [ @@ -39883,7 +51797,10 @@ 0.1, 1.25 ], - "limit": 200000 + "knowledge": "2025-02-28", + "limit": 200000, + "max_output": 64000, + "released": "2025-10-15" }, "claude-haiku-5-5": { "cost": [ @@ -39892,7 +51809,10 @@ 0.01, 0.125 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-10-07" }, "claude-opus-4-5-20251101": { "cost": [ @@ -39901,7 +51821,10 @@ 0.5, 6.25 ], - "limit": 200000 + "knowledge": "2025-05", + "limit": 200000, + "max_output": 64000, + "released": "2025-11-24" }, "claude-opus-4-6": { "cost": [ @@ -39910,7 +51833,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2025-05-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-05" }, "claude-opus-4-7": { "cost": [ @@ -39919,7 +51845,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-16" }, "claude-opus-4-8": { "cost": [ @@ -39928,7 +51857,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-28" }, "claude-opus-5": { "cost": [ @@ -39937,7 +51869,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-05", + "limit": 1000000, + "max_output": 128000, + "released": "2026-07-24" }, "claude-opus-5-5": { "cost": [ @@ -39946,7 +51881,10 @@ 0.2, 5.0 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-22" }, "claude-sonnet-4-5": { "cost": [ @@ -39955,7 +51893,10 @@ 0.3, 3.75 ], - "limit": 200000 + "knowledge": "2025-07-31", + "limit": 200000, + "max_output": 64000, + "released": "2025-09-29" }, "claude-sonnet-4-5-20250929": { "cost": [ @@ -39964,7 +51905,10 @@ 0.3, 3.75 ], - "limit": 200000 + "knowledge": "2025-07-31", + "limit": 200000, + "max_output": 64000, + "released": "2025-09-29" }, "claude-sonnet-4-6": { "cost": [ @@ -39973,7 +51917,10 @@ 0.3, 3.75 ], - "limit": 1000000 + "knowledge": "2025-08-31", + "limit": 1000000, + "max_output": 64000, + "released": "2026-02-17" }, "claude-sonnet-5": { "cost": [ @@ -39982,7 +51929,10 @@ 0.2, 2.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 1000000, + "released": "2026-06-30" }, "claude-sonnet-5-5": { "cost": [ @@ -39991,7 +51941,10 @@ 0.1, 2.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-28" }, "codestral-2508": { "cost": [ @@ -40000,7 +51953,9 @@ 0.0, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 16384, + "released": "2025-07-30" }, "custom": { "cost": [ @@ -40009,7 +51964,9 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 16384, + "released": "2024-01-01" }, "deepseek-v3.2": { "cost": [ @@ -40018,7 +51975,11 @@ 0.13, 0.0 ], - "limit": 163840 + "knowledge": "2024-07", + "limit": 163840, + "max_output": 16384, + "open": true, + "released": "2025-12-01" }, "deepseek-v4-flash": { "cost": [ @@ -40027,7 +51988,11 @@ 0.014, 0.0 ], - "limit": 1050000 + "knowledge": "2025-05", + "limit": 1050000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "deepseek-v4-pro": { "cost": [ @@ -40036,7 +52001,11 @@ 0.003625, 0.0 ], - "limit": 1050000 + "knowledge": "2025-05", + "limit": 1050000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "deepseek-v4.1-flash": { "cost": [ @@ -40045,7 +52014,11 @@ 0.0027, 0.0 ], - "limit": 1050000 + "knowledge": "2025-05", + "limit": 1050000, + "max_output": 384000, + "open": true, + "released": "2026-09-10" }, "deepseek-v4.1-flash-1017": { "cost": [ @@ -40054,7 +52027,11 @@ 0.003, 0.0 ], - "limit": 1050000 + "knowledge": "2025-05", + "limit": 1056784, + "max_output": 1050000, + "open": true, + "released": "2026-10-17" }, "devstral-2512": { "cost": [ @@ -40063,18 +52040,13 @@ 0.0, 0.0 ], + "knowledge": "2025-12", "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2025-12-09", "status": "deprecated" }, - "ernie-4.5-vl-424b-a47b": { - "cost": [ - 0.42, - 1.25, - 0.0, - 0.0 - ], - "limit": 123000 - }, "fugu-max": { "cost": [ 2.0, @@ -40082,7 +52054,9 @@ 0.25, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 1000000, + "released": "2026-09-11" }, "fugu-ultra": { "cost": [ @@ -40091,7 +52065,9 @@ 0.5, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 1000000, + "released": "2026-06-15" }, "fugu-ultra-v2.0": { "cost": [ @@ -40100,7 +52076,9 @@ 0.5, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 1000000, + "released": "2026-09-11" }, "gemini-3-flash-preview": { "cost": [ @@ -40109,7 +52087,10 @@ 0.05, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2025-12-17" }, "gemini-3.1-flash-lite": { "cost": [ @@ -40118,7 +52099,10 @@ 0.025, 0.08333 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-05-07" }, "gemini-3.1-pro-preview": { "cost": [ @@ -40127,7 +52111,10 @@ 0.2, 0.0 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2026-02-19", "tiers": [ { "cost": [ @@ -40150,7 +52137,10 @@ 0.15, 0.08333 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-05-19" }, "gemini-3.5-flash-lite": { "cost": [ @@ -40159,7 +52149,10 @@ 0.03, 0.08333 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-07-21" }, "gemini-3.6-flash": { "cost": [ @@ -40168,7 +52161,10 @@ 0.075, 0.08333 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-07-21" }, "gemini-3.7-flash": { "cost": [ @@ -40177,7 +52173,10 @@ 0.075, 0.08333 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-08-13" }, "gemini-3.8-flash": { "cost": [ @@ -40186,7 +52185,9 @@ 0.075, 0.08333 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "released": "2026-09-02" }, "gemini-4-argon": { "cost": [ @@ -40195,7 +52196,10 @@ 0.2, 0.375 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 1048576, + "released": "2026-10-13" }, "gemini-pro-latest": { "cost": [ @@ -40204,7 +52208,9 @@ 0.2, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65536, + "released": "2026-02-27" }, "gemma-4-26b-a4b-it": { "cost": [ @@ -40213,7 +52219,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-04-02" }, "gemma-4-31b-it": { "cost": [ @@ -40222,7 +52231,11 @@ 0.01, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-04-02" }, "glm-4-32b-0414-128k": { "cost": [ @@ -40231,7 +52244,9 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 16384, + "released": "2025-04-14" }, "glm-4.5": { "cost": [ @@ -40240,7 +52255,11 @@ 0.11, 0.0 ], - "limit": 131000 + "knowledge": "2025-04", + "limit": 131000, + "max_output": 98304, + "open": true, + "released": "2025-07-28" }, "glm-4.5-air": { "cost": [ @@ -40249,7 +52268,11 @@ 0.03, 0.0 ], - "limit": 131000 + "knowledge": "2025-04", + "limit": 131000, + "max_output": 98304, + "open": true, + "released": "2025-07-28" }, "glm-4.5-airx": { "cost": [ @@ -40258,7 +52281,9 @@ 0.22, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 16384, + "released": "2025-07-28" }, "glm-4.5-x": { "cost": [ @@ -40268,6 +52293,8 @@ 0.0 ], "limit": 128000, + "max_output": 16384, + "released": "2025-07-28", "status": "beta" }, "glm-4.5v": { @@ -40277,7 +52304,11 @@ 0.11, 0.0 ], - "limit": 128000 + "knowledge": "2025-04", + "limit": 128000, + "max_output": 16384, + "open": true, + "released": "2025-08-11" }, "glm-4.6": { "cost": [ @@ -40286,7 +52317,11 @@ 0.11, 0.0 ], - "limit": 204800 + "knowledge": "2025-04", + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-09-30" }, "glm-4.6v": { "cost": [ @@ -40295,7 +52330,11 @@ 0.05, 0.0 ], - "limit": 131072 + "knowledge": "2025-04", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-12-08" }, "glm-4.6v-flashx": { "cost": [ @@ -40304,7 +52343,9 @@ 0.004, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 16000, + "released": "2025-12-08" }, "glm-4.7": { "cost": [ @@ -40313,16 +52354,11 @@ 0.19, 0.0 ], - "limit": 204800 - }, - "glm-4.7-flash": { - "cost": [ - 0.06, - 0.4, - 0.01, - 0.0 - ], - "limit": 200000 + "knowledge": "2025-04", + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-12-22" }, "glm-4.7-flashx": { "cost": [ @@ -40331,7 +52367,11 @@ 0.01, 0.0 ], - "limit": 200000 + "knowledge": "2025-04", + "limit": 200000, + "max_output": 131072, + "open": true, + "released": "2026-01-19" }, "glm-5": { "cost": [ @@ -40340,7 +52380,10 @@ 0.144, 0.0 ], - "limit": 203000 + "limit": 203000, + "max_output": 131072, + "open": true, + "released": "2026-02-12" }, "glm-5-turbo": { "cost": [ @@ -40349,7 +52392,9 @@ 0.24, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 131072, + "released": "2026-03-16" }, "glm-5.1": { "cost": [ @@ -40358,7 +52403,10 @@ 0.26, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-04-07" }, "glm-5.2": { "cost": [ @@ -40367,7 +52415,10 @@ 0.154, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "glm-5.2-fast": { "cost": [ @@ -40376,16 +52427,22 @@ 0.429, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "glm-5.3": { "cost": [ - 0.5, - 2.0, - 0.15, + 0.45, + 1.8, + 0.135, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "glm-5.3-fast": { "cost": [ @@ -40394,7 +52451,10 @@ 0.56, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "glm-5.3-flash": { "cost": [ @@ -40403,7 +52463,10 @@ 0.025, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-08-26" }, "glm-5v-turbo": { "cost": [ @@ -40412,7 +52475,9 @@ 0.24, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 131072, + "released": "2026-04-01" }, "gpt-4.1": { "cost": [ @@ -40421,7 +52486,10 @@ 0.5, 0.0 ], - "limit": 1000000 + "knowledge": "2024-04", + "limit": 1000000, + "max_output": 32768, + "released": "2025-04-14" }, "gpt-4.1-mini": { "cost": [ @@ -40430,7 +52498,10 @@ 0.1, 0.0 ], - "limit": 1000000 + "knowledge": "2024-04", + "limit": 1000000, + "max_output": 32768, + "released": "2025-04-14" }, "gpt-4o": { "cost": [ @@ -40439,7 +52510,10 @@ 1.25, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-05-13" }, "gpt-4o-mini": { "cost": [ @@ -40448,7 +52522,10 @@ 0.075, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-07-18" }, "gpt-4o-mini-transcribe": { "cost": [ @@ -40457,7 +52534,9 @@ 0.0, 0.0 ], - "limit": 16000 + "limit": 16000, + "max_output": 16000, + "released": "2025-03-20" }, "gpt-4o-transcribe": { "cost": [ @@ -40466,7 +52545,9 @@ 0.0, 0.0 ], - "limit": 16000 + "limit": 16000, + "max_output": 16000, + "released": "2025-03-20" }, "gpt-5": { "cost": [ @@ -40475,7 +52556,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "gpt-5-mini": { "cost": [ @@ -40484,7 +52568,10 @@ 0.025, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "gpt-5-nano": { "cost": [ @@ -40493,7 +52580,10 @@ 0.005, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "gpt-5-pro": { "cost": [ @@ -40502,7 +52592,10 @@ 0.0, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 272000, + "released": "2025-10-06" }, "gpt-5.1": { "cost": [ @@ -40511,7 +52604,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "gpt-5.1-codex": { "cost": [ @@ -40520,7 +52616,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "gpt-5.1-codex-mini": { "cost": [ @@ -40529,7 +52628,10 @@ 0.025, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "gpt-5.2": { "cost": [ @@ -40538,7 +52640,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "gpt-5.2-codex": { "cost": [ @@ -40547,7 +52652,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "gpt-5.2-pro": { "cost": [ @@ -40556,7 +52664,10 @@ 0.0, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "gpt-5.3-codex": { "cost": [ @@ -40565,7 +52676,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-02-05" }, "gpt-5.4": { "cost": [ @@ -40574,7 +52688,10 @@ 0.25, 0.0 ], - "limit": 1050000 + "knowledge": "2025-08-31", + "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05" }, "gpt-5.4-mini": { "cost": [ @@ -40583,7 +52700,10 @@ 0.075, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "gpt-5.4-nano": { "cost": [ @@ -40592,7 +52712,10 @@ 0.02, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "gpt-5.4-pro": { "cost": [ @@ -40601,7 +52724,10 @@ 0.0, 0.0 ], - "limit": 1050000 + "knowledge": "2025-08-31", + "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05" }, "gpt-5.5": { "cost": [ @@ -40610,7 +52736,10 @@ 0.5, 0.0 ], + "knowledge": "2025-12-01", "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23", "tiers": [ { "cost": [ @@ -40633,7 +52762,10 @@ 0.0, 0.0 ], + "knowledge": "2025-12-01", "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23", "tiers": [ { "cost": [ @@ -40656,7 +52788,10 @@ 0.02, 0.25 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "gpt-5.6-sol": { "cost": [ @@ -40665,7 +52800,10 @@ 0.4, 5.0 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "gpt-5.6-terra": { "cost": [ @@ -40674,7 +52812,10 @@ 0.2, 2.5 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "gpt-6-astra": { "cost": [ @@ -40683,7 +52824,10 @@ 1.0, 12.5 ], - "limit": 1050000 + "knowledge": "2026-04-30", + "limit": 1050000, + "max_output": 1050000, + "released": "2026-09-04" }, "gpt-6-luna": { "cost": [ @@ -40692,7 +52836,10 @@ 0.01, 0.125 ], - "limit": 1050000 + "knowledge": "2026-05-18", + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22" }, "gpt-6-sol": { "cost": [ @@ -40701,7 +52848,10 @@ 0.2, 2.5 ], - "limit": 1050000 + "knowledge": "2026-04-20", + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22" }, "gpt-6.1-sol": { "cost": [ @@ -40710,7 +52860,22 @@ 0.1, 2.5 ], - "limit": 1050000 + "knowledge": "2026-04-30", + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-29" + }, + "gpt-6.1-terra": { + "cost": [ + 1.0, + 5.0, + 0.05, + 1.25 + ], + "knowledge": "2026-06-01", + "limit": 1050000, + "max_output": 128000, + "released": "2026-10-26" }, "gpt-live-transcribe": { "cost": [ @@ -40718,7 +52883,9 @@ 0.0, 0.0, 0.0 - ] + ], + "released": "2026-07-28", + "type": "transcription" }, "gpt-oss-120b": { "cost": [ @@ -40727,7 +52894,11 @@ 0.032, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 32766, + "open": true, + "released": "2025-08-05" }, "gpt-oss-20b": { "cost": [ @@ -40736,7 +52907,11 @@ 0.01, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 32766, + "open": true, + "released": "2025-08-05" }, "gpt-transcribe": { "cost": [ @@ -40744,7 +52919,9 @@ 0.0, 0.0, 0.0 - ] + ], + "released": "2026-07-28", + "type": "transcription" }, "granite-4.2-8b": { "cost": [ @@ -40753,7 +52930,10 @@ 0.015, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2026-08-25" }, "grok-4": { "cost": [ @@ -40762,50 +52942,47 @@ 0.75, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 256000, + "released": "2025-07-09" }, - "grok-4-1-fast-non-reasoning": { + "grok-4-1-fast-reasoning": { "cost": [ 0.2, 0.5, 0.05, 0.0 ], - "limit": 2000000 + "limit": 2000000, + "max_output": 30000, + "released": "2025-11-19" }, - "grok-4-1-fast-reasoning": { + "grok-4-20-beta-0309-non-reasoning": { "cost": [ + 2.0, + 6.0, 0.2, - 0.5, - 0.05, 0.0 ], - "limit": 2000000 + "limit": 2000000, + "max_output": 30000, + "released": "2026-03-09", + "tiers": [ + { + "cost": [ + 2.5, + 5.0, + 0.4, + 0.0 + ], + "tier": { + "size": 200000, + "type": "context" + } + } + ] }, - "grok-4-20-beta-0309-non-reasoning": { - "cost": [ - 2.0, - 6.0, - 0.2, - 0.0 - ], - "limit": 2000000, - "tiers": [ - { - "cost": [ - 2.5, - 5.0, - 0.4, - 0.0 - ], - "tier": { - "size": 200000, - "type": "context" - } - } - ] - }, - "grok-4-20-beta-0309-reasoning": { + "grok-4-20-beta-0309-reasoning": { "cost": [ 2.0, 6.0, @@ -40813,6 +52990,8 @@ 0.0 ], "limit": 2000000, + "max_output": 30000, + "released": "2026-03-09", "tiers": [ { "cost": [ @@ -40836,6 +53015,8 @@ 0.0 ], "limit": 2000000, + "max_output": 30000, + "released": "2026-03-09", "tiers": [ { "cost": [ @@ -40859,6 +53040,8 @@ 0.0 ], "limit": 2000000, + "max_output": 30000, + "released": "2026-03-09", "tiers": [ { "cost": [ @@ -40882,6 +53065,8 @@ 0.0 ], "limit": 1000000, + "max_output": 30000, + "released": "2026-04-17", "tiers": [ { "cost": [ @@ -40904,7 +53089,9 @@ 0.3, 0.0 ], - "limit": 500000 + "limit": 500000, + "max_output": 500000, + "released": "2026-07-08" }, "grok-4-6": { "cost": [ @@ -40913,7 +53100,10 @@ 0.5, 0.0 ], - "limit": 500000 + "knowledge": "2026-02-01", + "limit": 500000, + "max_output": 500000, + "released": "2026-08-12" }, "grok-4-7": { "cost": [ @@ -40922,7 +53112,10 @@ 0.5, 0.0 ], - "limit": 524288 + "knowledge": "2026-05", + "limit": 524288, + "max_output": 500000, + "released": "2026-09-21" }, "grok-build-0-1": { "cost": [ @@ -40932,6 +53125,8 @@ 0.0 ], "limit": 256000, + "max_output": 256000, + "released": "2026-04-16", "tiers": [ { "cost": [ @@ -40954,7 +53149,9 @@ 0.0, 0.0 ], - "limit": 8192 + "limit": 8192, + "max_output": 8192, + "released": "2026-05-21" }, "hy3": { "cost": [ @@ -40963,7 +53160,10 @@ 0.033, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 128000, + "open": true, + "released": "2026-07-06" }, "hy4-preview": { "cost": [ @@ -40972,7 +53172,10 @@ 0.042, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 64000, + "open": true, + "released": "2026-08-28" }, "kimi-k2": { "cost": [ @@ -40981,7 +53184,10 @@ 0.5, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 16384, + "open": true, + "released": "2025-07-11" }, "kimi-k2.5": { "cost": [ @@ -40990,7 +53196,11 @@ 0.225, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-01-27" }, "kimi-k2.6": { "cost": [ @@ -40999,7 +53209,11 @@ 0.13, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-20" }, "kimi-k2.7-code": { "cost": [ @@ -41008,7 +53222,11 @@ 0.143, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-06-12" }, "kimi-k2.7-code-highspeed": { "cost": [ @@ -41017,7 +53235,11 @@ 0.38, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-06-12" }, "kimi-k3": { "cost": [ @@ -41026,7 +53248,10 @@ 0.3, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-16" }, "kimi-k3-fast": { "cost": [ @@ -41035,7 +53260,32 @@ 0.45, 0.0 ], - "limit": 1040384 + "limit": 1040384, + "max_output": 131072, + "open": true, + "released": "2026-07-16" + }, + "kimi-k3.1-pro": { + "cost": [ + 2.0, + 10.0, + 0.2, + 2.0 + ], + "limit": 1048576, + "max_output": 131072, + "released": "2026-10-23" + }, + "kimi-k3.1-pro-highspeed": { + "cost": [ + 4.0, + 20.0, + 0.2, + 4.0 + ], + "limit": 1048576, + "max_output": 1048576, + "released": "2026-10-23" }, "ling-3.0-flash": { "cost": [ @@ -41044,7 +53294,10 @@ 0.012, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-07-23" }, "ling-3.0-flash-vl": { "cost": [ @@ -41053,16 +53306,10 @@ 0.012, 0.0 ], - "limit": 131072 - }, - "llama-3-70b-instruct": { - "cost": [ - 0.51, - 0.74, - 0.0, - 0.0 - ], - "limit": 8192 + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2026-09-10" }, "llama-3.1-70b-instruct": { "cost": [ @@ -41071,7 +53318,11 @@ 0.0, 0.0 ], + "knowledge": "2023-12", "limit": 128000, + "max_output": 2048, + "open": true, + "released": "2024-07-23", "status": "beta" }, "llama-3.2-11b-instruct": { @@ -41081,16 +53332,10 @@ 0.0, 0.0 ], - "limit": 128000 - }, - "llama-3.2-3b-instruct": { - "cost": [ - 0.03, - 0.05, - 0.0, - 0.0 - ], - "limit": 32768 + "limit": 128000, + "max_output": 8192, + "open": true, + "released": "2024-09-25" }, "llama-3.3-70b-instruct": { "cost": [ @@ -41099,7 +53344,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2023-12", + "limit": 131072, + "max_output": 4096, + "open": true, + "released": "2024-12-06" }, "llama-4-maverick-17b-instruct": { "cost": [ @@ -41108,7 +53357,11 @@ 0.0, 0.0 ], - "limit": 1048576 + "knowledge": "2024-08", + "limit": 1048576, + "max_output": 2048, + "open": true, + "released": "2025-04-05" }, "llama-4-scout-17b-instruct": { "cost": [ @@ -41117,7 +53370,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-08", + "limit": 131072, + "max_output": 2048, + "open": true, + "released": "2025-04-05" }, "mimo-v2.6-flash": { "cost": [ @@ -41126,7 +53383,10 @@ 0.0025, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-09-22" }, "mimo-v2.6-pro": { "cost": [ @@ -41135,7 +53395,10 @@ 0.0036, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-09-22" }, "minimax-m2": { "cost": [ @@ -41144,7 +53407,10 @@ 0.03, 0.0 ], - "limit": 196608 + "limit": 196608, + "max_output": 131072, + "open": true, + "released": "2025-10-27" }, "minimax-m2.1": { "cost": [ @@ -41153,7 +53419,10 @@ 0.0, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-12-23" }, "minimax-m2.1-lightning": { "cost": [ @@ -41162,7 +53431,10 @@ 0.0, 0.0 ], - "limit": 196608 + "limit": 196608, + "max_output": 131072, + "open": true, + "released": "2025-12-23" }, "minimax-m2.5": { "cost": [ @@ -41171,7 +53443,10 @@ 0.03, 0.375 ], - "limit": 228700 + "limit": 228700, + "max_output": 131072, + "open": true, + "released": "2026-02-12" }, "minimax-m2.5-highspeed": { "cost": [ @@ -41180,16 +53455,22 @@ 0.03, 0.375 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-02-13" }, "minimax-m2.7": { "cost": [ - 0.08, - 0.32, - 0.017, + 0.3, + 1.2, + 0.06, 0.375 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-03-18" }, "minimax-m2.7-highspeed": { "cost": [ @@ -41198,7 +53479,10 @@ 0.06, 0.375 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-03-18" }, "minimax-m3": { "cost": [ @@ -41207,16 +53491,21 @@ 0.05, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 512000, + "open": true, + "released": "2026-06-01" }, "minimax-m3.1-flash": { "cost": [ - 0.15, - 0.6, - 0.015, + 0.1, + 0.5, + 0.005, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 512000, + "released": "2026-10-19" }, "minimax-text-01": { "cost": [ @@ -41225,7 +53514,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2025-01-15" }, "ministral-14b-2512": { "cost": [ @@ -41234,7 +53526,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 8192, + "open": true, + "released": "2025-12-02" }, "ministral-3b-2512": { "cost": [ @@ -41243,7 +53538,10 @@ 0.0, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 8192, + "open": true, + "released": "2025-12-02" }, "ministral-8b-2512": { "cost": [ @@ -41252,7 +53550,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 8192, + "open": true, + "released": "2025-12-02" }, "mistral-large-2512": { "cost": [ @@ -41261,7 +53562,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2024-11", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2025-12-02" }, "mistral-large-4": { "cost": [ @@ -41270,7 +53575,9 @@ 0.14, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 262144, + "released": "2026-10-06" }, "mistral-large-latest": { "cost": [ @@ -41279,7 +53586,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-11", + "limit": 128000, + "max_output": 262144, + "open": true, + "released": "2024-11-01" }, "mistral-medium-3-5": { "cost": [ @@ -41288,7 +53599,9 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "released": "2026-04-30" }, "mistral-small-2506": { "cost": [ @@ -41297,7 +53610,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2025-03", + "limit": 128000, + "max_output": 16384, + "open": true, + "released": "2025-06-20" }, "mistral-small-2603": { "cost": [ @@ -41306,7 +53623,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-06", + "limit": 262144, + "max_output": 256000, + "open": true, + "released": "2026-03-16" }, "muse-glimmer-30b": { "cost": [ @@ -41315,7 +53636,11 @@ 0.04, 0.0 ], - "limit": 131072 + "knowledge": "2026-01-04", + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2026-08-10" }, "muse-spark-1.1": { "cost": [ @@ -41324,7 +53649,9 @@ 0.15, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-04-08" }, "muse-spark-1.2": { "cost": [ @@ -41333,7 +53660,9 @@ 0.15, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-08-05" }, "muse-spark-1.2-contributor": { "cost": [ @@ -41342,7 +53671,9 @@ 0.002, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "released": "2026-08-06" }, "muse-spark-1.3": { "cost": [ @@ -41351,7 +53682,9 @@ 0.15, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-09-02" }, "muse-spark-1.3-contributor": { "cost": [ @@ -41360,7 +53693,9 @@ 0.002, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "released": "2026-09-02" }, "muse-wonder-1.0": { "cost": [ @@ -41369,7 +53704,9 @@ 0.2, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-10-12" }, "nemotron-3-ultra-550b": { "cost": [ @@ -41378,7 +53715,11 @@ 0.1, 0.0 ], - "limit": 1048576 + "knowledge": "2025-09", + "limit": 1048576, + "max_output": 128000, + "open": true, + "released": "2026-06-04" }, "o3": { "cost": [ @@ -41387,7 +53728,10 @@ 0.5, 0.0 ], - "limit": 200000 + "knowledge": "2024-05", + "limit": 200000, + "max_output": 100000, + "released": "2025-04-16" }, "qwen-flash": { "cost": [ @@ -41396,7 +53740,10 @@ 0.01, 0.0625 ], - "limit": 1000000 + "knowledge": "2024-04", + "limit": 1000000, + "max_output": 32768, + "released": "2025-07-28" }, "qwen-max": { "cost": [ @@ -41405,7 +53752,10 @@ 0.0, 0.0 ], - "limit": 32768 + "knowledge": "2024-04", + "limit": 32768, + "max_output": 8192, + "released": "2024-04-03" }, "qwen-plus": { "cost": [ @@ -41414,7 +53764,11 @@ 0.08, 0.5 ], - "limit": 131072 + "knowledge": "2024-04", + "limit": 131072, + "max_output": 32768, + "reasoning": 4.0, + "released": "2024-01-25" }, "qwen-plus-latest": { "cost": [ @@ -41423,7 +53777,9 @@ 0.08, 0.5 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 8192, + "released": "2025-01-25" }, "qwen3-14b": { "cost": [ @@ -41432,34 +53788,9 @@ 0.0, 0.0 ], - "limit": 32768 - }, - "qwen3-235b-a22b-fp8": { - "cost": [ - 0.2, - 0.8, - 0.0, - 0.0 - ], - "limit": 40960 - }, - "qwen3-235b-a22b-instruct-2507": { - "cost": [ - 0.09, - 0.58, - 0.0, - 0.0 - ], - "limit": 262144 - }, - "qwen3-235b-a22b-thinking-2507": { - "cost": [ - 0.3, - 3.0, - 0.0, - 0.0 - ], - "limit": 262000 + "limit": 32768, + "max_output": 32768, + "released": "2025-04-28" }, "qwen3-30b-a3b": { "cost": [ @@ -41468,7 +53799,10 @@ 0.0, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 16384, + "open": true, + "released": "2025-04-28" }, "qwen3-32b": { "cost": [ @@ -41477,25 +53811,12 @@ 0.0, 0.0 ], - "limit": 40960 - }, - "qwen3-coder-30b-a3b-instruct": { - "cost": [ - 0.07, - 0.27, - 0.0, - 0.0 - ], - "limit": 262000 - }, - "qwen3-coder-480b-a35b-instruct": { - "cost": [ - 0.38, - 1.55, - 0.0, - 0.0 - ], - "limit": 262144 + "knowledge": "2025-04", + "limit": 40960, + "max_output": 16384, + "open": true, + "reasoning": 8.4, + "released": "2025-04-28" }, "qwen3-coder-flash": { "cost": [ @@ -41504,34 +53825,10 @@ 0.06, 0.375 ], - "limit": 997952 - }, - "qwen3-coder-next": { - "cost": [ - 0.108, - 0.675, - 0.06, - 0.0 - ], - "limit": 262144 - }, - "qwen3-max": { - "cost": [ - 0.845, - 3.38, - 0.6, - 3.75 - ], - "limit": 262144 - }, - "qwen3-next-80b-a3b-instruct": { - "cost": [ - 0.15, - 1.5, - 0.0, - 0.0 - ], - "limit": 131072 + "knowledge": "2025-04", + "limit": 997952, + "max_output": 65536, + "released": "2025-07-28" }, "qwen3-vl-235b-a22b-instruct": { "cost": [ @@ -41540,16 +53837,11 @@ 0.11, 0.0 ], - "limit": 262144 - }, - "qwen3-vl-235b-a22b-thinking": { - "cost": [ - 0.98, - 3.95, - 0.0, - 0.0 - ], - "limit": 131072 + "knowledge": "2025-03-31", + "limit": 262144, + "max_output": 8192, + "open": true, + "released": "2025-09-23" }, "qwen3-vl-30b-a3b-instruct": { "cost": [ @@ -41558,7 +53850,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 8192, + "open": true, + "released": "2025-10-04" }, "qwen3-vl-plus": { "cost": [ @@ -41567,7 +53862,11 @@ 0.04, 0.25 ], - "limit": 262144 + "knowledge": "2025-04", + "limit": 262144, + "max_output": 32768, + "reasoning": 4.8, + "released": "2025-09-23" }, "qwen3.5-122b-a10b": { "cost": [ @@ -41576,7 +53875,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-23" }, "qwen3.5-27b": { "cost": [ @@ -41585,7 +53887,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-23" }, "qwen3.5-35b-a3b": { "cost": [ @@ -41594,7 +53899,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-23" }, "qwen3.5-9b": { "cost": [ @@ -41603,7 +53911,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-23" }, "qwen3.6-27b": { "cost": [ @@ -41612,7 +53923,10 @@ 0.0, 0.0 ], - "limit": 16384 + "limit": 16384, + "max_output": 65536, + "open": true, + "released": "2026-04-22" }, "qwen3.6-35b-a3b": { "cost": [ @@ -41621,7 +53935,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-04-17" }, "qwen3.6-flash": { "cost": [ @@ -41630,7 +53947,9 @@ 0.05, 0.3125 ], - "limit": 983616 + "limit": 983616, + "max_output": 65536, + "released": "2026-04-27" }, "qwen3.6-plus": { "cost": [ @@ -41639,7 +53958,10 @@ 0.05, 0.625 ], + "knowledge": "2025-04", "limit": 983616, + "max_output": 65536, + "released": "2026-04-02", "tiers": [ { "cost": [ @@ -41662,7 +53984,9 @@ 0.006, 0.0375 ], - "limit": 983616 + "limit": 983616, + "max_output": 1000000, + "released": "2026-07-15" }, "qwen3.7-max": { "cost": [ @@ -41671,7 +53995,9 @@ 0.25, 3.125 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-05-21" }, "qwen3.7-plus": { "cost": [ @@ -41680,7 +54006,10 @@ 0.08, 0.5 ], - "limit": 983616 + "knowledge": "2025-04", + "limit": 983616, + "max_output": 64000, + "released": "2026-06-02" }, "qwen3.8-2.4t-a95b": { "cost": [ @@ -41689,7 +54018,10 @@ 0.25, 0.0 ], - "limit": 1010000 + "limit": 1010000, + "max_output": 131072, + "open": true, + "released": "2026-08-12" }, "qwen3.8-flash": { "cost": [ @@ -41698,7 +54030,9 @@ 0.016, 0.2 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-08-26" }, "qwen3.8-max": { "cost": [ @@ -41707,7 +54041,20 @@ 0.198, 2.5 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 1000000, + "released": "2026-07-19" + }, + "qwen3.8-omni-flash": { + "cost": [ + 0.15, + 0.47, + 0.016, + 0.0 + ], + "limit": 983616, + "max_output": 131072, + "released": "2026-09-17" }, "qwen35-397b-a17b": { "cost": [ @@ -41716,7 +54063,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-15" }, "reka-edge-2603": { "cost": [ @@ -41725,7 +54075,9 @@ 0.0, 0.0 ], - "limit": 16384 + "limit": 16384, + "max_output": 16384, + "released": "2026-10-09" }, "seed-1-6-250615": { "cost": [ @@ -41734,7 +54086,10 @@ 0.05, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 8192, + "open": true, + "released": "2025-06-25" }, "seed-1-6-250915": { "cost": [ @@ -41743,7 +54098,10 @@ 0.05, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 8192, + "open": true, + "released": "2025-09-15" }, "seed-1-6-flash-250715": { "cost": [ @@ -41752,7 +54110,10 @@ 0.015, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 8192, + "open": true, + "released": "2025-07-26" }, "seed-1-8-251228": { "cost": [ @@ -41761,7 +54122,10 @@ 0.05, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 8192, + "open": true, + "released": "2025-12-18" }, "seed-2-0-code-preview-260328": { "cost": [ @@ -41770,7 +54134,9 @@ 0.1, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "released": "2026-03-28" }, "seed-2-0-lite-260428": { "cost": [ @@ -41779,7 +54145,9 @@ 0.05, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "released": "2026-04-28" }, "seed-2-0-mini-260428": { "cost": [ @@ -41788,7 +54156,9 @@ 0.02, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "released": "2026-04-28" }, "seed-2-0-pro-260328": { "cost": [ @@ -41797,7 +54167,9 @@ 0.1, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "released": "2026-03-28" }, "sonar": { "cost": [ @@ -41806,7 +54178,10 @@ 0.0, 0.25 ], - "limit": 130000 + "knowledge": "2025-09-01", + "limit": 130000, + "max_output": 4096, + "released": "2024-01-01" }, "step-3.7-flash": { "cost": [ @@ -41815,7 +54190,11 @@ 0.04, 0.0 ], - "limit": 262144 + "knowledge": "2026-03-01", + "limit": 262144, + "max_output": 256000, + "open": true, + "released": "2026-05-29" } }, "name": "DevPass (LLM Gateway)" @@ -41829,7 +54208,11 @@ 0.04, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 393216, + "open": true, + "released": "2026-04-24" }, "alibaba/deepseek-v4-pro": { "cost": [ @@ -41838,7 +54221,11 @@ 0.2, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 393216, + "open": true, + "released": "2026-04-24" }, "alibaba/deepseek-v4.1-flash": { "cost": [ @@ -41847,7 +54234,11 @@ 0.03, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 393216, + "open": true, + "released": "2026-09-10" }, "alibaba/deepseek-v4.1-flash-1017": { "cost": [ @@ -41856,7 +54247,11 @@ 0.03, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 393216, + "open": true, + "released": "2026-10-17" }, "alibaba/glm-5": { "cost": [ @@ -41865,7 +54260,10 @@ 0.0, 0.0 ], - "limit": 202752 + "limit": 202752, + "max_output": 16384, + "open": true, + "released": "2026-02-12" }, "alibaba/glm-5.2": { "cost": [ @@ -41874,7 +54272,10 @@ 0.28, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "alibaba/glm-5.3": { "cost": [ @@ -41883,7 +54284,10 @@ 0.28, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "alibaba/kimi-k2.5": { "cost": [ @@ -41892,7 +54296,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 98304, + "open": true, + "released": "2026-01-27" }, "alibaba/kimi-k3": { "cost": [ @@ -41901,7 +54309,10 @@ 0.3, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-07-16" }, "alibaba/qwen-flash": { "cost": [ @@ -41910,7 +54321,10 @@ 0.01, 0.0625 ], - "limit": 1000000 + "knowledge": "2024-04", + "limit": 1000000, + "max_output": 32000, + "released": "2025-07-28" }, "alibaba/qwen-max": { "cost": [ @@ -41919,7 +54333,10 @@ 0.0, 0.0 ], - "limit": 32768 + "knowledge": "2024-04", + "limit": 32768, + "max_output": 8192, + "released": "2024-04-03" }, "alibaba/qwen-plus": { "cost": [ @@ -41928,7 +54345,10 @@ 0.08, 0.5 ], - "limit": 131072 + "knowledge": "2024-04", + "limit": 131072, + "max_output": 32000, + "released": "2024-01-25" }, "alibaba/qwen-plus-latest": { "cost": [ @@ -41937,7 +54357,9 @@ 0.08, 0.5 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 32000, + "released": "2024-09-09" }, "alibaba/qwen3-coder-flash": { "cost": [ @@ -41946,7 +54368,10 @@ 0.06, 0.375 ], - "limit": 997952 + "knowledge": "2025-04", + "limit": 997952, + "max_output": 65536, + "released": "2025-07-28" }, "alibaba/qwen3-vl-plus": { "cost": [ @@ -41955,7 +54380,10 @@ 0.04, 0.25 ], - "limit": 262144 + "knowledge": "2025-04", + "limit": 262144, + "max_output": 32768, + "released": "2025-09-23" }, "alibaba/qwen3.5-122b-a10b": { "cost": [ @@ -41964,7 +54392,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-23" }, "alibaba/qwen3.5-27b": { "cost": [ @@ -41973,7 +54404,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-23" }, "alibaba/qwen3.5-35b-a3b": { "cost": [ @@ -41982,7 +54416,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-23" }, "alibaba/qwen3.6-35b-a3b": { "cost": [ @@ -41991,7 +54428,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-04-17" }, "alibaba/qwen3.6-flash": { "cost": [ @@ -42000,7 +54440,9 @@ 0.05, 0.3125 ], - "limit": 983616 + "limit": 983616, + "max_output": 65536, + "released": "2026-04-27" }, "alibaba/qwen3.6-plus": { "cost": [ @@ -42009,7 +54451,10 @@ 0.05, 0.625 ], + "knowledge": "2025-04", "limit": 983616, + "max_output": 65536, + "released": "2026-04-02", "tiers": [ { "cost": [ @@ -42032,7 +54477,9 @@ 0.006, 0.0375 ], - "limit": 983616 + "limit": 983616, + "max_output": 65536, + "released": "2026-07-15" }, "alibaba/qwen3.7-max": { "cost": [ @@ -42041,7 +54488,9 @@ 0.5, 3.125 ], - "limit": 983616 + "limit": 983616, + "max_output": 65536, + "released": "2026-05-21" }, "alibaba/qwen3.7-plus": { "cost": [ @@ -42050,7 +54499,10 @@ 0.08, 0.5 ], - "limit": 983616 + "knowledge": "2025-04", + "limit": 983616, + "max_output": 65536, + "released": "2026-06-02" }, "alibaba/qwen3.8-flash": { "cost": [ @@ -42059,7 +54511,9 @@ 0.016, 0.2 ], - "limit": 983616 + "limit": 983616, + "max_output": 131072, + "released": "2026-08-26" }, "alibaba/qwen3.8-max": { "cost": [ @@ -42068,7 +54522,20 @@ 0.25, 2.5 ], - "limit": 983616 + "limit": 983616, + "max_output": 131072, + "released": "2026-08-03" + }, + "alibaba/qwen3.8-omni-flash": { + "cost": [ + 0.15, + 0.47, + 0.016, + 0.0 + ], + "limit": 983616, + "max_output": 131072, + "released": "2026-09-17" }, "alibaba/qwen35-397b-a17b": { "cost": [ @@ -42077,7 +54544,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-15" }, "anthropic/claude-fable-5": { "cost": [ @@ -42086,7 +54556,10 @@ 1.0, 12.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-09" }, "anthropic/claude-fable-5-1": { "cost": [ @@ -42095,7 +54568,10 @@ 0.25, 12.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-01" }, "anthropic/claude-haiku-4-5": { "cost": [ @@ -42104,7 +54580,10 @@ 0.1, 1.25 ], - "limit": 200000 + "knowledge": "2025-02-28", + "limit": 200000, + "max_output": 64000, + "released": "2025-10-15" }, "anthropic/claude-haiku-4-5-20251001": { "cost": [ @@ -42113,7 +54592,10 @@ 0.1, 1.25 ], - "limit": 200000 + "knowledge": "2025-02-28", + "limit": 200000, + "max_output": 64000, + "released": "2025-10-15" }, "anthropic/claude-haiku-5-5": { "cost": [ @@ -42122,7 +54604,10 @@ 0.01, 0.125 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-10-07" }, "anthropic/claude-opus-4-5-20251101": { "cost": [ @@ -42131,7 +54616,10 @@ 0.5, 6.25 ], - "limit": 200000 + "knowledge": "2025-05", + "limit": 200000, + "max_output": 32000, + "released": "2025-11-24" }, "anthropic/claude-opus-4-6": { "cost": [ @@ -42140,7 +54628,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2025-05-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-05" }, "anthropic/claude-opus-4-7": { "cost": [ @@ -42149,7 +54640,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-16" }, "anthropic/claude-opus-4-8": { "cost": [ @@ -42158,7 +54652,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-28" }, "anthropic/claude-opus-5": { "cost": [ @@ -42167,7 +54664,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-05", + "limit": 1000000, + "max_output": 128000, + "released": "2026-07-24" }, "anthropic/claude-opus-5-5": { "cost": [ @@ -42176,7 +54676,10 @@ 0.2, 5.0 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-22" }, "anthropic/claude-sonnet-4-5": { "cost": [ @@ -42185,7 +54688,10 @@ 0.3, 3.75 ], - "limit": 200000 + "knowledge": "2025-07-31", + "limit": 200000, + "max_output": 64000, + "released": "2025-09-29" }, "anthropic/claude-sonnet-4-5-20250929": { "cost": [ @@ -42194,7 +54700,10 @@ 0.3, 3.75 ], - "limit": 200000 + "knowledge": "2025-07-31", + "limit": 200000, + "max_output": 64000, + "released": "2025-09-29" }, "anthropic/claude-sonnet-4-6": { "cost": [ @@ -42203,7 +54712,10 @@ 0.3, 3.75 ], - "limit": 1000000 + "knowledge": "2025-08-31", + "limit": 1000000, + "max_output": 64000, + "released": "2026-02-17" }, "anthropic/claude-sonnet-5": { "cost": [ @@ -42212,7 +54724,10 @@ 0.2, 2.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-30" }, "anthropic/claude-sonnet-5-5": { "cost": [ @@ -42221,7 +54736,10 @@ 0.1, 2.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-28" }, "aws-bedrock/claude-fable-5": { "cost": [ @@ -42230,7 +54748,10 @@ 1.0, 12.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-09" }, "aws-bedrock/claude-fable-5-1": { "cost": [ @@ -42239,7 +54760,10 @@ 0.25, 12.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-01" }, "aws-bedrock/claude-haiku-4-5": { "cost": [ @@ -42248,7 +54772,10 @@ 0.1, 1.25 ], - "limit": 200000 + "knowledge": "2025-02-28", + "limit": 200000, + "max_output": 64000, + "released": "2025-10-15" }, "aws-bedrock/claude-haiku-4-5-20251001": { "cost": [ @@ -42257,7 +54784,10 @@ 0.1, 1.25 ], - "limit": 200000 + "knowledge": "2025-02-28", + "limit": 200000, + "max_output": 64000, + "released": "2025-10-15" }, "aws-bedrock/claude-haiku-5-5": { "cost": [ @@ -42266,7 +54796,10 @@ 0.01, 0.125 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-10-07" }, "aws-bedrock/claude-opus-4-5-20251101": { "cost": [ @@ -42275,7 +54808,10 @@ 0.5, 6.25 ], - "limit": 200000 + "knowledge": "2025-05", + "limit": 200000, + "max_output": 32000, + "released": "2025-11-24" }, "aws-bedrock/claude-opus-4-6": { "cost": [ @@ -42284,7 +54820,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2025-05-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-05" }, "aws-bedrock/claude-opus-4-7": { "cost": [ @@ -42293,7 +54832,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-16" }, "aws-bedrock/claude-opus-4-8": { "cost": [ @@ -42302,7 +54844,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-28" }, "aws-bedrock/claude-opus-5": { "cost": [ @@ -42311,7 +54856,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-05", + "limit": 1000000, + "max_output": 128000, + "released": "2026-07-24" }, "aws-bedrock/claude-opus-5-5": { "cost": [ @@ -42320,7 +54868,10 @@ 0.2, 5.0 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-22" }, "aws-bedrock/claude-sonnet-4-5": { "cost": [ @@ -42329,7 +54880,10 @@ 0.3, 3.75 ], - "limit": 200000 + "knowledge": "2025-07-31", + "limit": 200000, + "max_output": 8192, + "released": "2025-09-29" }, "aws-bedrock/claude-sonnet-4-5-20250929": { "cost": [ @@ -42338,7 +54892,10 @@ 0.3, 3.75 ], - "limit": 200000 + "knowledge": "2025-07-31", + "limit": 200000, + "max_output": 8192, + "released": "2025-09-29" }, "aws-bedrock/claude-sonnet-4-6": { "cost": [ @@ -42347,7 +54904,10 @@ 0.3, 3.75 ], - "limit": 1000000 + "knowledge": "2025-08-31", + "limit": 1000000, + "max_output": 64000, + "released": "2026-02-17" }, "aws-bedrock/claude-sonnet-5": { "cost": [ @@ -42356,7 +54916,10 @@ 0.2, 2.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-30" }, "aws-bedrock/claude-sonnet-5-5": { "cost": [ @@ -42365,7 +54928,10 @@ 0.1, 2.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-28" }, "aws-bedrock/grok-4-3": { "cost": [ @@ -42375,6 +54941,8 @@ 0.0 ], "limit": 1000000, + "max_output": 131072, + "released": "2026-04-17", "tiers": [ { "cost": [ @@ -42397,7 +54965,10 @@ 0.5, 0.0 ], - "limit": 500000 + "knowledge": "2026-02-01", + "limit": 500000, + "max_output": 500000, + "released": "2026-08-12" }, "aws-bedrock/grok-4-7": { "cost": [ @@ -42406,7 +54977,10 @@ 0.5, 0.0 ], - "limit": 524288 + "knowledge": "2026-05", + "limit": 524288, + "max_output": 524288, + "released": "2026-09-21" }, "aws-bedrock/kimi-k3": { "cost": [ @@ -42415,7 +54989,10 @@ 0.3, 3.75 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-07-16" }, "aws-bedrock/llama-3.1-70b-instruct": { "cost": [ @@ -42424,7 +55001,11 @@ 0.0, 0.0 ], + "knowledge": "2023-12", "limit": 128000, + "max_output": 2048, + "open": true, + "released": "2024-07-23", "status": "deprecated" }, "aws-bedrock/llama-4-maverick-17b-instruct": { @@ -42434,7 +55015,11 @@ 0.0, 0.0 ], + "knowledge": "2024-08", "limit": 8192, + "max_output": 2048, + "open": true, + "released": "2025-04-05", "status": "deprecated" }, "aws-bedrock/llama-4-scout-17b-instruct": { @@ -42444,7 +55029,11 @@ 0.0, 0.0 ], + "knowledge": "2024-08", "limit": 8192, + "max_output": 2048, + "open": true, + "released": "2025-04-05", "status": "deprecated" }, "aws-mantle/gpt-5.6-luna": { @@ -42454,7 +55043,10 @@ 0.022, 0.275 ], - "limit": 921600 + "knowledge": "2026-02-16", + "limit": 921600, + "max_output": 128000, + "released": "2026-07-09" }, "aws-mantle/gpt-5.6-sol": { "cost": [ @@ -42463,7 +55055,10 @@ 0.44, 5.5 ], - "limit": 921600 + "knowledge": "2026-02-16", + "limit": 921600, + "max_output": 128000, + "released": "2026-07-09" }, "aws-mantle/gpt-5.6-terra": { "cost": [ @@ -42472,7 +55067,10 @@ 0.22, 2.75 ], - "limit": 921600 + "knowledge": "2026-02-16", + "limit": 921600, + "max_output": 128000, + "released": "2026-07-09" }, "aws-mantle/gpt-6-astra": { "cost": [ @@ -42481,16 +55079,10 @@ 1.0, 12.5 ], - "limit": 1050000 - }, - "azure-ai-foundry/grok-4-1-fast-non-reasoning": { - "cost": [ - 0.2, - 0.5, - 0.0, - 0.0 - ], - "limit": 2000000 + "knowledge": "2026-04-30", + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-04" }, "azure-ai-foundry/grok-4-1-fast-reasoning": { "cost": [ @@ -42499,7 +55091,9 @@ 0.0, 0.0 ], - "limit": 2000000 + "limit": 2000000, + "max_output": 30000, + "released": "2025-11-19" }, "azure-ai-foundry/grok-4-3": { "cost": [ @@ -42509,6 +55103,8 @@ 0.0 ], "limit": 20000, + "max_output": 8192, + "released": "2026-04-17", "tiers": [ { "cost": [ @@ -42531,7 +55127,10 @@ 1.0, 12.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-09" }, "azure-anthropic/claude-fable-5-1": { "cost": [ @@ -42540,7 +55139,10 @@ 0.25, 12.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-01" }, "azure-anthropic/claude-opus-4-6": { "cost": [ @@ -42549,7 +55151,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2025-05-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-05" }, "azure-anthropic/claude-opus-4-7": { "cost": [ @@ -42558,7 +55163,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-16" }, "azure-anthropic/claude-opus-4-8": { "cost": [ @@ -42567,7 +55175,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-28" }, "azure-anthropic/claude-opus-5": { "cost": [ @@ -42576,7 +55187,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-05", + "limit": 1000000, + "max_output": 128000, + "released": "2026-07-24" }, "azure-anthropic/claude-opus-5-5": { "cost": [ @@ -42585,7 +55199,10 @@ 0.2, 5.0 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-22" }, "azure-anthropic/claude-sonnet-5": { "cost": [ @@ -42594,7 +55211,10 @@ 0.2, 2.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-30" }, "azure-anthropic/claude-sonnet-5-5": { "cost": [ @@ -42603,7 +55223,10 @@ 0.1, 2.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-28" }, "azure/gpt-4.1": { "cost": [ @@ -42612,7 +55235,10 @@ 0.5, 0.0 ], - "limit": 1000000 + "knowledge": "2024-04", + "limit": 1000000, + "max_output": 32768, + "released": "2025-04-14" }, "azure/gpt-4.1-mini": { "cost": [ @@ -42621,7 +55247,10 @@ 0.1, 0.0 ], - "limit": 1000000 + "knowledge": "2024-04", + "limit": 1000000, + "max_output": 32768, + "released": "2025-04-14" }, "azure/gpt-4o": { "cost": [ @@ -42630,7 +55259,10 @@ 1.25, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-05-13" }, "azure/gpt-5": { "cost": [ @@ -42639,7 +55271,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "azure/gpt-5-mini": { "cost": [ @@ -42648,7 +55283,10 @@ 0.025, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "azure/gpt-5-nano": { "cost": [ @@ -42657,7 +55295,10 @@ 0.005, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "azure/gpt-5.1": { "cost": [ @@ -42666,7 +55307,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "azure/gpt-5.1-codex": { "cost": [ @@ -42675,7 +55319,10 @@ 0.0, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 272000, + "released": "2025-11-13" }, "azure/gpt-5.1-codex-mini": { "cost": [ @@ -42684,7 +55331,10 @@ 0.025, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "azure/gpt-5.2": { "cost": [ @@ -42693,7 +55343,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "azure/gpt-5.2-codex": { "cost": [ @@ -42702,7 +55355,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "azure/gpt-5.3-codex": { "cost": [ @@ -42711,7 +55367,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-02-05" }, "azure/gpt-5.4": { "cost": [ @@ -42720,7 +55379,10 @@ 0.25, 0.0 ], - "limit": 1050000 + "knowledge": "2025-08-31", + "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05" }, "azure/gpt-5.4-mini": { "cost": [ @@ -42729,7 +55391,10 @@ 0.075, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "azure/gpt-5.4-nano": { "cost": [ @@ -42738,7 +55403,10 @@ 0.02, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "azure/gpt-5.4-pro": { "cost": [ @@ -42747,7 +55415,10 @@ 0.0, 0.0 ], - "limit": 1050000 + "knowledge": "2025-08-31", + "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05" }, "azure/gpt-5.5": { "cost": [ @@ -42756,7 +55427,10 @@ 0.5, 0.0 ], + "knowledge": "2025-12-01", "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23", "tiers": [ { "cost": [ @@ -42779,7 +55453,10 @@ 0.02, 0.25 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "azure/gpt-5.6-sol": { "cost": [ @@ -42788,7 +55465,10 @@ 0.4, 5.0 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "azure/gpt-5.6-terra": { "cost": [ @@ -42797,7 +55477,10 @@ 0.2, 2.5 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "azure/gpt-6-astra": { "cost": [ @@ -42806,7 +55489,10 @@ 1.0, 12.5 ], - "limit": 1050000 + "knowledge": "2026-04-30", + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-04" }, "azure/gpt-6-luna": { "cost": [ @@ -42815,7 +55501,10 @@ 0.01, 0.125 ], - "limit": 1050000 + "knowledge": "2026-05-18", + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22" }, "azure/gpt-6-sol": { "cost": [ @@ -42824,7 +55513,10 @@ 0.2, 2.5 ], - "limit": 1050000 + "knowledge": "2026-04-20", + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22" }, "azure/gpt-6.1-sol": { "cost": [ @@ -42833,7 +55525,10 @@ 0.1, 2.5 ], - "limit": 1050000 + "knowledge": "2026-04-30", + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-29" }, "azure/gpt-oss-120b": { "cost": [ @@ -42842,7 +55537,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "baidu/deepseek-v4-flash": { "cost": [ @@ -42851,7 +55550,11 @@ 0.014, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-04-24" }, "baidu/deepseek-v4-pro": { "cost": [ @@ -42860,7 +55563,11 @@ 0.042, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-04-24" }, "baidu/deepseek-v4.1-flash": { "cost": [ @@ -42869,7 +55576,24 @@ 0.006, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 393216, + "open": true, + "released": "2026-09-10" + }, + "baidu/deepseek-v4.1-flash-1017": { + "cost": [ + 0.28, + 1.13, + 0.006, + 0.0 + ], + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 393216, + "open": true, + "released": "2026-10-17" }, "baidu/glm-5.1": { "cost": [ @@ -42878,7 +55602,10 @@ 0.26, 0.0 ], - "limit": 202752 + "limit": 202752, + "max_output": 131072, + "open": true, + "released": "2026-04-07" }, "baidu/glm-5.2": { "cost": [ @@ -42887,7 +55614,10 @@ 0.26, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "baidu/glm-5.3": { "cost": [ @@ -42896,16 +55626,22 @@ 0.26, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, - "baidu/kimi-k2.6": { + "baidu/glm-5.3-flash": { "cost": [ - 0.95, - 4.0, - 0.16, + 0.15, + 0.5, + 0.03, 0.0 ], - "limit": 262144 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-08-26" }, "bytedance/deepseek-v3.2": { "cost": [ @@ -42914,7 +55650,11 @@ 0.056, 0.0 ], - "limit": 131072 + "knowledge": "2024-07", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-12-01" }, "bytedance/deepseek-v4-flash": { "cost": [ @@ -42923,7 +55663,11 @@ 0.014, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 393216, + "open": true, + "released": "2026-04-24" }, "bytedance/deepseek-v4-pro": { "cost": [ @@ -42932,7 +55676,11 @@ 0.044, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 393216, + "open": true, + "released": "2026-04-24" }, "bytedance/glm-4.7": { "cost": [ @@ -42941,7 +55689,11 @@ 0.11, 0.0 ], - "limit": 200000 + "knowledge": "2025-04", + "limit": 200000, + "max_output": 128000, + "open": true, + "released": "2025-12-22" }, "bytedance/glm-5.2": { "cost": [ @@ -42950,7 +55702,10 @@ 0.26, 0.0 ], - "limit": 1024000 + "limit": 1024000, + "max_output": 128000, + "open": true, + "released": "2026-06-13" }, "bytedance/gpt-oss-120b": { "cost": [ @@ -42959,7 +55714,11 @@ 0.02, 0.0 ], - "limit": 128000 + "knowledge": "2024-06", + "limit": 128000, + "max_output": 32000, + "open": true, + "released": "2025-08-05" }, "bytedance/seed-1-6-250615": { "cost": [ @@ -42968,7 +55727,9 @@ 0.05, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 256000, + "released": "2025-06-25" }, "bytedance/seed-1-6-250915": { "cost": [ @@ -42977,7 +55738,9 @@ 0.05, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 256000, + "released": "2025-09-15" }, "bytedance/seed-1-6-flash-250715": { "cost": [ @@ -42986,7 +55749,9 @@ 0.015, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 256000, + "released": "2025-07-26" }, "bytedance/seed-1-8-251228": { "cost": [ @@ -42995,7 +55760,9 @@ 0.05, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 256000, + "released": "2025-12-18" }, "bytedance/seed-2-0-code-preview-260328": { "cost": [ @@ -43004,7 +55771,9 @@ 0.1, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 131072, + "released": "2026-03-28" }, "bytedance/seed-2-0-lite-260428": { "cost": [ @@ -43013,7 +55782,9 @@ 0.05, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 131072, + "released": "2026-04-28" }, "bytedance/seed-2-0-mini-260428": { "cost": [ @@ -43022,7 +55793,9 @@ 0.02, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 131072, + "released": "2026-04-28" }, "bytedance/seed-2-0-pro-260328": { "cost": [ @@ -43031,7 +55804,9 @@ 0.1, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 131072, + "released": "2026-03-28" }, "canopywave/deepseek-v4-flash": { "cost": [ @@ -43040,7 +55815,11 @@ 0.03, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 393216, + "open": true, + "released": "2026-04-24" }, "canopywave/deepseek-v4-pro": { "cost": [ @@ -43049,7 +55828,11 @@ 0.01, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 393216, + "open": true, + "released": "2026-04-24" }, "canopywave/glm-5.2": { "cost": [ @@ -43058,7 +55841,10 @@ 0.26, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 32768, + "open": true, + "released": "2026-06-13" }, "canopywave/kimi-k2.6": { "cost": [ @@ -43067,7 +55853,11 @@ 0.16, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-04-20" }, "canopywave/kimi-k3": { "cost": [ @@ -43076,52 +55866,86 @@ 0.3, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-07-16" }, - "cerebras/gemma-4-31b-it": { + "cerebras/gpt-oss-120b": { "cost": [ - 0.99, - 1.49, + 0.35, + 0.75, 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, - "cerebras/glm-4.7": { + "cloudflare/deepseek-v4-flash": { "cost": [ - 2.25, - 2.75, - 0.0, + 0.44, + 1.32, + 0.014, 0.0 ], - "limit": 200000 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 393216, + "open": true, + "released": "2026-04-24" }, - "cerebras/gpt-oss-120b": { + "cloudflare/deepseek-v4-pro": { "cost": [ - 0.35, - 0.75, - 0.0, + 1.32, + 3.96, + 0.044, 0.0 ], - "limit": 131072 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 393216, + "open": true, + "released": "2026-04-24" }, - "cerebras/llama-3.3-70b-instruct": { + "cloudflare/deepseek-v4.1-flash-1017": { "cost": [ - 0.85, + 0.3, 1.2, - 0.0, + 0.006, 0.0 ], - "limit": 128000 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 393216, + "open": true, + "released": "2026-10-17" }, - "cerebras/qwen3-235b-a22b-instruct-2507": { + "cloudflare/glm-5.3": { "cost": [ - 0.6, - 1.2, - 0.0, + 1.4, + 4.4, + 0.26, + 0.0 + ], + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-08-14" + }, + "cloudflare/glm-5.3-flash": { + "cost": [ + 0.15, + 0.5, + 0.03, 0.0 ], - "limit": 262000 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-08-26" }, "consensusprotocol/Qwen3.8-27B": { "cost": [ @@ -43130,7 +55954,10 @@ 0.05, 0.0 ], - "limit": 262000 + "limit": 262000, + "max_output": 32768, + "open": true, + "released": "2026-08-14" }, "consensusprotocol/deepseek-v4-flash": { "cost": [ @@ -43139,7 +55966,11 @@ 0.005, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "consensusprotocol/deepseek-v4.1-flash": { "cost": [ @@ -43148,7 +55979,11 @@ 0.005, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-09-10" }, "consensusprotocol/gemma-4-31b-it": { "cost": [ @@ -43157,7 +55992,11 @@ 0.01, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-04-02" }, "consensusprotocol/glm-5.3-flash": { "cost": [ @@ -43166,7 +56005,10 @@ 0.01, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-08-26" }, "consensusprotocol/gpt-oss-20b": { "cost": [ @@ -43175,7 +56017,11 @@ 0.01, 0.0 ], - "limit": 128000 + "knowledge": "2024-06", + "limit": 128000, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "consensusprotocol/mimo-v2.6-flash": { "cost": [ @@ -43184,7 +56030,10 @@ 0.0025, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-09-22" }, "consensusprotocol/minimax-m3": { "cost": [ @@ -43193,7 +56042,10 @@ 0.05, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 512000, + "open": true, + "released": "2026-06-01" }, "deepinfra/deepseek-v3.2": { "cost": [ @@ -43202,7 +56054,11 @@ 0.13, 0.0 ], - "limit": 160000 + "knowledge": "2024-07", + "limit": 160000, + "max_output": 65536, + "open": true, + "released": "2025-12-01" }, "deepinfra/deepseek-v4-flash": { "cost": [ @@ -43211,7 +56067,11 @@ 0.016, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 393216, + "open": true, + "released": "2026-04-24" }, "deepinfra/deepseek-v4-pro": { "cost": [ @@ -43220,7 +56080,11 @@ 0.1, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 64000, + "open": true, + "released": "2026-04-24" }, "deepinfra/deepseek-v4.1-flash": { "cost": [ @@ -43229,7 +56093,11 @@ 0.006, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 393216, + "open": true, + "released": "2026-09-10" }, "deepinfra/deepseek-v4.1-flash-1017": { "cost": [ @@ -43238,7 +56106,11 @@ 0.006, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 393216, + "open": true, + "released": "2026-10-17" }, "deepinfra/gemma-4-26b-a4b-it": { "cost": [ @@ -43247,7 +56119,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-04-02" }, "deepinfra/gemma-4-31b-it": { "cost": [ @@ -43256,7 +56131,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-04-02" }, "deepinfra/granite-4.2-8b": { "cost": [ @@ -43265,7 +56144,10 @@ 0.015, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 117964, + "open": true, + "released": "2026-08-25" }, "deepinfra/ling-3.0-flash": { "cost": [ @@ -43274,7 +56156,10 @@ 0.012, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-07-23" }, "deepinfra/ling-3.0-flash-vl": { "cost": [ @@ -43283,7 +56168,10 @@ 0.012, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2026-09-10" }, "deepinfra/mimo-v2.6-flash": { "cost": [ @@ -43292,7 +56180,10 @@ 0.0028, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65536, + "open": true, + "released": "2026-09-22" }, "deepinfra/mimo-v2.6-pro": { "cost": [ @@ -43301,7 +56192,10 @@ 0.0036, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65536, + "open": true, + "released": "2026-09-22" }, "deepinfra/muse-glimmer-30b": { "cost": [ @@ -43310,7 +56204,11 @@ 0.04, 0.0 ], - "limit": 131072 + "knowledge": "2026-01-04", + "limit": 131072, + "max_output": 16384, + "open": true, + "released": "2026-08-10" }, "deepinfra/nemotron-3-ultra-550b": { "cost": [ @@ -43319,7 +56217,9 @@ 0.1, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "released": "2026-06-01" }, "deepinfra/qwen3-vl-235b-a22b-instruct": { "cost": [ @@ -43328,7 +56228,11 @@ 0.11, 0.0 ], - "limit": 262144 + "knowledge": "2025-03-31", + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2025-09-23" }, "deepinfra/qwen3-vl-30b-a3b-instruct": { "cost": [ @@ -43337,7 +56241,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2025-10-04" }, "deepinfra/qwen3.5-9b": { "cost": [ @@ -43346,7 +56253,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-02-23" }, "deepseek/deepseek-v4-pro": { "cost": [ @@ -43355,16 +56265,11 @@ 0.003625, 0.0 ], - "limit": 1050000 - }, - "deepseek/deepseek-v4.1-flash": { - "cost": [ - 0.15, - 0.6, - 0.003, - 0.0 - ], - "limit": 1050000 + "knowledge": "2025-05", + "limit": 1050000, + "max_output": 393216, + "open": true, + "released": "2026-04-24" }, "deepseek/deepseek-v4.1-flash-1017": { "cost": [ @@ -43373,97 +56278,37 @@ 0.003, 0.0 ], - "limit": 1050000 + "knowledge": "2025-05", + "limit": 1050000, + "max_output": 393216, + "open": true, + "released": "2026-10-17" }, - "embercloud/glm-4.5": { + "entrim/deepseek-v4.1-flash": { "cost": [ + 0.2, 0.6, - 2.2, - 0.11, - 0.0 - ], - "limit": 131000 - }, - "embercloud/glm-4.5-air": { - "cost": [ - 0.13, - 0.85, - 0.025, - 0.0 - ], - "limit": 131000 - }, - "embercloud/glm-4.7": { - "cost": [ - 0.38, - 1.98, - 0.19, - 0.0 - ], - "limit": 200000 - }, - "embercloud/glm-4.7-flash": { - "cost": [ - 0.06, - 0.4, - 0.01, - 0.0 - ], - "limit": 200000 - }, - "embercloud/glm-5": { - "cost": [ - 0.72, - 2.3, - 0.144, - 0.0 - ], - "limit": 203000 - }, - "embercloud/glm-5.1": { - "cost": [ - 0.931, - 2.93, - 0.173, - 0.0 - ], - "limit": 203000 - }, - "embercloud/glm-5.2": { - "cost": [ - 1.26, - 3.96, - 0.234, - 0.0 - ], - "limit": 203000 - }, - "embercloud/kimi-k2.5": { - "cost": [ - 0.405, - 1.98, - 0.225, - 0.0 - ], - "limit": 262144 - }, - "embercloud/qwen3-coder-next": { - "cost": [ - 0.108, - 0.675, - 0.06, + 0.005, 0.0 ], - "limit": 262144 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-09-10" }, - "entrim/deepseek-v4.1-flash": { + "entrim/deepseek-v4.1-flash-1017": { "cost": [ 0.2, - 0.6, + 0.8, 0.005, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-10-17" }, "entrim/glm-5.3": { "cost": [ @@ -43472,7 +56317,10 @@ 0.15, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "entrim/glm-5.3-flash": { "cost": [ @@ -43481,7 +56329,10 @@ 0.0175, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-08-26" }, "fireworks/deepseek-v4.1-flash": { "cost": [ @@ -43490,7 +56341,11 @@ 0.007, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 393216, + "open": true, + "released": "2026-09-10" }, "fireworks/glm-5.3": { "cost": [ @@ -43499,7 +56354,10 @@ 0.26, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "fireworks/glm-5.3-flash": { "cost": [ @@ -43508,7 +56366,10 @@ 0.03, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-08-26" }, "fireworks/kimi-k3": { "cost": [ @@ -43517,7 +56378,10 @@ 0.3, 0.0 ], - "limit": 1040384 + "limit": 1040384, + "max_output": 1040384, + "open": true, + "released": "2026-07-16" }, "fireworks/kimi-k3-fast": { "cost": [ @@ -43526,129 +56390,154 @@ 0.45, 0.0 ], - "limit": 1040384 + "limit": 1040384, + "max_output": 1040384, + "open": true, + "released": "2026-07-16" }, - "gonka24/minimax-m2.7": { + "google-ai-studio/gemini-3-flash-preview": { "cost": [ - 0.08, - 0.32, - 0.017, + 0.5, + 3.0, + 0.05, 0.0 ], - "limit": 204800 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65535, + "released": "2025-12-17" }, - "google-ai-studio/gemini-3-flash-preview": { + "google-ai-studio/gemini-3.1-flash-lite": { + "cost": [ + 0.25, + 1.5, + 0.025, + 0.08333 + ], + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-05-07" + }, + "google-ai-studio/gemini-3.1-pro-preview": { + "cost": [ + 2.0, + 12.0, + 0.2, + 0.0 + ], + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-02-19", + "tiers": [ + { + "cost": [ + 4.0, + 18.0, + 0.4, + 0.0 + ], + "tier": { + "size": 200000, + "type": "context" + } + } + ] + }, + "google-ai-studio/gemini-3.5-flash-lite": { + "cost": [ + 0.3, + 2.5, + 0.03, + 0.08333 + ], + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-07-21" + }, + "google-ai-studio/gemini-3.6-flash": { + "cost": [ + 0.75, + 3.75, + 0.075, + 0.08333 + ], + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-07-21" + }, + "google-ai-studio/gemini-3.8-flash": { + "cost": [ + 0.75, + 3.75, + 0.075, + 0.08333 + ], + "limit": 1048576, + "max_output": 65536, + "released": "2026-09-02" + }, + "google-ai-studio/gemini-4-argon": { + "cost": [ + 4.0, + 20.0, + 0.2, + 0.375 + ], + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 1048576, + "released": "2026-10-13" + }, + "google-ai-studio/gemini-pro-latest": { + "cost": [ + 2.0, + 12.0, + 0.2, + 0.0 + ], + "limit": 1048576, + "max_output": 65536, + "released": "2026-02-27" + }, + "google-vertex/gemini-3-flash-preview": { "cost": [ 0.5, 3.0, 0.05, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65535, + "released": "2025-12-17" }, - "google-ai-studio/gemini-3.1-flash-lite": { + "google-vertex/gemini-3.1-flash-lite": { "cost": [ 0.25, 1.5, 0.025, 0.08333 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-05-07" }, - "google-ai-studio/gemini-3.1-pro-preview": { - "cost": [ - 2.0, - 12.0, - 0.2, - 0.0 - ], - "limit": 1048576, - "tiers": [ - { - "cost": [ - 4.0, - 18.0, - 0.4, - 0.0 - ], - "tier": { - "size": 200000, - "type": "context" - } - } - ] - }, - "google-ai-studio/gemini-3.5-flash-lite": { - "cost": [ - 0.3, - 2.5, - 0.03, - 0.08333 - ], - "limit": 1048576 - }, - "google-ai-studio/gemini-3.6-flash": { - "cost": [ - 0.75, - 3.75, - 0.075, - 0.08333 - ], - "limit": 1048576 - }, - "google-ai-studio/gemini-3.8-flash": { - "cost": [ - 0.75, - 3.75, - 0.075, - 0.08333 - ], - "limit": 1048576 - }, - "google-ai-studio/gemini-4-argon": { - "cost": [ - 4.0, - 20.0, - 0.2, - 0.375 - ], - "limit": 1048576 - }, - "google-ai-studio/gemini-pro-latest": { - "cost": [ - 2.0, - 12.0, - 0.2, - 0.0 - ], - "limit": 1048576 - }, - "google-vertex/gemini-3-flash-preview": { - "cost": [ - 0.5, - 3.0, - 0.05, - 0.0 - ], - "limit": 1048576 - }, - "google-vertex/gemini-3.1-flash-lite": { - "cost": [ - 0.25, - 1.5, - 0.025, - 0.08333 - ], - "limit": 1048576 - }, - "google-vertex/gemini-3.1-pro-preview": { + "google-vertex/gemini-3.1-pro-preview": { "cost": [ 2.0, 12.0, 0.2, 0.0 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2026-02-19", "tiers": [ { "cost": [ @@ -43671,7 +56560,10 @@ 0.15, 0.08333 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-05-19" }, "google-vertex/gemini-3.5-flash-lite": { "cost": [ @@ -43680,7 +56572,10 @@ 0.03, 0.08333 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-07-21" }, "google-vertex/gemini-3.6-flash": { "cost": [ @@ -43689,7 +56584,10 @@ 0.075, 0.08333 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-07-21" }, "google-vertex/gemini-3.7-flash": { "cost": [ @@ -43698,7 +56596,10 @@ 0.075, 0.08333 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-08-13" }, "google-vertex/gemini-3.8-flash": { "cost": [ @@ -43707,7 +56608,9 @@ 0.075, 0.08333 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65536, + "released": "2026-09-02" }, "google-vertex/gemini-4-argon": { "cost": [ @@ -43716,7 +56619,10 @@ 0.2, 0.375 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 1048576, + "released": "2026-10-13" }, "greenference/glm-5.3-flash": { "cost": [ @@ -43725,7 +56631,10 @@ 0.028, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-08-26" }, "greenference/qwen3-14b": { "cost": [ @@ -43734,7 +56643,9 @@ 0.0, 0.0 ], - "limit": 16384 + "limit": 16384, + "max_output": 8192, + "released": "2025-04-28" }, "greenference/qwen3-30b-a3b": { "cost": [ @@ -43743,7 +56654,10 @@ 0.0, 0.0 ], - "limit": 8192 + "limit": 8192, + "max_output": 4096, + "open": true, + "released": "2025-04-28" }, "greenference/qwen3.6-27b": { "cost": [ @@ -43752,7 +56666,10 @@ 0.0, 0.0 ], - "limit": 16384 + "limit": 16384, + "max_output": 8192, + "open": true, + "released": "2026-04-22" }, "groq/gpt-oss-120b": { "cost": [ @@ -43761,7 +56678,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 32766, + "open": true, + "released": "2025-08-05" }, "groq/gpt-oss-20b": { "cost": [ @@ -43770,7 +56691,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 32766, + "open": true, + "released": "2025-08-05" }, "inference.net/deepseek-v4.1-flash-1017": { "cost": [ @@ -43779,7 +56704,11 @@ 0.007, 0.0 ], - "limit": 262144 + "knowledge": "2025-05", + "limit": 262144, + "max_output": 131072, + "open": true, + "released": "2026-10-17" }, "inference.net/glm-5.3": { "cost": [ @@ -43788,7 +56717,10 @@ 0.15, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "inference.net/glm-5.3-flash": { "cost": [ @@ -43797,7 +56729,10 @@ 0.02, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 128000, + "open": true, + "released": "2026-08-26" }, "inference.net/llama-3.2-11b-instruct": { "cost": [ @@ -43806,7 +56741,20 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 128000, + "released": "2024-09-25" + }, + "inference.net/minimax-m3.1-flash": { + "cost": [ + 0.1, + 0.5, + 0.005, + 0.0 + ], + "limit": 1000000, + "max_output": 524288, + "released": "2026-10-19" }, "luminal/deepseek-v4.1-flash": { "cost": [ @@ -43815,7 +56763,11 @@ 0.0027, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-09-10" }, "meta-contributor/muse-spark-1.2-contributor": { "cost": [ @@ -43824,7 +56776,9 @@ 0.002, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-08-06" }, "meta-contributor/muse-spark-1.3-contributor": { "cost": [ @@ -43833,7 +56787,9 @@ 0.002, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "released": "2026-09-02" }, "meta/muse-spark-1.1": { "cost": [ @@ -43842,7 +56798,9 @@ 0.15, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-04-08" }, "meta/muse-spark-1.2": { "cost": [ @@ -43851,7 +56809,9 @@ 0.15, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-08-05" }, "meta/muse-spark-1.3": { "cost": [ @@ -43860,7 +56820,9 @@ 0.15, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "released": "2026-09-02" }, "meta/muse-wonder-1.0": { "cost": [ @@ -43869,7 +56831,9 @@ 0.2, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "released": "2026-10-12" }, "minimax/minimax-m2": { "cost": [ @@ -43878,7 +56842,10 @@ 0.03, 0.0 ], - "limit": 196608 + "limit": 196608, + "max_output": 131072, + "open": true, + "released": "2025-10-27" }, "minimax/minimax-m2.1": { "cost": [ @@ -43887,7 +56854,10 @@ 0.0, 0.0 ], - "limit": 196608 + "limit": 196608, + "max_output": 131072, + "open": true, + "released": "2025-12-23" }, "minimax/minimax-m2.1-lightning": { "cost": [ @@ -43896,7 +56866,9 @@ 0.0, 0.0 ], - "limit": 196608 + "limit": 196608, + "max_output": 131072, + "released": "2025-12-23" }, "minimax/minimax-m2.5": { "cost": [ @@ -43905,7 +56877,10 @@ 0.03, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 131100, + "open": true, + "released": "2026-02-12" }, "minimax/minimax-m2.5-highspeed": { "cost": [ @@ -43914,7 +56889,10 @@ 0.03, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 131100, + "open": true, + "released": "2026-02-13" }, "minimax/minimax-m2.7": { "cost": [ @@ -43923,7 +56901,10 @@ 0.06, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 131100, + "open": true, + "released": "2026-03-18" }, "minimax/minimax-m2.7-highspeed": { "cost": [ @@ -43932,7 +56913,10 @@ 0.06, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 131100, + "open": true, + "released": "2026-03-18" }, "minimax/minimax-m3": { "cost": [ @@ -43941,7 +56925,10 @@ 0.12, 0.0 ], - "limit": 512000 + "limit": 512000, + "max_output": 131072, + "open": true, + "released": "2026-06-01" }, "minimax/minimax-m3.1-flash": { "cost": [ @@ -43950,7 +56937,9 @@ 0.015, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 524288, + "released": "2026-10-19" }, "minimax/minimax-text-01": { "cost": [ @@ -43959,7 +56948,9 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2025-01-15" }, "mistral/codestral-2508": { "cost": [ @@ -43968,7 +56959,9 @@ 0.0, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 256000, + "released": "2025-07-30" }, "mistral/devstral-2512": { "cost": [ @@ -43977,7 +56970,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-12", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2025-12-09" }, "mistral/glm-5.3": { "cost": [ @@ -43986,7 +56983,10 @@ 0.14, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "mistral/ministral-14b-2512": { "cost": [ @@ -43995,7 +56995,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2025-12-02" }, "mistral/ministral-3b-2512": { "cost": [ @@ -44004,7 +57007,10 @@ 0.0, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2025-12-02" }, "mistral/ministral-8b-2512": { "cost": [ @@ -44013,7 +57019,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2025-12-02" }, "mistral/mistral-large-2512": { "cost": [ @@ -44022,7 +57031,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2024-11", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2025-12-02" }, "mistral/mistral-large-4": { "cost": [ @@ -44031,7 +57044,9 @@ 0.14, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 262144, + "released": "2026-10-06" }, "mistral/mistral-large-latest": { "cost": [ @@ -44040,7 +57055,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-11", + "limit": 128000, + "max_output": 262144, + "open": true, + "released": "2024-11-01" }, "mistral/mistral-medium-3-5": { "cost": [ @@ -44049,7 +57068,9 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "released": "2026-04-30" }, "mistral/mistral-small-2506": { "cost": [ @@ -44058,7 +57079,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2025-03", + "limit": 128000, + "max_output": 16384, + "open": true, + "released": "2025-06-20" }, "mistral/mistral-small-2603": { "cost": [ @@ -44067,7 +57092,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-06", + "limit": 262144, + "max_output": 256000, + "open": true, + "released": "2026-03-16" }, "moonshot/kimi-k2.5": { "cost": [ @@ -44076,7 +57105,11 @@ 0.1, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-01-27" }, "moonshot/kimi-k2.6": { "cost": [ @@ -44085,7 +57118,11 @@ 0.16, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-20" }, "moonshot/kimi-k2.7-code": { "cost": [ @@ -44094,7 +57131,11 @@ 0.19, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-06-12" }, "moonshot/kimi-k2.7-code-highspeed": { "cost": [ @@ -44103,7 +57144,11 @@ 0.38, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-06-12" }, "moonshot/kimi-k3": { "cost": [ @@ -44112,16 +57157,43 @@ 0.3, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-07-16" }, - "novita/deepseek-v3.2": { + "moonshot/kimi-k3.1-pro": { "cost": [ - 0.269, - 0.4, - 0.1345, + 2.0, + 10.0, + 0.2, + 2.0 + ], + "limit": 1048576, + "max_output": 1048576, + "released": "2026-10-23" + }, + "moonshot/kimi-k3.1-pro-highspeed": { + "cost": [ + 4.0, + 20.0, + 0.2, + 4.0 + ], + "limit": 1048576, + "max_output": 1048576, + "released": "2026-10-23" + }, + "nebius/minimax-m3.1-flash": { + "cost": [ + 0.15, + 0.6, + 0.015, 0.0 ], - "limit": 163840 + "limit": 1048576, + "max_output": 1048576, + "released": "2026-10-19" }, "novita/deepseek-v4-flash": { "cost": [ @@ -44130,7 +57202,11 @@ 0.028, 0.0 ], - "limit": 1050000 + "knowledge": "2025-05", + "limit": 1050000, + "max_output": 393216, + "open": true, + "released": "2026-04-24" }, "novita/deepseek-v4.1-flash": { "cost": [ @@ -44139,7 +57215,11 @@ 0.006, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 393216, + "open": true, + "released": "2026-09-10" }, "novita/deepseek-v4.1-flash-1017": { "cost": [ @@ -44148,16 +57228,11 @@ 0.006, 0.0 ], - "limit": 1048576 - }, - "novita/ernie-4.5-vl-424b-a47b": { - "cost": [ - 0.42, - 1.25, - 0.0, - 0.0 - ], - "limit": 123000 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 393216, + "open": true, + "released": "2026-10-17" }, "novita/gemma-4-26b-a4b-it": { "cost": [ @@ -44166,7 +57241,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-04-02" }, "novita/gemma-4-31b-it": { "cost": [ @@ -44175,7 +57253,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-04-02" }, "novita/glm-4.5v": { "cost": [ @@ -44184,7 +57266,11 @@ 0.11, 0.0 ], - "limit": 65536 + "knowledge": "2025-04", + "limit": 65536, + "max_output": 16000, + "open": true, + "released": "2025-08-11" }, "novita/glm-4.6": { "cost": [ @@ -44193,7 +57279,11 @@ 0.11, 0.0 ], - "limit": 204800 + "knowledge": "2025-04", + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-09-30" }, "novita/glm-4.6v": { "cost": [ @@ -44202,7 +57292,11 @@ 0.055, 0.0 ], - "limit": 131072 + "knowledge": "2025-04", + "limit": 131072, + "max_output": 16000, + "open": true, + "released": "2025-12-08" }, "novita/glm-4.7": { "cost": [ @@ -44211,7 +57305,11 @@ 0.11, 0.0 ], - "limit": 204800 + "knowledge": "2025-04", + "limit": 204800, + "max_output": 128000, + "open": true, + "released": "2025-12-22" }, "novita/glm-5": { "cost": [ @@ -44220,7 +57318,10 @@ 0.2, 0.0 ], - "limit": 202800 + "limit": 202800, + "max_output": 131072, + "open": true, + "released": "2026-02-12" }, "novita/glm-5.1": { "cost": [ @@ -44229,7 +57330,10 @@ 0.26, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-04-07" }, "novita/glm-5.2": { "cost": [ @@ -44238,7 +57342,10 @@ 0.26, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "novita/glm-5.3": { "cost": [ @@ -44247,7 +57354,10 @@ 0.26, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "novita/glm-5.3-flash": { "cost": [ @@ -44256,7 +57366,10 @@ 0.03, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-08-26" }, "novita/hy3": { "cost": [ @@ -44265,7 +57378,10 @@ 0.035, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-07-06" }, "novita/kimi-k2": { "cost": [ @@ -44274,7 +57390,9 @@ 0.0, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 131072, + "released": "2025-07-11" }, "novita/kimi-k2.6": { "cost": [ @@ -44283,7 +57401,11 @@ 0.16, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-20" }, "novita/kimi-k2.7-code": { "cost": [ @@ -44292,7 +57414,11 @@ 0.19, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-06-12" }, "novita/kimi-k3": { "cost": [ @@ -44301,7 +57427,10 @@ 0.3, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-07-16" }, "novita/ling-3.0-flash": { "cost": [ @@ -44310,25 +57439,10 @@ 0.012, 0.0 ], - "limit": 262144 - }, - "novita/llama-3-70b-instruct": { - "cost": [ - 0.51, - 0.74, - 0.0, - 0.0 - ], - "limit": 8192 - }, - "novita/llama-3.2-3b-instruct": { - "cost": [ - 0.03, - 0.05, - 0.0, - 0.0 - ], - "limit": 32768 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-07-23" }, "novita/llama-3.3-70b-instruct": { "cost": [ @@ -44337,7 +57451,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2023-12", + "limit": 131072, + "max_output": 120000, + "open": true, + "released": "2024-12-06" }, "novita/llama-4-maverick-17b-instruct": { "cost": [ @@ -44346,7 +57464,11 @@ 0.0, 0.0 ], - "limit": 1048576 + "knowledge": "2024-08", + "limit": 1048576, + "max_output": 8192, + "open": true, + "released": "2025-04-05" }, "novita/llama-4-scout-17b-instruct": { "cost": [ @@ -44355,16 +57477,11 @@ 0.0, 0.0 ], - "limit": 131072 - }, - "novita/minimax-m2.1": { - "cost": [ - 0.3, - 1.2, - 0.03, - 0.0 - ], - "limit": 204800 + "knowledge": "2024-08", + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2025-04-05" }, "novita/minimax-m2.5": { "cost": [ @@ -44373,7 +57490,10 @@ 0.03, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 131100, + "open": true, + "released": "2026-02-12" }, "novita/minimax-m2.7": { "cost": [ @@ -44382,88 +57502,21 @@ 0.06, 0.0 ], - "limit": 204800 - }, - "novita/qwen3-235b-a22b-fp8": { - "cost": [ - 0.2, - 0.8, - 0.0, - 0.0 - ], - "limit": 40960 - }, - "novita/qwen3-235b-a22b-instruct-2507": { - "cost": [ - 0.09, - 0.58, - 0.0, - 0.0 - ], - "limit": 131072 - }, - "novita/qwen3-235b-a22b-thinking-2507": { - "cost": [ - 0.3, - 3.0, - 0.0, - 0.0 - ], - "limit": 131072 - }, - "novita/qwen3-coder-30b-a3b-instruct": { - "cost": [ - 0.07, - 0.27, - 0.0, - 0.0 - ], - "limit": 160000 - }, - "novita/qwen3-coder-480b-a35b-instruct": { - "cost": [ - 0.38, - 1.55, - 0.0, - 0.0 - ], - "limit": 262144 - }, - "novita/qwen3-max": { - "cost": [ - 0.845, - 3.38, - 0.0, - 0.0 - ], - "limit": 262144 + "limit": 204800, + "max_output": 131100, + "open": true, + "released": "2026-03-18" }, - "novita/qwen3-next-80b-a3b-instruct": { + "novita/minimax-m3.1-flash": { "cost": [ 0.15, - 1.5, - 0.0, - 0.0 - ], - "limit": 131072 - }, - "novita/qwen3-vl-235b-a22b-instruct": { - "cost": [ - 0.3, - 1.5, - 0.0, - 0.0 - ], - "limit": 131072 - }, - "novita/qwen3-vl-235b-a22b-thinking": { - "cost": [ - 0.98, - 3.95, - 0.0, + 0.6, + 0.015, 0.0 ], - "limit": 131072 + "limit": 1000000, + "max_output": 524288, + "released": "2026-10-19" }, "novita/qwen3-vl-30b-a3b-instruct": { "cost": [ @@ -44472,7 +57525,10 @@ 0.0, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-10-04" }, "novita/qwen3.5-122b-a10b": { "cost": [ @@ -44481,7 +57537,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-23" }, "novita/qwen3.6-35b-a3b": { "cost": [ @@ -44490,7 +57549,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 64000, + "open": true, + "released": "2026-04-17" }, "novita/qwen3.7-max": { "cost": [ @@ -44499,7 +57561,9 @@ 0.25, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 65536, + "released": "2026-05-21" }, "novita/qwen3.8-2.4t-a95b": { "cost": [ @@ -44508,7 +57572,10 @@ 0.25, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-12" }, "novita/qwen3.8-27b": { "cost": [ @@ -44517,7 +57584,10 @@ 0.085, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "novita/qwen3.8-flash": { "cost": [ @@ -44526,7 +57596,9 @@ 0.016, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-08-26" }, "novita/qwen3.8-max": { "cost": [ @@ -44535,7 +57607,9 @@ 0.25, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-08-03" }, "novita/qwen35-397b-a17b": { "cost": [ @@ -44544,7 +57618,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 64000, + "open": true, + "released": "2026-02-15" }, "novita/step-3.7-flash": { "cost": [ @@ -44553,7 +57630,11 @@ 0.04, 0.0 ], - "limit": 262144 + "knowledge": "2026-03-01", + "limit": 262144, + "max_output": 256000, + "open": true, + "released": "2026-05-29" }, "openai/gpt-4.1": { "cost": [ @@ -44562,7 +57643,10 @@ 0.5, 0.0 ], - "limit": 1000000 + "knowledge": "2024-04", + "limit": 1000000, + "max_output": 32768, + "released": "2025-04-14" }, "openai/gpt-4.1-mini": { "cost": [ @@ -44571,7 +57655,10 @@ 0.1, 0.0 ], - "limit": 1000000 + "knowledge": "2024-04", + "limit": 1000000, + "max_output": 32768, + "released": "2025-04-14" }, "openai/gpt-4o": { "cost": [ @@ -44580,7 +57667,10 @@ 1.25, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-05-13" }, "openai/gpt-4o-mini": { "cost": [ @@ -44589,7 +57679,10 @@ 0.075, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-07-18" }, "openai/gpt-4o-mini-transcribe": { "cost": [ @@ -44598,7 +57691,9 @@ 0.0, 0.0 ], - "limit": 16000 + "limit": 16000, + "max_output": 2000, + "released": "2025-03-20" }, "openai/gpt-4o-transcribe": { "cost": [ @@ -44607,7 +57702,9 @@ 0.0, 0.0 ], - "limit": 16000 + "limit": 16000, + "max_output": 2000, + "released": "2025-03-20" }, "openai/gpt-5": { "cost": [ @@ -44616,7 +57713,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "openai/gpt-5-mini": { "cost": [ @@ -44625,7 +57725,10 @@ 0.025, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "openai/gpt-5-nano": { "cost": [ @@ -44634,7 +57737,10 @@ 0.005, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "openai/gpt-5-pro": { "cost": [ @@ -44643,7 +57749,10 @@ 0.0, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 272000, + "released": "2025-10-06" }, "openai/gpt-5.1": { "cost": [ @@ -44652,7 +57761,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "openai/gpt-5.2": { "cost": [ @@ -44661,7 +57773,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "openai/gpt-5.2-pro": { "cost": [ @@ -44670,7 +57785,10 @@ 0.0, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 272000, + "released": "2025-12-11" }, "openai/gpt-5.3-codex": { "cost": [ @@ -44679,7 +57797,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-02-05" }, "openai/gpt-5.4": { "cost": [ @@ -44688,7 +57809,10 @@ 0.25, 0.0 ], - "limit": 1050000 + "knowledge": "2025-08-31", + "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05" }, "openai/gpt-5.4-mini": { "cost": [ @@ -44697,7 +57821,10 @@ 0.075, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "openai/gpt-5.4-nano": { "cost": [ @@ -44706,7 +57833,10 @@ 0.02, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "openai/gpt-5.4-pro": { "cost": [ @@ -44715,7 +57845,10 @@ 0.0, 0.0 ], - "limit": 1050000 + "knowledge": "2025-08-31", + "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05" }, "openai/gpt-5.5": { "cost": [ @@ -44724,7 +57857,10 @@ 0.5, 0.0 ], + "knowledge": "2025-12-01", "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23", "tiers": [ { "cost": [ @@ -44747,7 +57883,10 @@ 0.0, 0.0 ], + "knowledge": "2025-12-01", "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23", "tiers": [ { "cost": [ @@ -44770,7 +57909,10 @@ 0.02, 0.25 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "openai/gpt-5.6-sol": { "cost": [ @@ -44779,7 +57921,10 @@ 0.4, 5.0 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "openai/gpt-5.6-terra": { "cost": [ @@ -44788,7 +57933,10 @@ 0.2, 2.5 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "openai/gpt-6-astra": { "cost": [ @@ -44797,7 +57945,10 @@ 1.0, 12.5 ], - "limit": 1050000 + "knowledge": "2026-04-30", + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-04" }, "openai/gpt-6-luna": { "cost": [ @@ -44806,7 +57957,10 @@ 0.01, 0.125 ], - "limit": 1050000 + "knowledge": "2026-05-18", + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22" }, "openai/gpt-6-sol": { "cost": [ @@ -44815,7 +57969,10 @@ 0.2, 2.5 ], - "limit": 1050000 + "knowledge": "2026-04-20", + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22" }, "openai/gpt-6.1-sol": { "cost": [ @@ -44824,7 +57981,22 @@ 0.1, 2.5 ], - "limit": 1050000 + "knowledge": "2026-04-30", + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-29" + }, + "openai/gpt-6.1-terra": { + "cost": [ + 1.0, + 5.0, + 0.05, + 1.25 + ], + "knowledge": "2026-06-01", + "limit": 1050000, + "max_output": 128000, + "released": "2026-10-26" }, "openai/gpt-live-transcribe": { "cost": [ @@ -44832,7 +58004,9 @@ 0.0, 0.0, 0.0 - ] + ], + "released": "2026-07-28", + "type": "transcription" }, "openai/gpt-transcribe": { "cost": [ @@ -44840,7 +58014,9 @@ 0.0, 0.0, 0.0 - ] + ], + "released": "2026-07-28", + "type": "transcription" }, "openai/o3": { "cost": [ @@ -44849,7 +58025,10 @@ 0.5, 0.0 ], - "limit": 200000 + "knowledge": "2024-05", + "limit": 200000, + "max_output": 100000, + "released": "2025-04-16" }, "perplexity/sonar": { "cost": [ @@ -44858,7 +58037,10 @@ 0.0, 0.25 ], - "limit": 130000 + "knowledge": "2025-09-01", + "limit": 130000, + "max_output": 4096, + "released": "2024-01-01" }, "quartz/gemini-3.1-pro-preview": { "cost": [ @@ -44867,7 +58049,10 @@ 0.2, 0.0 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2026-02-19", "tiers": [ { "cost": [ @@ -44890,52 +58075,61 @@ 0.028, 0.0 ], - "limit": 1000000 - }, - "reka-ai/deepseek-v4-pro": { - "cost": [ - 1.2, - 3.3, - 0.13, - 0.0 - ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 393216, + "open": true, + "released": "2026-04-24" }, "reka-ai/deepseek-v4.1-flash": { "cost": [ - 0.3, - 1.2, - 0.006, + 0.15, + 0.6, + 0.009, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 393216, + "open": true, + "released": "2026-09-10" }, "reka-ai/deepseek-v4.1-flash-1017": { "cost": [ - 0.15, - 0.6, - 0.003, + 0.16, + 0.64, + 0.006, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 393216, + "open": true, + "released": "2026-10-17" }, "reka-ai/glm-5.3": { "cost": [ - 1.17, - 3.96, - 0.234, + 0.45, + 1.8, + 0.135, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 262144, + "open": true, + "released": "2026-08-14" }, "reka-ai/glm-5.3-flash": { "cost": [ 0.15, 0.5, - 0.02, + 0.027, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-08-26" }, "reka-ai/reka-edge-2603": { "cost": [ @@ -44944,7 +58138,9 @@ 0.0, 0.0 ], - "limit": 16384 + "limit": 16384, + "max_output": 16384, + "released": "2026-10-09" }, "runpod/kimi-k3": { "cost": [ @@ -44953,7 +58149,10 @@ 0.3, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-07-16" }, "runware/deepseek-v4-flash": { "cost": [ @@ -44962,7 +58161,11 @@ 0.014, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "runware/deepseek-v4-pro": { "cost": [ @@ -44971,7 +58174,11 @@ 0.079, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "runware/deepseek-v4.1-flash": { "cost": [ @@ -44980,7 +58187,24 @@ 0.01, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-09-10" + }, + "runware/deepseek-v4.1-flash-1017": { + "cost": [ + 0.15, + 0.6, + 0.01, + 0.0 + ], + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-10-17" }, "runware/gemma-4-31b-it": { "cost": [ @@ -44989,7 +58213,11 @@ 0.012, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-04-02" }, "runware/glm-5.2": { "cost": [ @@ -44998,7 +58226,10 @@ 0.16, 0.0 ], - "limit": 1024000 + "limit": 1024000, + "max_output": 128000, + "open": true, + "released": "2026-06-13" }, "runware/glm-5.3": { "cost": [ @@ -45007,7 +58238,10 @@ 0.2, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "runware/glm-5.3-flash": { "cost": [ @@ -45016,7 +58250,10 @@ 0.03, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-26" }, "runware/gpt-oss-120b": { "cost": [ @@ -45025,7 +58262,11 @@ 0.032, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "runware/kimi-k2.6": { "cost": [ @@ -45034,7 +58275,11 @@ 0.13, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 131072, + "open": true, + "released": "2026-04-20" }, "runware/kimi-k3": { "cost": [ @@ -45043,7 +58288,10 @@ 0.3, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-07-16" }, "sakana/fugu-max": { "cost": [ @@ -45052,7 +58300,9 @@ 0.25, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 1000000, + "released": "2026-09-11" }, "sakana/fugu-ultra": { "cost": [ @@ -45061,7 +58311,9 @@ 0.5, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 1000000, + "released": "2026-06-15" }, "sakana/fugu-ultra-v2.0": { "cost": [ @@ -45070,7 +58322,23 @@ 0.5, 0.0 ], - "limit": 1000000 + "knowledge": "2026-08-28", + "limit": 1000000, + "max_output": 1000000, + "released": "2026-09-11" + }, + "sciforium/deepseek-v4.1-flash-1017": { + "cost": [ + 0.15, + 0.6, + 0.003, + 0.0 + ], + "knowledge": "2025-05", + "limit": 1056784, + "max_output": 384000, + "open": true, + "released": "2026-10-17" }, "scx-ai-gp/deepseek-v4.1-flash": { "cost": [ @@ -45079,7 +58347,11 @@ 0.01, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-09-10" }, "scx-ai-gp/glm-5.2": { "cost": [ @@ -45088,7 +58360,10 @@ 0.154, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "scx-ai-gp/glm-5.2-fast": { "cost": [ @@ -45097,7 +58372,10 @@ 0.429, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "scx-ai-gp/glm-5.3": { "cost": [ @@ -45106,7 +58384,10 @@ 0.1716, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 128000, + "open": true, + "released": "2026-08-14" }, "scx-ai-gp/glm-5.3-fast": { "cost": [ @@ -45115,7 +58396,10 @@ 0.56, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 128000, + "open": true, + "released": "2026-08-14" }, "scx-ai-gp/glm-5.3-flash": { "cost": [ @@ -45124,7 +58408,10 @@ 0.025, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-08-26" }, "scx-ai-gp/kimi-k2.7-code": { "cost": [ @@ -45133,7 +58420,11 @@ 0.143, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-06-12" }, "scx-ai-gp/kimi-k3": { "cost": [ @@ -45142,7 +58433,10 @@ 0.319, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-07-16" }, "scx-ai-gp/qwen3.8-max": { "cost": [ @@ -45151,7 +58445,9 @@ 0.198, 2.5 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-08-03" }, "scx-ai/gpt-oss-120b": { "cost": [ @@ -45160,7 +58456,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "scx-ai/minimax-m2.7": { "cost": [ @@ -45169,7 +58469,10 @@ 0.05, 0.0 ], - "limit": 196608 + "limit": 196608, + "max_output": 196608, + "open": true, + "released": "2026-03-18" }, "scx-ai/qwen3-32b": { "cost": [ @@ -45178,7 +58481,11 @@ 0.0, 0.0 ], - "limit": 32768 + "knowledge": "2025-04", + "limit": 32768, + "max_output": 8192, + "open": true, + "released": "2025-04-28" }, "tencent/deepseek-v4-flash": { "cost": [ @@ -45187,7 +58494,11 @@ 0.0028, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 393216, + "open": true, + "released": "2026-04-24" }, "tencent/deepseek-v4-pro": { "cost": [ @@ -45196,7 +58507,11 @@ 0.00363, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 393216, + "open": true, + "released": "2026-04-24" }, "tencent/glm-5": { "cost": [ @@ -45205,7 +58520,10 @@ 0.2, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 128000, + "open": true, + "released": "2026-02-12" }, "tencent/glm-5-turbo": { "cost": [ @@ -45214,7 +58532,9 @@ 0.24, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 128000, + "released": "2026-03-16" }, "tencent/glm-5.1": { "cost": [ @@ -45223,7 +58543,10 @@ 0.26, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 128000, + "open": true, + "released": "2026-04-07" }, "tencent/glm-5.2": { "cost": [ @@ -45232,7 +58555,10 @@ 0.26, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 128000, + "open": true, + "released": "2026-06-13" }, "tencent/glm-5v-turbo": { "cost": [ @@ -45241,7 +58567,9 @@ 0.24, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 128000, + "released": "2026-04-01" }, "tencent/hy-mt2-plus": { "cost": [ @@ -45250,7 +58578,9 @@ 0.0, 0.0 ], - "limit": 8192 + "limit": 8192, + "max_output": 4096, + "released": "2026-05-21" }, "tencent/hy3": { "cost": [ @@ -45259,7 +58589,10 @@ 0.033, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 131072, + "open": true, + "released": "2026-07-06" }, "tencent/hy4-preview": { "cost": [ @@ -45268,7 +58601,10 @@ 0.042, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 65536, + "open": true, + "released": "2026-08-28" }, "tencent/kimi-k2.6": { "cost": [ @@ -45277,7 +58613,11 @@ 0.145, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-20" }, "tencent/kimi-k2.7-code": { "cost": [ @@ -45286,7 +58626,11 @@ 0.19, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-06-12" }, "tencent/kimi-k2.7-code-highspeed": { "cost": [ @@ -45295,7 +58639,11 @@ 0.38, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-06-12" }, "tencent/kimi-k3": { "cost": [ @@ -45304,7 +58652,10 @@ 0.3, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-07-16" }, "tencent/minimax-m2.7": { "cost": [ @@ -45313,7 +58664,10 @@ 0.06, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 128000, + "open": true, + "released": "2026-03-18" }, "tencent/minimax-m3": { "cost": [ @@ -45322,7 +58676,10 @@ 0.06, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-01" }, "together-ai/deepseek-v4-pro": { "cost": [ @@ -45331,7 +58688,11 @@ 0.13, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 163840, + "open": true, + "released": "2026-04-24" }, "together-ai/deepseek-v4.1-flash": { "cost": [ @@ -45340,7 +58701,11 @@ 0.006, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 393216, + "open": true, + "released": "2026-09-10" }, "together-ai/deepseek-v4.1-flash-1017": { "cost": [ @@ -45349,7 +58714,11 @@ 0.006, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 393216, + "open": true, + "released": "2026-10-17" }, "together-ai/glm-4.7": { "cost": [ @@ -45358,7 +58727,11 @@ 0.0, 0.0 ], - "limit": 202752 + "knowledge": "2025-04", + "limit": 202752, + "max_output": 128000, + "open": true, + "released": "2025-12-22" }, "together-ai/glm-5.3": { "cost": [ @@ -45367,7 +58740,10 @@ 0.26, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 943717, + "open": true, + "released": "2026-08-14" }, "together-ai/glm-5.3-flash": { "cost": [ @@ -45376,7 +58752,10 @@ 0.03, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 943717, + "open": true, + "released": "2026-08-26" }, "together-ai/gpt-oss-120b": { "cost": [ @@ -45385,7 +58764,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "together-ai/kimi-k3": { "cost": [ @@ -45394,7 +58777,10 @@ 0.3, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 1000000, + "open": true, + "released": "2026-07-16" }, "together-ai/minimax-m3": { "cost": [ @@ -45403,7 +58789,21 @@ 0.06, 0.0 ], - "limit": 524288 + "limit": 524288, + "max_output": 131072, + "open": true, + "released": "2026-06-01" + }, + "together-ai/minimax-m3.1-flash": { + "cost": [ + 0.15, + 0.6, + 0.015, + 0.0 + ], + "limit": 1048576, + "max_output": 1048576, + "released": "2026-10-19" }, "together-ai/muse-glimmer-30b": { "cost": [ @@ -45412,7 +58812,11 @@ 0.04, 0.0 ], - "limit": 131072 + "knowledge": "2026-01-04", + "limit": 131072, + "max_output": 117964, + "open": true, + "released": "2026-08-10" }, "together-ai/qwen3.8-2.4t-a95b": { "cost": [ @@ -45421,7 +58825,10 @@ 0.25, 0.0 ], - "limit": 1010000 + "limit": 1010000, + "max_output": 909000, + "open": true, + "released": "2026-08-12" }, "vertex-anthropic/claude-haiku-4-5": { "cost": [ @@ -45430,7 +58837,10 @@ 0.1, 1.25 ], - "limit": 200000 + "knowledge": "2025-02-28", + "limit": 200000, + "max_output": 64000, + "released": "2025-10-15" }, "vertex-anthropic/claude-opus-4-5-20251101": { "cost": [ @@ -45439,7 +58849,10 @@ 0.5, 6.25 ], - "limit": 200000 + "knowledge": "2025-05", + "limit": 200000, + "max_output": 32000, + "released": "2025-11-24" }, "vertex-anthropic/claude-opus-4-6": { "cost": [ @@ -45448,7 +58861,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2025-05-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-05" }, "vertex-anthropic/claude-opus-4-7": { "cost": [ @@ -45457,7 +58873,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-16" }, "vertex-anthropic/claude-sonnet-4-5": { "cost": [ @@ -45466,7 +58885,10 @@ 0.3, 3.75 ], - "limit": 200000 + "knowledge": "2025-07-31", + "limit": 200000, + "max_output": 64000, + "released": "2025-09-29" }, "vertex-anthropic/claude-sonnet-4-6": { "cost": [ @@ -45475,7 +58897,10 @@ 0.3, 3.75 ], - "limit": 1000000 + "knowledge": "2025-08-31", + "limit": 1000000, + "max_output": 64000, + "released": "2026-02-17" }, "vertex-anthropic/claude-sonnet-5": { "cost": [ @@ -45484,7 +58909,10 @@ 0.2, 2.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-30" }, "vertex-openai/grok-4-20-non-reasoning": { "cost": [ @@ -45494,6 +58922,8 @@ 0.0 ], "limit": 2000000, + "max_output": 30000, + "released": "2026-03-09", "tiers": [ { "cost": [ @@ -45517,6 +58947,8 @@ 0.0 ], "limit": 2000000, + "max_output": 30000, + "released": "2026-03-09", "tiers": [ { "cost": [ @@ -45539,7 +58971,10 @@ 0.5, 0.0 ], - "limit": 500000 + "knowledge": "2026-02-01", + "limit": 500000, + "max_output": 500000, + "released": "2026-08-12" }, "vertex-openai/grok-4-7": { "cost": [ @@ -45548,7 +58983,10 @@ 0.5, 0.0 ], - "limit": 524288 + "knowledge": "2026-05", + "limit": 524288, + "max_output": 524288, + "released": "2026-09-21" }, "xai/grok-4": { "cost": [ @@ -45557,7 +58995,9 @@ 0.75, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 256000, + "released": "2025-07-09" }, "xai/grok-4-20-beta-0309-non-reasoning": { "cost": [ @@ -45567,6 +59007,8 @@ 0.0 ], "limit": 2000000, + "max_output": 30000, + "released": "2026-03-09", "tiers": [ { "cost": [ @@ -45590,6 +59032,8 @@ 0.0 ], "limit": 2000000, + "max_output": 30000, + "released": "2026-03-09", "tiers": [ { "cost": [ @@ -45613,6 +59057,8 @@ 0.0 ], "limit": 1000000, + "max_output": 1000000, + "released": "2026-04-17", "tiers": [ { "cost": [ @@ -45635,7 +59081,9 @@ 0.3, 0.0 ], - "limit": 500000 + "limit": 500000, + "max_output": 500000, + "released": "2026-07-08" }, "xai/grok-4-6": { "cost": [ @@ -45644,7 +59092,10 @@ 0.5, 0.0 ], - "limit": 500000 + "knowledge": "2026-02-01", + "limit": 500000, + "max_output": 500000, + "released": "2026-08-12" }, "xai/grok-4-7": { "cost": [ @@ -45653,7 +59104,10 @@ 0.5, 0.0 ], - "limit": 500000 + "knowledge": "2026-05", + "limit": 500000, + "max_output": 500000, + "released": "2026-09-21" }, "xai/grok-build-0-1": { "cost": [ @@ -45663,6 +59117,8 @@ 0.0 ], "limit": 256000, + "max_output": 256000, + "released": "2026-04-16", "tiers": [ { "cost": [ @@ -45685,7 +59141,10 @@ 0.0028, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-09-22" }, "xiaomi/mimo-v2.6-pro": { "cost": [ @@ -45694,7 +59153,10 @@ 0.0036, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-09-22" }, "zai/glm-4-32b-0414-128k": { "cost": [ @@ -45703,7 +59165,9 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 128000, + "released": "2025-04-14" }, "zai/glm-4.5": { "cost": [ @@ -45712,7 +59176,11 @@ 0.11, 0.0 ], - "limit": 128000 + "knowledge": "2025-04", + "limit": 128000, + "max_output": 98304, + "open": true, + "released": "2025-07-28" }, "zai/glm-4.5-air": { "cost": [ @@ -45721,7 +59189,11 @@ 0.03, 0.0 ], - "limit": 128000 + "knowledge": "2025-04", + "limit": 128000, + "max_output": 98304, + "open": true, + "released": "2025-07-28" }, "zai/glm-4.5-airx": { "cost": [ @@ -45730,7 +59202,9 @@ 0.22, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 128000, + "released": "2025-07-28" }, "zai/glm-4.5-x": { "cost": [ @@ -45739,7 +59213,9 @@ 0.45, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 128000, + "released": "2025-07-28" }, "zai/glm-4.5v": { "cost": [ @@ -45748,7 +59224,11 @@ 0.11, 0.0 ], - "limit": 128000 + "knowledge": "2025-04", + "limit": 128000, + "max_output": 16000, + "open": true, + "released": "2025-08-11" }, "zai/glm-4.6": { "cost": [ @@ -45757,7 +59237,11 @@ 0.11, 0.0 ], - "limit": 200000 + "knowledge": "2025-04", + "limit": 200000, + "max_output": 131072, + "open": true, + "released": "2025-09-30" }, "zai/glm-4.6v": { "cost": [ @@ -45766,7 +59250,11 @@ 0.05, 0.0 ], - "limit": 128000 + "knowledge": "2025-04", + "limit": 128000, + "max_output": 16000, + "open": true, + "released": "2025-12-08" }, "zai/glm-4.6v-flashx": { "cost": [ @@ -45775,7 +59263,9 @@ 0.004, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 16000, + "released": "2025-12-08" }, "zai/glm-4.7": { "cost": [ @@ -45784,7 +59274,11 @@ 0.11, 0.0 ], - "limit": 200000 + "knowledge": "2025-04", + "limit": 200000, + "max_output": 128000, + "open": true, + "released": "2025-12-22" }, "zai/glm-4.7-flashx": { "cost": [ @@ -45793,7 +59287,11 @@ 0.01, 0.0 ], - "limit": 200000 + "knowledge": "2025-04", + "limit": 200000, + "max_output": 128000, + "open": true, + "released": "2026-01-19" }, "zai/glm-5": { "cost": [ @@ -45802,7 +59300,10 @@ 0.2, 0.0 ], - "limit": 202800 + "limit": 202800, + "max_output": 131100, + "open": true, + "released": "2026-02-12" }, "zai/glm-5.1": { "cost": [ @@ -45811,7 +59312,10 @@ 0.26, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 128000, + "open": true, + "released": "2026-04-07" }, "zai/glm-5.2": { "cost": [ @@ -45820,7 +59324,10 @@ 0.26, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 128000, + "open": true, + "released": "2026-06-13" }, "zai/glm-5.3": { "cost": [ @@ -45829,7 +59336,10 @@ 0.26, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 128000, + "open": true, + "released": "2026-08-14" }, "zai/glm-5.3-flash": { "cost": [ @@ -45838,7 +59348,10 @@ 0.03, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-08-26" } }, "name": "LLM Gateway" @@ -45852,7 +59365,10 @@ 0.04, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-08-14" } }, "name": "LLM Tech" @@ -45866,7 +59382,11 @@ 0.5, 0.0 ], - "limit": 131072 + "knowledge": "2025-01", + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2026-04-02" }, "google/gemini-2.5-flash-lite": { "cost": [ @@ -45875,7 +59395,10 @@ 0.0, 0.0 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2025-06-17", "status": "deprecated" }, "magibu-11b-v8": { @@ -45885,7 +59408,9 @@ 0.0, 0.0 ], - "limit": 8192 + "limit": 8192, + "max_output": 8192, + "released": "2026-06-05" }, "medgemma-4b": { "cost": [ @@ -45895,6 +59420,9 @@ 0.0 ], "limit": 8192, + "max_output": 8192, + "open": true, + "released": "2026-04-26", "status": "deprecated" }, "meta/muse-spark-1.2-contributor": { @@ -45904,7 +59432,9 @@ 0.002, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-08-05" }, "mimo/mimo-v2.5": { "cost": [ @@ -45913,7 +59443,11 @@ 0.0, 0.0 ], + "knowledge": "2024-12", "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-04-22", "status": "deprecated" }, "mimo/mimo-v2.5-pro": { @@ -45923,7 +59457,11 @@ 0.0, 0.0 ], + "knowledge": "2024-12", "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-04-22", "status": "deprecated" }, "mistral/voxtral-small-latest": { @@ -45933,7 +59471,10 @@ 0.0, 0.0 ], - "limit": 32000 + "limit": 32000, + "max_output": 32000, + "open": true, + "released": "2025-07-15" }, "muse-glimmer-30b-tr": { "cost": [ @@ -45942,7 +59483,11 @@ 0.5, 0.0 ], - "limit": 131072 + "knowledge": "2026-01-04", + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2026-08-10" }, "perplexity/sonar-deep-research": { "cost": [ @@ -45951,7 +59496,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2025-01", + "limit": 128000, + "max_output": 32768, + "reasoning": 3.0, + "released": "2025-02-01" }, "poolside/laguna-xs-2.1": { "cost": [ @@ -45960,7 +59509,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-07-02" }, "publicai/apertus-70b-instruct": { "cost": [ @@ -45969,7 +59521,11 @@ 0.0, 0.0 ], - "limit": 65536 + "knowledge": "2025-09", + "limit": 65536, + "max_output": 8192, + "open": true, + "released": "2025-09-02" }, "publicai/apertus-8b-instruct": { "cost": [ @@ -45978,7 +59534,11 @@ 0.0, 0.0 ], - "limit": 65536 + "knowledge": "2025-09", + "limit": 65536, + "max_output": 8192, + "open": true, + "released": "2025-09-02" }, "qwen/qwen-flash": { "cost": [ @@ -45987,7 +59547,10 @@ 0.01, 0.0 ], - "limit": 1000000 + "knowledge": "2024-04", + "limit": 1000000, + "max_output": 32768, + "released": "2025-07-28" }, "qwen/qwen-plus": { "cost": [ @@ -45996,7 +59559,10 @@ 0.08, 0.0 ], - "limit": 1000000 + "knowledge": "2024-04", + "limit": 1000000, + "max_output": 32768, + "released": "2024-01-25" }, "qwen/qwen3-coder-flash": { "cost": [ @@ -46005,7 +59571,10 @@ 0.06, 0.0 ], - "limit": 1000000 + "knowledge": "2025-04", + "limit": 1000000, + "max_output": 65536, + "released": "2025-07-28" }, "qwen/qwen3-coder-plus": { "cost": [ @@ -46014,7 +59583,10 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 1000000, + "max_output": 65536, + "released": "2025-07-23", "status": "deprecated" }, "qwen/qwen3-max": { @@ -46024,7 +59596,10 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 256000, + "max_output": 65536, + "released": "2025-09-23", "status": "deprecated" }, "qwen/qwen3-vl-plus": { @@ -46034,7 +59609,10 @@ 0.04, 0.0 ], - "limit": 256000 + "knowledge": "2025-04", + "limit": 256000, + "max_output": 32768, + "released": "2025-09-23" }, "qwen/qwen3.5-397b-a17b": { "cost": [ @@ -46043,7 +59621,10 @@ 0.0, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 65536, + "open": true, + "released": "2026-02-15" }, "qwen/qwen3.5-plus": { "cost": [ @@ -46052,7 +59633,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-04", + "limit": 1000000, + "max_output": 65536, + "released": "2026-02-16" }, "qwen/qwen3.6-flash": { "cost": [ @@ -46061,7 +59645,9 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 65536, + "released": "2026-04-27" }, "qwen/qwen3.6-plus": { "cost": [ @@ -46070,7 +59656,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-04", + "limit": 1000000, + "max_output": 65536, + "released": "2026-04-02" }, "qwen/qwen3.7-plus": { "cost": [ @@ -46079,7 +59668,10 @@ 0.08, 0.0 ], - "limit": 1000000 + "knowledge": "2025-04", + "limit": 1000000, + "max_output": 64000, + "released": "2026-06-02" }, "qwen3-6-35b": { "cost": [ @@ -46088,7 +59680,10 @@ 0.0, 0.0 ], - "limit": 16384 + "limit": 16384, + "max_output": 16384, + "open": true, + "released": "2026-04-17" }, "sakana/fugu-ultra": { "cost": [ @@ -46097,7 +59692,9 @@ 0.5, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 1000000, + "released": "2026-06-15" }, "thinkingmachines/inkling": { "cost": [ @@ -46106,7 +59703,10 @@ 0.374, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-07-15" }, "thinkingmachines/inkling-small": { "cost": [ @@ -46115,7 +59715,10 @@ 0.116, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-07-30" }, "trendyol-asure-12b": { "cost": [ @@ -46124,7 +59727,10 @@ 0.025, 0.0 ], - "limit": 40960 + "limit": 40960, + "max_output": 40960, + "open": true, + "released": "2026-02-19" }, "upstage/solar-pro2": { "cost": [ @@ -46133,7 +59739,10 @@ 0.015, 0.0 ], - "limit": 65536 + "knowledge": "2025-03", + "limit": 65536, + "max_output": 8192, + "released": "2025-05-20" }, "upstage/solar-pro3": { "cost": [ @@ -46142,7 +59751,10 @@ 0.015, 0.0 ], - "limit": 131072 + "knowledge": "2025-07", + "limit": 131072, + "max_output": 8192, + "released": "2026-01-26" }, "upstage/solar-pro4": { "cost": [ @@ -46151,7 +59763,10 @@ 0.03, 0.0 ], - "limit": 524288 + "knowledge": "2026-02", + "limit": 524288, + "max_output": 131072, + "released": "2026-08-06" } }, "name": "LLMTR" @@ -46165,7 +59780,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "qwen/qwen3-30b-a3b-2507": { "cost": [ @@ -46174,7 +59793,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-04", + "limit": 262144, + "max_output": 16384, + "open": true, + "released": "2025-07-28" }, "qwen/qwen3-coder-30b": { "cost": [ @@ -46183,7 +59806,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-04", + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2025-07-31" } }, "name": "LMStudio" @@ -46197,7 +59824,10 @@ 0.006, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-06-30" }, "LongCat-2.5-Preview": { "cost": [ @@ -46206,7 +59836,9 @@ 0.006, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 262144, + "released": "2026-09-25" } }, "name": "LongCat" @@ -46220,7 +59852,9 @@ 0.0314, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 8192, + "released": "2025-07-30" }, "auto/mistralai/ministral-14b-2512": { "cost": [ @@ -46229,7 +59863,10 @@ 0.0209, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2025-12-02" }, "auto/mistralai/ministral-3b-2512": { "cost": [ @@ -46238,7 +59875,10 @@ 0.0105, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2025-12-02" }, "auto/mistralai/ministral-8b-2512": { "cost": [ @@ -46247,7 +59887,10 @@ 0.0157, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2025-12-02" }, "auto/mistralai/mistral-large-2512": { "cost": [ @@ -46256,7 +59899,11 @@ 0.0523, 0.0 ], - "limit": 262144 + "knowledge": "2024-11", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2025-12-02" }, "auto/mistralai/mistral-large-4": { "cost": [ @@ -46266,6 +59913,8 @@ 0.0 ], "limit": 524288, + "max_output": 262144, + "released": "2026-10-06", "status": "beta" }, "auto/mistralai/mistral-medium-3.5": { @@ -46275,7 +59924,10 @@ 0.1569, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-29" }, "auto/mistralai/mistral-small-2603": { "cost": [ @@ -46284,7 +59936,11 @@ 0.0157, 0.0 ], - "limit": 256000 + "knowledge": "2025-06", + "limit": 256000, + "max_output": 256000, + "open": true, + "released": "2026-03-16" }, "auto/openai/gpt-4.1": { "cost": [ @@ -46293,7 +59949,10 @@ 0.5, 0.0 ], - "limit": 1047576 + "knowledge": "2024-04", + "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14" }, "auto/openai/gpt-4.1-mini": { "cost": [ @@ -46302,7 +59961,10 @@ 0.1, 0.0 ], - "limit": 1047576 + "knowledge": "2024-04", + "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14" }, "auto/openai/gpt-4o": { "cost": [ @@ -46311,7 +59973,10 @@ 1.25, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-05-13" }, "auto/openai/gpt-4o-mini": { "cost": [ @@ -46320,7 +59985,10 @@ 0.075, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-07-18" }, "auto/openai/gpt-5": { "cost": [ @@ -46329,7 +59997,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "auto/openai/gpt-5-mini": { "cost": [ @@ -46338,7 +60009,10 @@ 0.025, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "auto/openai/gpt-5-nano": { "cost": [ @@ -46347,7 +60021,10 @@ 0.005, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "auto/openai/gpt-5.2": { "cost": [ @@ -46356,7 +60033,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "auto/openai/gpt-5.4": { "cost": [ @@ -46365,7 +60045,10 @@ 0.25, 0.0 ], + "knowledge": "2025-08-31", "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05", "tiers": [ { "cost": [ @@ -46388,7 +60071,10 @@ 0.075, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "auto/openai/gpt-5.5": { "cost": [ @@ -46397,7 +60083,10 @@ 0.5, 0.0 ], + "knowledge": "2025-12-01", "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23", "tiers": [ { "cost": [ @@ -46420,7 +60109,10 @@ 0.02, 0.25 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -46443,7 +60135,10 @@ 0.4, 5.0 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -46466,7 +60161,10 @@ 0.2, 2.5 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -46489,7 +60187,10 @@ 1.0, 12.5 ], + "knowledge": "2026-04-30", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-04", "tiers": [ { "cost": [ @@ -46512,7 +60213,10 @@ 0.01, 0.125 ], + "knowledge": "2026-05-18", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -46535,7 +60239,10 @@ 0.2, 2.5 ], + "knowledge": "2026-04-20", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -46558,7 +60265,10 @@ 0.1, 2.5 ], + "knowledge": "2026-04-30", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-29", "tiers": [ { "cost": [ @@ -46574,6 +60284,32 @@ } ] }, + "auto/openai/gpt-6.1-terra": { + "cost": [ + 1.0, + 5.0, + 0.05, + 1.25 + ], + "knowledge": "2026-06-01", + "limit": 1050000, + "max_output": 128000, + "released": "2026-10-26", + "tiers": [ + { + "cost": [ + 2.0, + 7.5, + 0.1, + 2.5 + ], + "tier": { + "size": 272000, + "type": "context" + } + } + ] + }, "auto/openai/gpt-oss-120b": { "cost": [ 0.1695, @@ -46581,7 +60317,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "auto/openai/gpt-oss-20b": { "cost": [ @@ -46590,7 +60330,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "auto/openai/gpt-oss-safeguard-120b": { "cost": [ @@ -46599,7 +60343,10 @@ 0.0, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-10-29" }, "auto/openai/gpt-oss-safeguard-20b": { "cost": [ @@ -46608,7 +60355,10 @@ 0.0, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2025-10-29" }, "auto/openai/o3": { "cost": [ @@ -46617,7 +60367,10 @@ 0.5, 0.0 ], - "limit": 200000 + "knowledge": "2024-05", + "limit": 200000, + "max_output": 100000, + "released": "2025-04-16" } }, "name": "LowRouter" @@ -46631,7 +60384,10 @@ 0.0, 0.0 ], - "limit": 120000 + "knowledge": "2025-09-16", + "limit": 120000, + "max_output": 8000, + "released": "2024-12-28" }, "lucidquery-agi-01-frontier": { "cost": [ @@ -46640,7 +60396,10 @@ 0.0, 0.0 ], - "limit": 300000 + "knowledge": "2026-06-05", + "limit": 300000, + "max_output": 120000, + "released": "2026-06-16" }, "lucidquery-agi-01-swift": { "cost": [ @@ -46649,7 +60408,10 @@ 0.0, 0.0 ], - "limit": 300000 + "knowledge": "2026-06-05", + "limit": 300000, + "max_output": 120000, + "released": "2026-06-16" }, "lucidquery-nexus-coder": { "cost": [ @@ -46658,7 +60420,10 @@ 0.0, 0.0 ], - "limit": 250000 + "knowledge": "2025-08-01", + "limit": 250000, + "max_output": 60000, + "released": "2025-09-01" } }, "name": "LucidQuery" @@ -46672,7 +60437,9 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 8192, + "released": "2025-12-03" } }, "name": "Lynkr" @@ -46686,7 +60453,10 @@ 0.0, 0.0 ], - "limit": 196608 + "limit": 196608, + "max_output": 131072, + "open": true, + "released": "2025-12-23" }, "MiniMaxAI/MiniMax-M2.5": { "cost": [ @@ -46695,7 +60465,10 @@ 0.15, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-02-12" }, "Qwen/Qwen2.5-VL-32B-Instruct": { "cost": [ @@ -46704,7 +60477,10 @@ 0.0, 0.0 ], - "limit": 16384 + "limit": 16384, + "max_output": 16384, + "open": true, + "released": "2025-03-24" }, "Qwen/Qwen3-235B-A22B-Instruct-2507": { "cost": [ @@ -46713,7 +60489,10 @@ 0.0, 0.0 ], - "limit": 262000 + "limit": 262000, + "max_output": 262000, + "open": true, + "released": "2025-07-21" }, "Qwen/Qwen3.5-Plus": { "cost": [ @@ -46722,7 +60501,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-04", + "limit": 1000000, + "max_output": 65536, + "released": "2026-02-16" }, "XiaomiMiMo/MiMo-V2-Flash": { "cost": [ @@ -46731,7 +60513,11 @@ 0.0, 0.0 ], + "knowledge": "2024-12-01", "limit": 262144, + "max_output": 32000, + "open": true, + "released": "2025-12-16", "status": "deprecated" }, "deepseek-ai/DeepSeek-R1-0528": { @@ -46741,7 +60527,11 @@ 0.4, 0.0 ], - "limit": 163840 + "knowledge": "2024-07", + "limit": 163840, + "max_output": 64000, + "open": true, + "released": "2025-05-28" }, "deepseek-ai/DeepSeek-V3-0324": { "cost": [ @@ -46750,7 +60540,10 @@ 0.0, 0.0 ], - "limit": 163840 + "limit": 163840, + "max_output": 163840, + "open": true, + "released": "2025-03-24" }, "deepseek-ai/DeepSeek-V3.1": { "cost": [ @@ -46759,7 +60552,10 @@ 0.0, 0.0 ], - "limit": 164000 + "limit": 164000, + "max_output": 164000, + "open": true, + "released": "2025-08-21" }, "deepseek-ai/DeepSeek-V3.2": { "cost": [ @@ -46768,7 +60564,11 @@ 0.13, 0.0 ], - "limit": 164000 + "knowledge": "2024-07", + "limit": 164000, + "max_output": 164000, + "open": true, + "released": "2025-12-01" }, "deepseek-ai/DeepSeek-V3.2-Exp": { "cost": [ @@ -46777,7 +60577,10 @@ 0.13, 0.0 ], - "limit": 164000 + "limit": 164000, + "max_output": 164000, + "open": true, + "released": "2025-10-10" }, "meta-llama/Llama-3.3-70B-Instruct": { "cost": [ @@ -46786,7 +60589,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2023-12", + "limit": 131072, + "max_output": 16384, + "open": true, + "released": "2024-12-06" }, "mistralai/Mistral-Nemo-Instruct-2407": { "cost": [ @@ -46795,7 +60602,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-07", + "limit": 131072, + "max_output": 65536, + "open": true, + "released": "2024-07-18" }, "mistralai/Mistral-Small-3.2-24B-Instruct-2506": { "cost": [ @@ -46804,7 +60615,11 @@ 0.0, 0.0 ], - "limit": 32768 + "knowledge": "2024-10", + "limit": 32768, + "max_output": 8192, + "open": true, + "released": "2025-06-20" }, "moonshotai/Kimi-K2-Thinking": { "cost": [ @@ -46813,7 +60628,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2024-08", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2025-11-06" }, "moonshotai/Kimi-K2.5": { "cost": [ @@ -46822,7 +60641,11 @@ 0.07, 0.0 ], - "limit": 262144 + "knowledge": "2026-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-01-27" }, "zai-org/GLM-4.6": { "cost": [ @@ -46831,7 +60654,11 @@ 0.0, 0.0 ], - "limit": 202752 + "knowledge": "2025-04", + "limit": 202752, + "max_output": 131072, + "open": true, + "released": "2025-09-30" }, "zai-org/GLM-4.7": { "cost": [ @@ -46840,7 +60667,11 @@ 0.08, 0.0 ], - "limit": 202752 + "knowledge": "2025-04", + "limit": 202752, + "max_output": 131072, + "open": true, + "released": "2025-12-22" }, "zai-org/GLM-5": { "cost": [ @@ -46849,134 +60680,116 @@ 0.2, 0.0 ], - "limit": 202752 + "limit": 202752, + "max_output": 131072, + "open": true, + "released": "2026-02-12" } }, "name": "Meganova" }, "melious": { "models": { - "deepseek-r1-0528": { - "cost": [ - 0.69552, - 2.78208, - 0.185472, - 0.0 - ], - "limit": 164000, - "status": "deprecated" - }, - "deepseek-v3.2": { - "cost": [ - 0.34776, - 0.5796, - 0.092736, - 0.0 - ], - "limit": 164000, - "status": "deprecated" - }, "deepseek-v4-flash-0731": { "cost": [ - 0.11592, - 0.2898, - 0.023184, + 0.1115, + 0.27875, + 0.0223, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-07-31" }, "deepseek-v4.1-flash": { "cost": [ - 0.23184, - 1.1592, - 0.011592, + 0.223, + 1.115, + 0.01115, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-09-10" }, "deepseek-v4.1-flash-1017": { "cost": [ - 0.33675, - 1.347, - 0.033675, - 0.0 - ], - "limit": 1000000 - }, - "glm-5": { - "cost": [ - 1.10124, - 3.36168, - 0.266616, + 0.3345, + 1.338, + 0.03345, 0.0 ], - "limit": 203000, - "status": "deprecated" - }, - "glm-5.1": { - "cost": [ - 1.50696, - 4.6368, - 0.370944, - 0.0 - ], - "limit": 203000, - "status": "deprecated" + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-10-17" }, "glm-5.3": { "cost": [ - 1.1592, - 3.4776, - 0.23184, + 1.115, + 3.345, + 0.223, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "glm-5.3-flash": { "cost": [ - 0.11592, - 0.46368, - 0.023184, - 0.0 - ], - "limit": 1000000 - }, - "kimi-k2.5": { - "cost": [ - 0.5796, - 2.95596, - 0.139104, + 0.1115, + 0.446, + 0.0223, 0.0 ], - "limit": 262000, - "status": "deprecated" + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-26" }, "kimi-k2.6": { "cost": [ - 0.78505, - 3.3645, - 0.280375, + 0.669, + 4.014, + 0.16725, 0.0 ], - "limit": 256000 + "knowledge": "2025-01", + "limit": 256000, + "max_output": 256000, + "open": true, + "released": "2026-04-20" }, "kimi-k2.7-code": { "cost": [ - 0.728975, - 3.644875, - 0.190655, + 0.61325, + 3.28925, + 0.16725, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-06-12" }, "kimi-k3": { "cost": [ - 3.196275, - 15.981375, - 0.841125, + 3.17775, + 15.88875, + 0.79165, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-07-16" } }, "name": "Melious" @@ -46990,7 +60803,10 @@ 1.0, 12.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-09" }, "anthropic/claude-fable-5-1": { "cost": [ @@ -46999,7 +60815,10 @@ 0.25, 12.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-01" }, "anthropic/claude-haiku-4-5-20251001": { "cost": [ @@ -47008,7 +60827,10 @@ 0.1, 1.25 ], - "limit": 200000 + "knowledge": "2025-02-28", + "limit": 200000, + "max_output": 64000, + "released": "2025-10-15" }, "anthropic/claude-haiku-5-5": { "cost": [ @@ -47017,7 +60839,10 @@ 0.01, 0.125 ], + "knowledge": "2026-06", "limit": 1000000, + "max_output": 128000, + "released": "2026-10-07", "tiers": [ { "cost": [ @@ -47040,7 +60865,10 @@ 1.5, 18.75 ], - "limit": 200000 + "knowledge": "2025-03-31", + "limit": 200000, + "max_output": 32000, + "released": "2025-08-05" }, "anthropic/claude-opus-4-5-20251101": { "cost": [ @@ -47049,7 +60877,10 @@ 0.5, 6.25 ], - "limit": 200000 + "knowledge": "2025-05", + "limit": 200000, + "max_output": 64000, + "released": "2025-11-24" }, "anthropic/claude-opus-4-6": { "cost": [ @@ -47058,7 +60889,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2025-05-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-05" }, "anthropic/claude-opus-4-6-fast": { "cost": [ @@ -47067,7 +60901,10 @@ 3.0, 37.5 ], - "limit": 1000000 + "knowledge": "2025-05-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-05" }, "anthropic/claude-opus-4-7": { "cost": [ @@ -47076,7 +60913,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-16" }, "anthropic/claude-opus-4-7-fast": { "cost": [ @@ -47085,7 +60925,10 @@ 3.0, 37.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-16" }, "anthropic/claude-opus-4-8": { "cost": [ @@ -47094,7 +60937,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-28" }, "anthropic/claude-opus-5": { "cost": [ @@ -47103,7 +60949,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-05", + "limit": 1000000, + "max_output": 128000, + "released": "2026-07-24" }, "anthropic/claude-opus-5-5": { "cost": [ @@ -47112,7 +60961,10 @@ 0.2, 5.0 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-22" }, "anthropic/claude-sonnet-4-5-20250929": { "cost": [ @@ -47121,7 +60973,10 @@ 0.3, 3.75 ], - "limit": 200000 + "knowledge": "2025-07-31", + "limit": 200000, + "max_output": 64000, + "released": "2025-09-29" }, "anthropic/claude-sonnet-4-6": { "cost": [ @@ -47130,7 +60985,10 @@ 0.3, 3.75 ], - "limit": 1000000 + "knowledge": "2025-08-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-17" }, "anthropic/claude-sonnet-5": { "cost": [ @@ -47139,7 +60997,10 @@ 0.2, 2.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-30" }, "anthropic/claude-sonnet-5-5": { "cost": [ @@ -47148,7 +61009,10 @@ 0.1, 2.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-28" }, "bytedance/dola-seed-2.0-code": { "cost": [ @@ -47157,7 +61021,9 @@ 0.0, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 128000, + "released": "2026-02-14" }, "bytedance/dola-seed-2.0-code-preview": { "cost": [ @@ -47166,34 +61032,42 @@ 0.0, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 32768, + "released": "2026-03-28" }, "bytedance/dola-seed-2.0-lite": { "cost": [ - 0.25, - 2.0, + 0.31, + 2.5, 0.0, 0.0 ], - "limit": 131072 + "limit": 256000, + "max_output": 128000, + "released": "2026-02-14" }, "bytedance/dola-seed-2.0-mini": { "cost": [ - 0.1, - 0.4, + 0.12, + 0.5, 0.0, 0.0 ], - "limit": 131072 + "limit": 256000, + "max_output": 128000, + "released": "2026-02-14" }, "bytedance/dola-seed-2.0-pro": { "cost": [ - 0.5, - 3.0, + 0.63, + 3.79, 0.0, 0.0 ], - "limit": 131072 + "limit": 256000, + "max_output": 128000, + "released": "2026-02-14" }, "cohere/command-a-03-2025": { "cost": [ @@ -47202,7 +61076,11 @@ 0.0, 0.0 ], - "limit": 256000 + "knowledge": "2024-06-01", + "limit": 256000, + "max_output": 8000, + "open": true, + "released": "2025-03-13" }, "cohere/command-r-08-2024": { "cost": [ @@ -47211,7 +61089,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-06-01", + "limit": 128000, + "max_output": 4000, + "open": true, + "released": "2024-08-30" }, "cohere/command-r-plus-08-2024": { "cost": [ @@ -47220,7 +61102,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-06-01", + "limit": 128000, + "max_output": 4000, + "open": true, + "released": "2024-08-30" }, "cohere/command-r7b-12-2024": { "cost": [ @@ -47229,7 +61115,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-06-01", + "limit": 128000, + "max_output": 4000, + "open": true, + "released": "2024-12-13" }, "deepseek/deepseek-r1": { "cost": [ @@ -47238,7 +61128,11 @@ 0.0, 0.0 ], - "limit": 163840 + "knowledge": "2024-07", + "limit": 163840, + "max_output": 40960, + "open": true, + "released": "2025-01-20" }, "deepseek/deepseek-r1-0528": { "cost": [ @@ -47247,7 +61141,10 @@ 0.945, 0.0 ], - "limit": 65536 + "limit": 65536, + "max_output": 32768, + "open": true, + "released": "2025-05-28" }, "deepseek/deepseek-v3": { "cost": [ @@ -47256,7 +61153,10 @@ 0.0, 0.0 ], - "limit": 163840 + "limit": 163840, + "max_output": 81920, + "open": true, + "released": "2024-12-26" }, "deepseek/deepseek-v3.1": { "cost": [ @@ -47265,7 +61165,10 @@ 0.13, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-21" }, "deepseek/deepseek-v3.2": { "cost": [ @@ -47274,7 +61177,11 @@ 0.13, 0.0 ], - "limit": 128000 + "knowledge": "2024-07", + "limit": 128000, + "max_output": 32768, + "open": true, + "released": "2025-12-01" }, "deepseek/deepseek-v4-flash": { "cost": [ @@ -47283,7 +61190,11 @@ 0.006, 0.1125 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "deepseek/deepseek-v4-flash-0423": { "cost": [ @@ -47292,7 +61203,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2025-05", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2026-04-23" }, "deepseek/deepseek-v4-flash-0731": { "cost": [ @@ -47301,7 +61216,11 @@ 0.007, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-07-31" }, "deepseek/deepseek-v4-flash-0731-fast": { "cost": [ @@ -47310,7 +61229,11 @@ 0.07, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-07-31" }, "deepseek/deepseek-v4-pro": { "cost": [ @@ -47319,7 +61242,11 @@ 0.044, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "deepseek/deepseek-v4-pro-0423": { "cost": [ @@ -47328,7 +61255,11 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 393216, + "open": true, + "released": "2026-04-23" }, "deepseek/deepseek-v4-pro-0813": { "cost": [ @@ -47337,7 +61268,10 @@ 0.003625, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-08-13" }, "deepseek/deepseek-v4.1-flash": { "cost": [ @@ -47346,7 +61280,11 @@ 0.003, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-09-10" }, "deepseek/deepseek-v4.1-flash-1017": { "cost": [ @@ -47355,7 +61293,11 @@ 0.003, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-10-17" }, "google/gemini-2.5-computer-use-preview-10-2025": { "cost": [ @@ -47364,7 +61306,10 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2025-01", + "limit": 128000, + "max_output": 64000, + "released": "2025-10-07" }, "google/gemini-2.5-flash": { "cost": [ @@ -47373,7 +61318,10 @@ 0.03, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2025-06-17" }, "google/gemini-2.5-flash-image": { "cost": [ @@ -47382,7 +61330,11 @@ 0.0, 0.0 ], - "limit": 32768 + "knowledge": "2024-06", + "limit": 32768, + "max_output": 32768, + "released": "2025-08-26", + "type": "image" }, "google/gemini-2.5-flash-lite": { "cost": [ @@ -47391,7 +61343,10 @@ 0.01, 0.0 ], - "limit": 1000000 + "knowledge": "2025-01", + "limit": 1000000, + "max_output": 65536, + "released": "2025-06-17" }, "google/gemini-2.5-pro": { "cost": [ @@ -47400,7 +61355,10 @@ 0.125, 0.0 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2025-06-17", "tiers": [ { "cost": [ @@ -47423,7 +61381,10 @@ 0.05, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2025-12-17" }, "google/gemini-3-pro-image": { "cost": [ @@ -47432,7 +61393,11 @@ 0.0, 0.0 ], - "limit": 65536 + "knowledge": "2025-01", + "limit": 65536, + "max_output": 65536, + "released": "2026-05-28", + "type": "image" }, "google/gemini-3.1-flash-image": { "cost": [ @@ -47441,7 +61406,11 @@ 0.0, 0.0 ], - "limit": 32768 + "knowledge": "2025-01", + "limit": 32768, + "max_output": 32768, + "released": "2026-05-28", + "type": "image" }, "google/gemini-3.1-flash-lite": { "cost": [ @@ -47450,7 +61419,10 @@ 0.025, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-05-07" }, "google/gemini-3.1-pro-preview": { "cost": [ @@ -47459,7 +61431,10 @@ 0.2, 0.0 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2026-02-19", "tiers": [ { "cost": [ @@ -47482,7 +61457,10 @@ 0.2, 0.0 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2026-02-19", "tiers": [ { "cost": [ @@ -47505,7 +61483,10 @@ 0.15, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-05-19" }, "google/gemini-3.5-flash-lite": { "cost": [ @@ -47514,7 +61495,10 @@ 0.03, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-07-21" }, "google/gemini-3.6-flash": { "cost": [ @@ -47523,7 +61507,10 @@ 0.15, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-07-21" }, "google/gemini-3.7-flash": { "cost": [ @@ -47532,7 +61519,10 @@ 0.075, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-08-13" }, "google/gemini-3.8-flash": { "cost": [ @@ -47541,7 +61531,9 @@ 0.075, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65536, + "released": "2026-09-02" }, "google/gemini-4-argon": { "cost": [ @@ -47550,7 +61542,10 @@ 0.1, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-10-13" }, "google/gemini-embedding-001": { "cost": [ @@ -47559,7 +61554,11 @@ 0.0, 0.0 ], - "limit": 2048 + "knowledge": "2025-05", + "limit": 2048, + "max_output": 4096, + "released": "2025-05-20", + "type": "embedding" }, "google/gemini-embedding-2": { "cost": [ @@ -47568,7 +61567,11 @@ 0.0, 0.0 ], - "limit": 8192 + "knowledge": "2025-11", + "limit": 8192, + "max_output": 8192, + "released": "2026-04-22", + "type": "embedding" }, "google/gemini-flash-latest": { "cost": [ @@ -47577,7 +61580,10 @@ 0.15, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-08-13" }, "google/gemini-flash-lite-latest": { "cost": [ @@ -47586,7 +61592,10 @@ 0.025, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-07-21" }, "google/gemma-3-12b-it": { "cost": [ @@ -47595,7 +61604,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-08", + "limit": 128000, + "max_output": 8192, + "open": true, + "released": "2025-03-12" }, "google/gemma-3-27b-it": { "cost": [ @@ -47604,7 +61617,11 @@ 0.04, 0.0 ], - "limit": 131072 + "knowledge": "2024-08", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-03-12" }, "google/gemma-3-4b-it": { "cost": [ @@ -47613,7 +61630,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-08", + "limit": 128000, + "max_output": 8192, + "open": true, + "released": "2025-03-12" }, "google/gemma-4-26b-a4b-it": { "cost": [ @@ -47622,7 +61643,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-04-02" }, "google/gemma-4-31b-it": { "cost": [ @@ -47631,7 +61655,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-04-02" }, "meta/llama-3.1-70b-instruct": { "cost": [ @@ -47640,7 +61668,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2023-12", + "limit": 128000, + "max_output": 2048, + "open": true, + "released": "2024-07-23" }, "meta/llama-3.1-8b-instruct": { "cost": [ @@ -47649,7 +61681,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2023-12", + "limit": 128000, + "max_output": 2048, + "open": true, + "released": "2024-07-23" }, "meta/llama-3.3-70b-instruct": { "cost": [ @@ -47658,7 +61694,11 @@ 0.11, 0.0 ], - "limit": 131072 + "knowledge": "2023-12", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2024-12-06" }, "meta/muse-spark-open": { "cost": [ @@ -47667,7 +61707,11 @@ 0.15, 0.0 ], - "limit": 1048576 + "knowledge": "2026-01-04", + "limit": 1048576, + "max_output": 262144, + "open": true, + "released": "2026-10-15" }, "minimax/minimax-m2": { "cost": [ @@ -47676,7 +61720,10 @@ 0.03, 0.375 ], - "limit": 204800 + "limit": 204800, + "max_output": 8192, + "open": true, + "released": "2025-10-27" }, "minimax/minimax-m2.1": { "cost": [ @@ -47685,7 +61732,10 @@ 0.03, 0.375 ], - "limit": 204800 + "limit": 204800, + "max_output": 8192, + "open": true, + "released": "2025-12-23" }, "minimax/minimax-m2.5": { "cost": [ @@ -47694,7 +61744,10 @@ 0.03, 0.375 ], - "limit": 204800 + "limit": 204800, + "max_output": 8192, + "open": true, + "released": "2026-02-12" }, "minimax/minimax-m2.5-highspeed": { "cost": [ @@ -47703,7 +61756,10 @@ 0.03, 0.375 ], - "limit": 204800 + "limit": 204800, + "max_output": 8192, + "open": true, + "released": "2026-02-13" }, "minimax/minimax-m2.7": { "cost": [ @@ -47712,7 +61768,10 @@ 0.06, 0.375 ], - "limit": 204800 + "limit": 204800, + "max_output": 8192, + "open": true, + "released": "2026-03-18" }, "minimax/minimax-m2.7-highspeed": { "cost": [ @@ -47721,7 +61780,10 @@ 0.06, 0.375 ], - "limit": 204800 + "limit": 204800, + "max_output": 8192, + "open": true, + "released": "2026-03-18" }, "minimax/minimax-m3": { "cost": [ @@ -47730,7 +61792,10 @@ 0.06, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 128000, + "open": true, + "released": "2026-06-01" }, "minimax/minimax-m3.1-flash": { "cost": [ @@ -47739,7 +61804,9 @@ 0.015, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 128000, + "released": "2026-10-19" }, "mistral/codestral-latest": { "cost": [ @@ -47748,7 +61815,11 @@ 0.0, 0.0 ], - "limit": 256000 + "knowledge": "2024-10", + "limit": 256000, + "max_output": 4096, + "open": true, + "released": "2024-05-29" }, "mistral/devstral-2512": { "cost": [ @@ -47757,7 +61828,11 @@ 0.04, 0.0 ], - "limit": 256000 + "knowledge": "2025-12", + "limit": 256000, + "max_output": 256000, + "open": true, + "released": "2025-12-09" }, "mistral/devstral-medium-latest": { "cost": [ @@ -47766,7 +61841,11 @@ 0.0, 0.0 ], + "knowledge": "2025-12", "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2025-12-02", "status": "deprecated" }, "mistral/magistral-medium-latest": { @@ -47776,7 +61855,10 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2025-06", + "limit": 128000, + "max_output": 16384, + "released": "2025-03-17" }, "mistral/mistral-large-2512": { "cost": [ @@ -47785,7 +61867,11 @@ 0.05, 0.0 ], - "limit": 256000 + "knowledge": "2024-11", + "limit": 256000, + "max_output": 256000, + "open": true, + "released": "2025-12-02" }, "mistral/mistral-large-latest": { "cost": [ @@ -47794,7 +61880,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2024-11", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2024-11-01" }, "mistral/mistral-medium-2505": { "cost": [ @@ -47803,7 +61893,10 @@ 0.04, 0.0 ], - "limit": 128000 + "knowledge": "2025-05", + "limit": 128000, + "max_output": 128000, + "released": "2025-05-07" }, "mistral/mistral-medium-latest": { "cost": [ @@ -47812,7 +61905,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-29" }, "mistral/mistral-small-latest": { "cost": [ @@ -47821,7 +61917,11 @@ 0.0, 0.0 ], - "limit": 256000 + "knowledge": "2025-06", + "limit": 256000, + "max_output": 256000, + "open": true, + "released": "2026-03-16" }, "mistral/pixtral-large-latest": { "cost": [ @@ -47830,7 +61930,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-11", + "limit": 128000, + "max_output": 128000, + "open": true, + "released": "2024-11-01" }, "moonshot/kimi-k2.5": { "cost": [ @@ -47839,7 +61943,11 @@ 0.1, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-01-27" }, "moonshot/kimi-k2.6": { "cost": [ @@ -47848,7 +61956,11 @@ 0.16, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-20" }, "moonshot/kimi-k2.7-code": { "cost": [ @@ -47857,7 +61969,11 @@ 0.19, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-06-12" }, "moonshot/kimi-k2.7-code-highspeed": { "cost": [ @@ -47866,16 +61982,34 @@ 0.38, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-06-12" }, "moonshot/kimi-k3": { "cost": [ - 2.9, - 14.0, + 3.0, + 15.0, 0.3, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-07-16" + }, + "moonshot/kimi-k3.1-pro": { + "cost": [ + 2.0, + 10.0, + 0.2, + 0.0 + ], + "limit": 1048576, + "max_output": 1048576, + "released": "2026-10-23" }, "nvidia/nemotron-3-nano-30b-a3b": { "cost": [ @@ -47884,7 +62018,11 @@ 0.0, 0.0 ], - "limit": 256000 + "knowledge": "2025-06-25", + "limit": 256000, + "max_output": 32000, + "open": true, + "released": "2025-12-15" }, "nvidia/nemotron-3.5-lightning-30b-a3b": { "cost": [ @@ -47893,7 +62031,11 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-09", + "limit": 1000000, + "max_output": 262144, + "open": true, + "released": "2026-08-11" }, "nvidia/nemotron-nano-9b-v2": { "cost": [ @@ -47902,7 +62044,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-09", + "limit": 128000, + "max_output": 8192, + "open": true, + "released": "2025-08-18" }, "openai/gpt-3.5-turbo": { "cost": [ @@ -47911,7 +62057,10 @@ 0.0, 0.0 ], - "limit": 16385 + "knowledge": "2021-09-01", + "limit": 16385, + "max_output": 4096, + "released": "2023-03-01" }, "openai/gpt-4": { "cost": [ @@ -47920,7 +62069,10 @@ 0.0, 0.0 ], - "limit": 8192 + "knowledge": "2023-11", + "limit": 8192, + "max_output": 8192, + "released": "2023-11-06" }, "openai/gpt-4-turbo": { "cost": [ @@ -47929,7 +62081,10 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2023-12", + "limit": 128000, + "max_output": 4096, + "released": "2023-11-06" }, "openai/gpt-4.1": { "cost": [ @@ -47938,7 +62093,10 @@ 0.5, 0.0 ], - "limit": 1047576 + "knowledge": "2024-04", + "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14" }, "openai/gpt-4.1-mini": { "cost": [ @@ -47947,7 +62105,10 @@ 0.1, 0.0 ], - "limit": 1047576 + "knowledge": "2024-04", + "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14" }, "openai/gpt-4.1-nano": { "cost": [ @@ -47956,7 +62117,10 @@ 0.025, 0.0 ], - "limit": 1047576 + "knowledge": "2024-04", + "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14" }, "openai/gpt-4o": { "cost": [ @@ -47965,7 +62129,10 @@ 1.25, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-05-13" }, "openai/gpt-4o-2024-05-13": { "cost": [ @@ -47974,7 +62141,10 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 4096, + "released": "2024-05-13" }, "openai/gpt-4o-2024-08-06": { "cost": [ @@ -47983,7 +62153,10 @@ 1.25, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-08-06" }, "openai/gpt-4o-2024-11-20": { "cost": [ @@ -47992,7 +62165,10 @@ 1.25, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-11-20" }, "openai/gpt-4o-mini": { "cost": [ @@ -48001,7 +62177,10 @@ 0.075, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-07-18" }, "openai/gpt-5": { "cost": [ @@ -48010,7 +62189,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "openai/gpt-5-chat-latest": { "cost": [ @@ -48019,7 +62201,10 @@ 0.125, 0.0 ], - "limit": 128000 + "knowledge": "2024-09-30", + "limit": 128000, + "max_output": 16384, + "released": "2025-08-07" }, "openai/gpt-5-mini": { "cost": [ @@ -48028,7 +62213,10 @@ 0.025, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "openai/gpt-5-nano": { "cost": [ @@ -48037,7 +62225,10 @@ 0.005, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "openai/gpt-5-search-api": { "cost": [ @@ -48046,7 +62237,9 @@ 0.0, 0.0 ], - "limit": 272000 + "limit": 272000, + "max_output": 128000, + "released": "2025-10-14" }, "openai/gpt-5.1": { "cost": [ @@ -48055,7 +62248,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "openai/gpt-5.1-chat-latest": { "cost": [ @@ -48064,7 +62260,10 @@ 0.125, 0.0 ], - "limit": 128000 + "knowledge": "2024-09-30", + "limit": 128000, + "max_output": 16384, + "released": "2025-11-13" }, "openai/gpt-5.2": { "cost": [ @@ -48073,7 +62272,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "openai/gpt-5.2-chat-latest": { "cost": [ @@ -48082,7 +62284,10 @@ 0.175, 0.0 ], - "limit": 128000 + "knowledge": "2025-08-31", + "limit": 128000, + "max_output": 16384, + "released": "2025-12-11" }, "openai/gpt-5.3-chat-latest": { "cost": [ @@ -48091,7 +62296,10 @@ 0.175, 0.0 ], - "limit": 128000 + "knowledge": "2025-08-31", + "limit": 128000, + "max_output": 16384, + "released": "2026-03-03" }, "openai/gpt-5.4": { "cost": [ @@ -48100,7 +62308,10 @@ 0.25, 0.0 ], + "knowledge": "2025-08-31", "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05", "tiers": [ { "cost": [ @@ -48123,7 +62334,10 @@ 0.5, 0.0 ], - "limit": 1050000 + "knowledge": "2025-08-31", + "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05" }, "openai/gpt-5.4-mini": { "cost": [ @@ -48132,7 +62346,10 @@ 0.075, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "openai/gpt-5.4-mini-fast": { "cost": [ @@ -48141,7 +62358,10 @@ 0.15, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "openai/gpt-5.4-nano": { "cost": [ @@ -48150,7 +62370,10 @@ 0.02, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "openai/gpt-5.5": { "cost": [ @@ -48159,7 +62382,10 @@ 0.5, 0.0 ], + "knowledge": "2025-12-01", "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23", "tiers": [ { "cost": [ @@ -48182,7 +62408,10 @@ 1.25, 0.0 ], - "limit": 1050000 + "knowledge": "2025-12-01", + "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23" }, "openai/gpt-5.6-luna": { "cost": [ @@ -48191,7 +62420,10 @@ 0.02, 0.25 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -48214,7 +62446,10 @@ 0.5, 5.0 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -48237,7 +62472,10 @@ 0.2, 2.5 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -48260,7 +62498,10 @@ 1.0, 12.5 ], + "knowledge": "2026-04-30", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-04", "tiers": [ { "cost": [ @@ -48283,7 +62524,10 @@ 0.01, 0.125 ], + "knowledge": "2026-05-18", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -48306,7 +62550,10 @@ 0.2, 2.5 ], + "knowledge": "2026-04-20", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -48329,7 +62576,10 @@ 0.1, 2.5 ], + "knowledge": "2026-04-30", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-29", "tiers": [ { "cost": [ @@ -48345,6 +62595,32 @@ } ] }, + "openai/gpt-6.1-terra": { + "cost": [ + 1.0, + 5.0, + 0.05, + 1.25 + ], + "knowledge": "2026-06-01", + "limit": 1050000, + "max_output": 128000, + "released": "2026-10-26", + "tiers": [ + { + "cost": [ + 2.0, + 7.5, + 0.1, + 2.5 + ], + "tier": { + "size": 272000, + "type": "context" + } + } + ] + }, "openai/gpt-audio": { "cost": [ 2.5, @@ -48352,7 +62628,10 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2023-10-01", + "limit": 128000, + "max_output": 16384, + "released": "2025-08-28" }, "openai/gpt-audio-mini": { "cost": [ @@ -48361,7 +62640,10 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2023-10-01", + "limit": 128000, + "max_output": 16384, + "released": "2025-10-06" }, "openai/gpt-oss-120b": { "cost": [ @@ -48370,7 +62652,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-06", + "limit": 128000, + "max_output": 32000, + "open": true, + "released": "2025-08-05" }, "openai/gpt-oss-20b": { "cost": [ @@ -48379,7 +62665,11 @@ 0.02, 0.0 ], - "limit": 128000 + "knowledge": "2024-06", + "limit": 128000, + "max_output": 32000, + "open": true, + "released": "2025-08-05" }, "openai/gpt-oss-safeguard-120b": { "cost": [ @@ -48388,7 +62678,10 @@ 0.0, 0.0 ], - "limit": 4096 + "limit": 4096, + "max_output": 4096, + "open": true, + "released": "2025-10-29" }, "openai/gpt-oss-safeguard-20b": { "cost": [ @@ -48397,7 +62690,10 @@ 0.0, 0.0 ], - "limit": 4096 + "limit": 4096, + "max_output": 4096, + "open": true, + "released": "2025-10-29" }, "openai/o1": { "cost": [ @@ -48406,7 +62702,10 @@ 7.5, 0.0 ], - "limit": 200000 + "knowledge": "2023-09", + "limit": 200000, + "max_output": 100000, + "released": "2024-12-05" }, "openai/o3": { "cost": [ @@ -48415,7 +62714,10 @@ 0.5, 0.0 ], - "limit": 200000 + "knowledge": "2024-05", + "limit": 200000, + "max_output": 100000, + "released": "2025-04-16" }, "openai/o3-mini": { "cost": [ @@ -48424,7 +62726,10 @@ 0.55, 0.0 ], - "limit": 200000 + "knowledge": "2024-05", + "limit": 200000, + "max_output": 100000, + "released": "2024-12-20" }, "openai/o4-mini": { "cost": [ @@ -48433,7 +62738,10 @@ 0.275, 0.0 ], - "limit": 200000 + "knowledge": "2024-05", + "limit": 200000, + "max_output": 100000, + "released": "2025-04-16" }, "qwen/qwen-flash": { "cost": [ @@ -48442,7 +62750,10 @@ 0.0044, 0.0275 ], - "limit": 1000000 + "knowledge": "2024-04", + "limit": 1000000, + "max_output": 250000, + "released": "2025-07-28" }, "qwen/qwen-plus": { "cost": [ @@ -48451,7 +62762,10 @@ 0.023, 0.14375 ], - "limit": 1000000 + "knowledge": "2024-04", + "limit": 1000000, + "max_output": 250000, + "released": "2024-01-25" }, "qwen/qwen3-235b-a22b": { "cost": [ @@ -48460,7 +62774,11 @@ 0.0574, 0.0 ], - "limit": 131072 + "knowledge": "2025-04", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-04-28" }, "qwen/qwen3-235b-a22b-instruct-2507": { "cost": [ @@ -48469,7 +62787,10 @@ 0.0574, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-07-21" }, "qwen/qwen3-30b-a3b": { "cost": [ @@ -48478,7 +62799,10 @@ 0.0216, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-04-28" }, "qwen/qwen3-32b": { "cost": [ @@ -48487,7 +62811,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2025-04", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-04-28" }, "qwen/qwen3-coder-480b-a35b-instruct": { "cost": [ @@ -48496,7 +62824,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2025-04", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-07-22" }, "qwen/qwen3-coder-flash": { "cost": [ @@ -48505,7 +62837,10 @@ 0.0288, 0.18 ], - "limit": 1000000 + "knowledge": "2025-04", + "limit": 1000000, + "max_output": 250000, + "released": "2025-07-28" }, "qwen/qwen3-coder-next": { "cost": [ @@ -48514,7 +62849,11 @@ 0.075, 0.0 ], - "limit": 262144 + "knowledge": "2025-09", + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-03" }, "qwen/qwen3-coder-plus": { "cost": [ @@ -48523,7 +62862,10 @@ 0.1148, 0.7175 ], - "limit": 1000000 + "knowledge": "2025-04", + "limit": 1000000, + "max_output": 250000, + "released": "2025-07-23" }, "qwen/qwen3-max": { "cost": [ @@ -48532,7 +62874,10 @@ 0.0718, 0.44875 ], - "limit": 262144 + "knowledge": "2025-04", + "limit": 262144, + "max_output": 65536, + "released": "2025-09-23" }, "qwen/qwen3-max-preview": { "cost": [ @@ -48541,7 +62886,10 @@ 0.0, 0.0 ], - "limit": 256000 + "knowledge": "2025-04", + "limit": 256000, + "max_output": 65536, + "released": "2025-09-05" }, "qwen/qwen3-next-80b-a3b-instruct": { "cost": [ @@ -48550,7 +62898,11 @@ 0.05, 0.0 ], - "limit": 131072 + "knowledge": "2025-04", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-09" }, "qwen/qwen3-next-80b-a3b-thinking": { "cost": [ @@ -48559,7 +62911,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2025-04", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-09" }, "qwen/qwen3-vl-235b-a22b-instruct": { "cost": [ @@ -48568,7 +62924,11 @@ 0.105, 0.0 ], - "limit": 131072 + "knowledge": "2025-03-31", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-09-23" }, "qwen/qwen3-vl-235b-a22b-thinking": { "cost": [ @@ -48577,7 +62937,11 @@ 0.0574, 0.0 ], - "limit": 131072 + "knowledge": "2025-03-31", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-09-23" }, "qwen/qwen3-vl-30b-a3b-instruct": { "cost": [ @@ -48586,7 +62950,10 @@ 0.0216, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-10-04" }, "qwen/qwen3-vl-flash": { "cost": [ @@ -48595,7 +62962,9 @@ 0.0044, 0.0275 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "released": "2025-10-15" }, "qwen/qwen3-vl-plus": { "cost": [ @@ -48604,7 +62973,10 @@ 0.0286, 0.17875 ], - "limit": 262144 + "knowledge": "2025-04", + "limit": 262144, + "max_output": 65536, + "released": "2025-09-23" }, "qwen/qwen3.5-122b-a10b": { "cost": [ @@ -48613,7 +62985,10 @@ 0.023, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2026-02-23" }, "qwen/qwen3.5-27b": { "cost": [ @@ -48622,7 +62997,10 @@ 0.0172, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2026-02-23" }, "qwen/qwen3.5-35b-a3b": { "cost": [ @@ -48631,7 +63009,10 @@ 0.020357, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2026-02-23" }, "qwen/qwen3.5-397b-a17b": { "cost": [ @@ -48640,7 +63021,10 @@ 0.0344, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2026-02-15" }, "qwen/qwen3.5-4b": { "cost": [ @@ -48649,7 +63033,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-03-02" }, "qwen/qwen3.5-9b": { "cost": [ @@ -48658,7 +63045,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-02-23" }, "qwen/qwen3.5-flash": { "cost": [ @@ -48667,7 +63057,9 @@ 0.0029, 0.03625 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 250000, + "released": "2026-02-23" }, "qwen/qwen3.5-plus": { "cost": [ @@ -48676,7 +63068,10 @@ 0.0115, 0.14375 ], - "limit": 1000000 + "knowledge": "2025-04", + "limit": 1000000, + "max_output": 250000, + "released": "2026-02-16" }, "qwen/qwen3.6-27b": { "cost": [ @@ -48685,7 +63080,10 @@ 0.0, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 64000, + "open": true, + "released": "2026-04-22" }, "qwen/qwen3.6-35b-a3b": { "cost": [ @@ -48694,7 +63092,10 @@ 0.0496, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-04-17" }, "qwen/qwen3.6-flash": { "cost": [ @@ -48703,7 +63104,9 @@ 0.0165, 0.20625 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 250000, + "released": "2026-04-27" }, "qwen/qwen3.6-max-preview": { "cost": [ @@ -48712,7 +63115,10 @@ 0.0, 0.0 ], - "limit": 256000 + "knowledge": "2025-04", + "limit": 256000, + "max_output": 65536, + "released": "2026-04-20" }, "qwen/qwen3.6-plus": { "cost": [ @@ -48721,7 +63127,10 @@ 0.0276, 0.345 ], - "limit": 1000000 + "knowledge": "2025-04", + "limit": 1000000, + "max_output": 250000, + "released": "2026-04-02" }, "qwen/qwen3.7-max": { "cost": [ @@ -48730,7 +63139,9 @@ 0.165, 1.03125 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 250000, + "released": "2026-05-21" }, "qwen/qwen3.7-plus": { "cost": [ @@ -48739,7 +63150,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-04", + "limit": 1000000, + "max_output": 65536, + "released": "2026-06-02" }, "qwen/qwen3.8-2.4t-a95b": { "cost": [ @@ -48748,7 +63162,10 @@ 0.5, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 1010000, + "open": true, + "released": "2026-08-12" }, "qwen/qwen3.8-flash": { "cost": [ @@ -48757,7 +63174,9 @@ 0.016, 0.0 ], - "limit": 977000 + "limit": 977000, + "max_output": 128000, + "released": "2026-08-26" }, "qwen/qwen3.8-max": { "cost": [ @@ -48766,7 +63185,9 @@ 0.25, 2.5 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-08-03" }, "sakana/fugu-max": { "cost": [ @@ -48775,7 +63196,9 @@ 0.25, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-11" }, "sakana/fugu-ultra": { "cost": [ @@ -48785,6 +63208,8 @@ 0.0 ], "limit": 1000000, + "max_output": 128000, + "released": "2026-06-15", "tiers": [ { "cost": [ @@ -48807,7 +63232,9 @@ 0.15, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "released": "2026-08-03" }, "thinkingmachines/inkling": { "cost": [ @@ -48816,7 +63243,10 @@ 0.17, 0.0 ], - "limit": 1048000 + "limit": 1048000, + "max_output": 32000, + "open": true, + "released": "2026-07-15" }, "writer/palmyra-x4": { "cost": [ @@ -48825,7 +63255,9 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 32000, + "released": "2024-10-09" }, "writer/palmyra-x5": { "cost": [ @@ -48834,7 +63266,9 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 250000, + "released": "2025-04-28" }, "xai/grok-4.20-0309-non-reasoning": { "cost": [ @@ -48843,7 +63277,9 @@ 0.2, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 1000000, + "released": "2026-03-09" }, "xai/grok-4.20-0309-reasoning": { "cost": [ @@ -48853,6 +63289,8 @@ 0.0 ], "limit": 1000000, + "max_output": 1000000, + "released": "2026-03-09", "tiers": [ { "cost": [ @@ -48876,6 +63314,8 @@ 0.0 ], "limit": 1000000, + "max_output": 1000000, + "released": "2026-04-17", "tiers": [ { "cost": [ @@ -48898,7 +63338,9 @@ 0.5, 0.0 ], - "limit": 500000 + "limit": 500000, + "max_output": 500000, + "released": "2026-07-08" }, "xai/grok-4.6": { "cost": [ @@ -48907,7 +63349,10 @@ 0.5, 0.0 ], + "knowledge": "2026-02-01", "limit": 500000, + "max_output": 500000, + "released": "2026-08-12", "tiers": [ { "cost": [ @@ -48930,7 +63375,10 @@ 0.5, 0.0 ], + "knowledge": "2026-05", "limit": 500000, + "max_output": 500000, + "released": "2026-09-21", "tiers": [ { "cost": [ @@ -48953,7 +63401,9 @@ 0.2, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 256000, + "released": "2026-04-16" }, "zai/glm-4.5": { "cost": [ @@ -48962,7 +63412,11 @@ 0.11, 0.0 ], - "limit": 128000 + "knowledge": "2025-04", + "limit": 128000, + "max_output": 98304, + "open": true, + "released": "2025-07-28" }, "zai/glm-4.5-air": { "cost": [ @@ -48971,7 +63425,11 @@ 0.03, 0.0 ], - "limit": 128000 + "knowledge": "2025-04", + "limit": 128000, + "max_output": 98304, + "open": true, + "released": "2025-07-28" }, "zai/glm-4.5v": { "cost": [ @@ -48980,7 +63438,11 @@ 0.11, 0.0 ], - "limit": 128000 + "knowledge": "2025-04", + "limit": 128000, + "max_output": 32000, + "open": true, + "released": "2025-08-11" }, "zai/glm-4.6": { "cost": [ @@ -48989,7 +63451,11 @@ 0.11, 0.0 ], - "limit": 200000 + "knowledge": "2025-04", + "limit": 200000, + "max_output": 131072, + "open": true, + "released": "2025-09-30" }, "zai/glm-4.7": { "cost": [ @@ -48998,7 +63464,11 @@ 0.11, 0.0 ], - "limit": 200000 + "knowledge": "2025-04", + "limit": 200000, + "max_output": 131072, + "open": true, + "released": "2025-12-22" }, "zai/glm-4.7-flash": { "cost": [ @@ -49007,7 +63477,11 @@ 0.0, 0.0 ], - "limit": 200000 + "knowledge": "2025-04", + "limit": 200000, + "max_output": 128000, + "open": true, + "released": "2026-01-19" }, "zai/glm-4.7-flashx": { "cost": [ @@ -49016,7 +63490,11 @@ 0.01, 0.0 ], - "limit": 200000 + "knowledge": "2025-04", + "limit": 200000, + "max_output": 131072, + "open": true, + "released": "2026-01-19" }, "zai/glm-5": { "cost": [ @@ -49025,7 +63503,10 @@ 0.2, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 131072, + "open": true, + "released": "2026-02-12" }, "zai/glm-5-turbo": { "cost": [ @@ -49034,7 +63515,9 @@ 0.24, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 131072, + "released": "2026-03-16" }, "zai/glm-5.1": { "cost": [ @@ -49043,7 +63526,10 @@ 0.26, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 131072, + "open": true, + "released": "2026-04-07" }, "zai/glm-5.2": { "cost": [ @@ -49052,7 +63538,10 @@ 0.195, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "zai/glm-5.3": { "cost": [ @@ -49061,7 +63550,10 @@ 0.13, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "zai/glm-5.3-flash": { "cost": [ @@ -49070,7 +63562,10 @@ 0.03, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-26" } }, "name": "Merge Gateway" @@ -49084,7 +63579,9 @@ 0.15, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-04-08" }, "muse-spark-1.2": { "cost": [ @@ -49093,7 +63590,9 @@ 0.15, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-08-05" }, "muse-spark-1.2-contributor": { "cost": [ @@ -49102,7 +63601,9 @@ 0.002, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-08-05" }, "muse-spark-1.3": { "cost": [ @@ -49111,7 +63612,9 @@ 0.15, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-09-02" }, "muse-spark-1.3-contributor": { "cost": [ @@ -49120,7 +63623,9 @@ 0.002, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-09-02" }, "muse-wonder-1.0": { "cost": [ @@ -49129,7 +63634,9 @@ 0.2, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-10-12" } }, "name": "Meta" @@ -49144,6 +63651,9 @@ 0.0 ], "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-10-27", "status": "deprecated" }, "MiniMax-M2.1": { @@ -49154,6 +63664,9 @@ 0.375 ], "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-12-23", "status": "deprecated" }, "MiniMax-M2.5": { @@ -49164,6 +63677,9 @@ 0.375 ], "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-02-12", "status": "deprecated" }, "MiniMax-M2.5-highspeed": { @@ -49174,6 +63690,9 @@ 0.375 ], "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-02-13", "status": "deprecated" }, "MiniMax-M2.7": { @@ -49184,6 +63703,9 @@ 0.375 ], "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-03-18", "status": "deprecated" }, "MiniMax-M2.7-highspeed": { @@ -49194,6 +63716,9 @@ 0.375 ], "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-03-18", "status": "deprecated" }, "MiniMax-M3": { @@ -49204,6 +63729,9 @@ 0.0 ], "limit": 1000000, + "max_output": 524288, + "open": true, + "released": "2026-06-01", "tiers": [ { "cost": [ @@ -49226,7 +63754,9 @@ 0.015, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 524288, + "released": "2026-10-19" } }, "name": "MiniMax (minimax.io)" @@ -49241,6 +63771,9 @@ 0.3922 ], "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-10-27", "status": "deprecated" }, "MiniMax-M2.1": { @@ -49251,6 +63784,9 @@ 0.3922 ], "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-12-23", "status": "deprecated" }, "MiniMax-M2.5": { @@ -49261,6 +63797,9 @@ 0.3922 ], "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-02-12", "status": "deprecated" }, "MiniMax-M2.5-highspeed": { @@ -49271,6 +63810,9 @@ 0.3922 ], "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-02-13", "status": "deprecated" }, "MiniMax-M2.7": { @@ -49281,6 +63823,9 @@ 0.3922 ], "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-03-18", "status": "deprecated" }, "MiniMax-M2.7-highspeed": { @@ -49291,6 +63836,9 @@ 0.3922 ], "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-03-18", "status": "deprecated" }, "MiniMax-M3": { @@ -49301,6 +63849,9 @@ 0.0 ], "limit": 1000000, + "max_output": 524288, + "open": true, + "released": "2026-06-01", "tiers": [ { "cost": [ @@ -49323,7 +63874,9 @@ 0.0149, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 524288, + "released": "2026-10-19" } }, "name": "MiniMax (minimax.cn)" @@ -49338,6 +63891,9 @@ 0.0 ], "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-10-27", "status": "deprecated" }, "MiniMax-M2.1": { @@ -49348,6 +63904,9 @@ 0.0 ], "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-12-23", "status": "deprecated" }, "MiniMax-M2.5": { @@ -49358,6 +63917,9 @@ 0.0 ], "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-02-12", "status": "deprecated" }, "MiniMax-M2.5-highspeed": { @@ -49368,6 +63930,9 @@ 0.0 ], "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-02-13", "status": "deprecated" }, "MiniMax-M2.7": { @@ -49378,6 +63943,9 @@ 0.0 ], "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-03-18", "status": "deprecated" }, "MiniMax-M2.7-highspeed": { @@ -49388,6 +63956,9 @@ 0.0 ], "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-03-18", "status": "deprecated" }, "MiniMax-M3": { @@ -49397,7 +63968,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 524288, + "open": true, + "released": "2026-06-01" }, "MiniMax-M3.1-Flash": { "cost": [ @@ -49406,7 +63980,9 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 524288, + "released": "2026-10-19" }, "MiniMax-M3.1-Flash-Preview": { "cost": [ @@ -49416,6 +63992,8 @@ 0.0 ], "limit": 1000000, + "max_output": 512000, + "released": "2026-09-27", "status": "deprecated" } }, @@ -49431,6 +64009,9 @@ 0.0 ], "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-10-27", "status": "deprecated" }, "MiniMax-M2.1": { @@ -49441,6 +64022,9 @@ 0.0 ], "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-12-23", "status": "deprecated" }, "MiniMax-M2.5": { @@ -49451,6 +64035,9 @@ 0.0 ], "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-02-12", "status": "deprecated" }, "MiniMax-M2.5-highspeed": { @@ -49461,6 +64048,9 @@ 0.0 ], "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-02-13", "status": "deprecated" }, "MiniMax-M2.7": { @@ -49471,6 +64061,9 @@ 0.0 ], "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-03-18", "status": "deprecated" }, "MiniMax-M2.7-highspeed": { @@ -49481,6 +64074,9 @@ 0.0 ], "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-03-18", "status": "deprecated" }, "MiniMax-M3": { @@ -49490,7 +64086,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 524288, + "open": true, + "released": "2026-06-01" }, "MiniMax-M3.1-Flash": { "cost": [ @@ -49499,7 +64098,9 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 524288, + "released": "2026-10-19" }, "MiniMax-M3.1-Flash-Preview": { "cost": [ @@ -49509,6 +64110,8 @@ 0.0 ], "limit": 1000000, + "max_output": 512000, + "released": "2026-09-27", "status": "deprecated" } }, @@ -49523,7 +64126,9 @@ 0.03, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 8192, + "released": "2025-07-30" }, "codestral-latest": { "cost": [ @@ -49532,7 +64137,11 @@ 0.03, 0.0 ], - "limit": 256000 + "knowledge": "2024-10", + "limit": 256000, + "max_output": 4096, + "open": true, + "released": "2024-05-29" }, "devstral-2512": { "cost": [ @@ -49541,7 +64150,11 @@ 0.0, 0.0 ], + "knowledge": "2025-12", "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2025-12-09", "status": "deprecated" }, "devstral-latest": { @@ -49551,7 +64164,11 @@ 0.0, 0.0 ], + "knowledge": "2025-12", "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2025-12-09", "status": "deprecated" }, "devstral-medium-latest": { @@ -49561,7 +64178,11 @@ 0.0, 0.0 ], + "knowledge": "2025-12", "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2025-12-02", "status": "deprecated" }, "glm-5-2": { @@ -49572,6 +64193,9 @@ 0.0 ], "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-06-13", "status": "deprecated" }, "labs-devstral-small-2512": { @@ -49581,7 +64205,11 @@ 0.0, 0.0 ], + "knowledge": "2025-12", "limit": 256000, + "max_output": 256000, + "open": true, + "released": "2025-12-09", "status": "deprecated" }, "labs-leanstral-1-5-1": { @@ -49592,6 +64220,9 @@ 0.0 ], "limit": 262144, + "max_output": 128000, + "open": true, + "released": "2026-06-30", "status": "deprecated" }, "magistral-medium-latest": { @@ -49601,7 +64232,11 @@ 0.0, 0.0 ], + "knowledge": "2025-06", "limit": 262144, + "max_output": 16384, + "open": true, + "released": "2025-03-17", "status": "deprecated" }, "ministral-14b-2512": { @@ -49611,7 +64246,10 @@ 0.02, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2025-12-02" }, "ministral-3b-2512": { "cost": [ @@ -49620,7 +64258,10 @@ 0.01, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 262144, + "open": true, + "released": "2025-12-02" }, "ministral-3b-latest": { "cost": [ @@ -49629,7 +64270,11 @@ 0.01, 0.0 ], - "limit": 131072 + "knowledge": "2024-10", + "limit": 131072, + "max_output": 128000, + "open": true, + "released": "2024-10-01" }, "ministral-8b-2512": { "cost": [ @@ -49638,7 +64283,10 @@ 0.015, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2025-12-02" }, "ministral-8b-latest": { "cost": [ @@ -49647,7 +64295,11 @@ 0.015, 0.0 ], - "limit": 262144 + "knowledge": "2024-10", + "limit": 262144, + "max_output": 128000, + "open": true, + "released": "2024-10-01" }, "mistral-embed": { "cost": [ @@ -49656,7 +64308,10 @@ 0.0, 0.0 ], - "limit": 8000 + "limit": 8000, + "max_output": 3072, + "released": "2023-12-11", + "type": "embedding" }, "mistral-large-2512": { "cost": [ @@ -49665,7 +64320,11 @@ 0.05, 0.0 ], - "limit": 262144 + "knowledge": "2024-11", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2024-11-01" }, "mistral-large-4": { "cost": [ @@ -49675,6 +64334,8 @@ 0.0 ], "limit": 1048576, + "max_output": 262144, + "released": "2026-10-06", "status": "beta" }, "mistral-large-latest": { @@ -49684,7 +64345,11 @@ 0.05, 0.0 ], - "limit": 262144 + "knowledge": "2024-11", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2024-11-01" }, "mistral-medium-2505": { "cost": [ @@ -49693,7 +64358,10 @@ 0.0, 0.0 ], + "knowledge": "2025-05", "limit": 131072, + "max_output": 131072, + "released": "2025-05-07", "status": "deprecated" }, "mistral-medium-2508": { @@ -49703,7 +64371,10 @@ 0.0, 0.0 ], + "knowledge": "2025-05", "limit": 262144, + "max_output": 262144, + "released": "2025-08-12", "status": "deprecated" }, "mistral-medium-2604": { @@ -49713,7 +64384,10 @@ 0.15, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-29" }, "mistral-medium-latest": { "cost": [ @@ -49722,7 +64396,10 @@ 0.15, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-29" }, "mistral-small-2506": { "cost": [ @@ -49731,7 +64408,11 @@ 0.0, 0.0 ], + "knowledge": "2025-03", "limit": 128000, + "max_output": 16384, + "open": true, + "released": "2025-06-20", "status": "deprecated" }, "mistral-small-2603": { @@ -49741,7 +64422,11 @@ 0.015, 0.0 ], - "limit": 262144 + "knowledge": "2025-06", + "limit": 262144, + "max_output": 256000, + "open": true, + "released": "2026-03-16" }, "mistral-small-latest": { "cost": [ @@ -49750,7 +64435,11 @@ 0.015, 0.0 ], - "limit": 262144 + "knowledge": "2025-06", + "limit": 262144, + "max_output": 256000, + "open": true, + "released": "2026-03-16" }, "open-mistral-nemo": { "cost": [ @@ -49759,7 +64448,11 @@ 0.0, 0.0 ], + "knowledge": "2024-07", "limit": 128000, + "max_output": 128000, + "open": true, + "released": "2024-07-01", "status": "deprecated" }, "pixtral-12b": { @@ -49769,7 +64462,11 @@ 0.0, 0.0 ], + "knowledge": "2024-09", "limit": 128000, + "max_output": 128000, + "open": true, + "released": "2024-09-01", "status": "deprecated" }, "voxtral-small-2507": { @@ -49779,7 +64476,10 @@ 0.0, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 32000, + "open": true, + "released": "2025-07-15" }, "voxtral-small-latest": { "cost": [ @@ -49788,7 +64488,10 @@ 0.0, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 32000, + "open": true, + "released": "2025-07-15" }, "zai-glm-5-2": { "cost": [ @@ -49798,6 +64501,9 @@ 0.0 ], "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-06-13", "status": "deprecated" }, "zai-glm-5-3": { @@ -49807,7 +64513,10 @@ 0.14, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "zai-glm-5-3-flash": { "cost": [ @@ -49816,7 +64525,10 @@ 0.03, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-08-26" } }, "name": "Mistral" @@ -49830,7 +64542,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-02-23" }, "qwen/qwen3.5-27b": { "cost": [ @@ -49839,7 +64554,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-02-23" }, "qwen/qwen3.5-35b-a3b": { "cost": [ @@ -49848,7 +64566,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-02-23" }, "qwen/qwen3.5-397b-a17b": { "cost": [ @@ -49857,7 +64578,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-02-15" }, "qwen/qwen3.5-9b": { "cost": [ @@ -49866,7 +64590,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-02-23" } }, "name": "Mixlayer" @@ -49880,7 +64607,11 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "DeepSeek-V4-Pro": { "cost": [ @@ -49889,7 +64620,11 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "GLM-4.7": { "cost": [ @@ -49898,7 +64633,11 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-12-22", "status": "deprecated" }, "GLM-5.3": { @@ -49908,7 +64647,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "Kimi-K2.6": { "cost": [ @@ -49917,7 +64659,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-20" }, "MiniMax-M2.1": { "cost": [ @@ -49927,6 +64673,9 @@ 0.0 ], "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-12-23", "status": "deprecated" }, "MiniMax-M2.7": { @@ -49936,7 +64685,10 @@ 0.0, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-03-18" }, "Qwen3.6-Flash": { "cost": [ @@ -49945,7 +64697,9 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 65536, + "released": "2026-04-27" }, "deepseek-v4-flash-0731": { "cost": [ @@ -49954,7 +64708,11 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-07-31" }, "kimi-k3": { "cost": [ @@ -49963,7 +64721,10 @@ 0.0, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-16" } }, "name": "Moark" @@ -49977,7 +64738,10 @@ 0.25, 0.0 ], - "limit": 1010000 + "limit": 1010000, + "max_output": 131072, + "open": true, + "released": "2026-08-12" }, "deepseek-ai/DeepSeek-V4.1-Flash": { "cost": [ @@ -49986,7 +64750,11 @@ 0.03, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-09-10" }, "meta-models/Muse-Spark-Open-816B-A42B": { "cost": [ @@ -49995,7 +64763,11 @@ 0.15, 0.0 ], - "limit": 1048576 + "knowledge": "2026-01-04", + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-10-15" }, "moonshotai/Kimi-K3": { "cost": [ @@ -50004,7 +64776,10 @@ 0.3, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-16" }, "nvidia/GLM-5.3-Flash-NVFP4": { "cost": [ @@ -50013,7 +64788,10 @@ 0.03, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-26" }, "thinkingmachines/Inkling-NVFP4": { "cost": [ @@ -50022,7 +64800,10 @@ 0.27, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 262144, + "open": true, + "released": "2026-07-15" }, "zai-org/GLM-5.3": { "cost": [ @@ -50031,7 +64812,10 @@ 0.26, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "zai-org/GLM-5.3-Flash": { "cost": [ @@ -50040,7 +64824,10 @@ 0.09, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-26" } }, "name": "Modal" @@ -50054,7 +64841,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-09" }, "claude-opus-4-8": { "cost": [ @@ -50063,7 +64853,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2026-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-28" }, "claude-sonnet-4-6": { "cost": [ @@ -50072,7 +64865,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-08-31", + "limit": 1000000, + "max_output": 64000, + "released": "2026-02-17" }, "deepseek-v4-flash": { "cost": [ @@ -50081,7 +64877,11 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "deepseek-v4-pro": { "cost": [ @@ -50090,7 +64890,11 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "gemini-2.5-flash": { "cost": [ @@ -50099,7 +64903,10 @@ 0.0, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2025-06-17" }, "gemini-2.5-pro": { "cost": [ @@ -50108,7 +64915,10 @@ 0.0, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2025-06-17" }, "qwen/qwen3.7-max": { "cost": [ @@ -50117,7 +64927,9 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-05-21" }, "qwen/qwen3.7-plus": { "cost": [ @@ -50126,7 +64938,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-04", + "limit": 1000000, + "max_output": 64000, + "released": "2026-06-02" } }, "name": "Modelis" @@ -50140,7 +64955,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-04", + "limit": 262144, + "max_output": 131072, + "open": true, + "released": "2025-07-21" }, "Qwen/Qwen3-235B-A22B-Thinking-2507": { "cost": [ @@ -50149,7 +64968,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-04", + "limit": 262144, + "max_output": 131072, + "open": true, + "released": "2025-07-25" }, "Qwen/Qwen3-30B-A3B-Instruct-2507": { "cost": [ @@ -50158,7 +64981,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-04", + "limit": 262144, + "max_output": 16384, + "open": true, + "released": "2025-07-28" }, "Qwen/Qwen3-30B-A3B-Thinking-2507": { "cost": [ @@ -50167,7 +64994,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-04", + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2025-07-30" }, "Qwen/Qwen3-Coder-30B-A3B-Instruct": { "cost": [ @@ -50176,7 +65007,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-04", + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2025-07-31" }, "ZhipuAI/GLM-4.5": { "cost": [ @@ -50185,7 +65020,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2025-04", + "limit": 131072, + "max_output": 98304, + "open": true, + "released": "2025-07-28" }, "ZhipuAI/GLM-4.6": { "cost": [ @@ -50194,11 +65033,69 @@ 0.0, 0.0 ], - "limit": 202752 + "knowledge": "2025-07", + "limit": 202752, + "max_output": 98304, + "open": true, + "released": "2025-09-30" } }, "name": "ModelScope" }, + "modular": { + "models": { + "MiniMaxAI/MiniMax-M3.1-Flash": { + "cost": [ + 0.15, + 0.6, + 0.015, + 0.0 + ], + "limit": 1048576, + "max_output": 512000, + "released": "2026-10-19" + }, + "deepseek/deepseek-v4.1-flash": { + "cost": [ + 0.17, + 1.2, + 0.02, + 0.0 + ], + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-09-10" + }, + "google/gemma-4-31b-it": { + "cost": [ + 0.25, + 0.65, + 0.08, + 0.0 + ], + "knowledge": "2025-01", + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-04-02" + }, + "minimax/minimax-m3": { + "cost": [ + 0.3, + 1.2, + 0.06, + 0.0 + ], + "limit": 1048576, + "max_output": 512000, + "open": true, + "released": "2026-06-01" + } + }, + "name": "Modular" + }, "moonshotai": { "models": { "kimi-k2.6": { @@ -50208,7 +65105,11 @@ 0.16, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-20" }, "kimi-k2.7-code": { "cost": [ @@ -50217,7 +65118,11 @@ 0.19, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-06-12" }, "kimi-k2.7-code-highspeed": { "cost": [ @@ -50226,7 +65131,11 @@ 0.38, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-06-12" }, "kimi-k3": { "cost": [ @@ -50235,7 +65144,32 @@ 0.3, 3.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-07-16" + }, + "kimi-k3.1-pro": { + "cost": [ + 2.0, + 10.0, + 0.2, + 2.0 + ], + "limit": 1048576, + "max_output": 1048576, + "released": "2026-10-23" + }, + "kimi-k3.1-pro-highspeed": { + "cost": [ + 4.0, + 20.0, + 0.2, + 4.0 + ], + "limit": 1048576, + "max_output": 1048576, + "released": "2026-10-23" } }, "name": "Moonshot AI" @@ -50249,7 +65183,11 @@ 0.1643, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-20" }, "kimi-k2.7-code": { "cost": [ @@ -50258,7 +65196,11 @@ 0.1942, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-06-12" }, "kimi-k2.7-code-highspeed": { "cost": [ @@ -50267,7 +65209,11 @@ 0.3884, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-06-12" }, "kimi-k3": { "cost": [ @@ -50276,7 +65222,32 @@ 0.2988, 2.9879 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-07-16" + }, + "kimi-k3.1-pro": { + "cost": [ + 1.9437, + 10.1671, + 0.1944, + 1.9437 + ], + "limit": 1048576, + "max_output": 1048576, + "released": "2026-10-23" + }, + "kimi-k3.1-pro-highspeed": { + "cost": [ + 3.8874, + 20.3342, + 0.1944, + 3.8874 + ], + "limit": 1048576, + "max_output": 1048576, + "released": "2026-10-23" } }, "name": "Moonshot AI (China)" @@ -50290,7 +65261,108 @@ 0.0, 0.0 ], - "limit": 32000 + "limit": 32000, + "max_output": 32000, + "released": "2024-06-01" + }, + "morph-dsv41flash": { + "cost": [ + 0.12, + 0.8, + 0.008, + 0.0 + ], + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-09-10" + }, + "morph-dsv41flash-1017": { + "cost": [ + 0.12, + 0.8, + 0.008, + 0.0 + ], + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-10-17" + }, + "morph-dsv4flash": { + "cost": [ + 0.141953125, + 0.399625, + 0.0359375, + 0.0 + ], + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-07-31" + }, + "morph-glm52-744b": { + "cost": [ + 1.19, + 6.0, + 0.1955, + 0.0 + ], + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-06-13" + }, + "morph-glm53-744b": { + "cost": [ + 1.19, + 6.0, + 0.1955, + 0.0 + ], + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-08-14" + }, + "morph-glm53flash": { + "cost": [ + 0.2, + 0.7, + 0.04, + 0.0 + ], + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-08-26" + }, + "morph-kimik3": { + "cost": [ + 2.5, + 14.0, + 0.29, + 0.0 + ], + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-07-16" + }, + "morph-kimik3-fast": { + "cost": [ + 6.0, + 22.5, + 0.6, + 0.0 + ], + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-07-16" }, "morph-v3-fast": { "cost": [ @@ -50299,7 +65371,9 @@ 0.0, 0.0 ], - "limit": 16000 + "limit": 262144, + "max_output": 131072, + "released": "2025-07-07" }, "morph-v3-large": { "cost": [ @@ -50308,11 +65382,137 @@ 0.0, 0.0 ], - "limit": 32000 + "limit": 262144, + "max_output": 131072, + "released": "2025-07-07" } }, "name": "Morph" }, + "munito": { + "models": { + "aleph-alpha/kolibri-1": { + "cost": [ + 0.13, + 0.51, + 0.078, + 0.0 + ], + "knowledge": "2026-06-18", + "limit": 1048576, + "max_output": 943718, + "open": true, + "released": "2026-10-03" + }, + "deepseek-ai/deepseek-v4-flash": { + "cost": [ + 0.099, + 0.25, + 0.019, + 0.0 + ], + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 943718, + "open": true, + "released": "2026-07-31" + }, + "deepseek-ai/deepseek-v4.1-flash-1017": { + "cost": [ + 0.27, + 1.0, + 0.0054, + 0.0 + ], + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 943718, + "open": true, + "released": "2026-10-17", + "status": "beta" + }, + "qwen/qwen3.8-27b": { + "cost": [ + 0.18, + 2.4, + 0.05, + 0.0 + ], + "limit": 262144, + "max_output": 235929, + "open": true, + "released": "2026-08-14" + }, + "zai-org/glm-5.3-flash": { + "cost": [ + 0.13, + 0.45, + 0.027, + 0.0 + ], + "limit": 1048576, + "max_output": 943718, + "open": true, + "released": "2026-08-26" + } + }, + "name": "Munito AI" + }, + "munito-eu": { + "models": { + "aleph-alpha/kolibri-1": { + "cost": [ + 0.16, + 0.56, + 0.094, + 0.0 + ], + "knowledge": "2026-06-18", + "limit": 1048576, + "max_output": 943718, + "open": true, + "released": "2026-10-03" + }, + "deepseek-ai/deepseek-v4-flash": { + "cost": [ + 0.11, + 0.28, + 0.022, + 0.0 + ], + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 943718, + "open": true, + "released": "2026-07-31" + }, + "qwen/qwen3.8-27b": { + "cost": [ + 0.2, + 2.7, + 0.11, + 0.0 + ], + "limit": 262144, + "max_output": 235929, + "open": true, + "released": "2026-08-14" + }, + "zai-org/glm-5.3-flash": { + "cost": [ + 0.15, + 0.5, + 0.03, + 0.0 + ], + "limit": 1048576, + "max_output": 943718, + "open": true, + "released": "2026-08-26" + } + }, + "name": "Munito AI (EU)" + }, "nan": { "models": { "deepseek-v4-flash": { @@ -50322,7 +65522,11 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-09-10" }, "gemma4": { "cost": [ @@ -50331,7 +65535,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-04-02" }, "glm5.3": { "cost": [ @@ -50340,7 +65547,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "glm5.3-flash": { "cost": [ @@ -50349,7 +65559,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-26" }, "mimo-v2.6-flash": { "cost": [ @@ -50358,7 +65571,10 @@ 0.0, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-09-22" }, "qwen-image-2.1": { "cost": [ @@ -50367,7 +65583,10 @@ 0.0, 0.0 ], - "limit": 8192 + "limit": 8192, + "open": true, + "released": "2026-09-14", + "type": "image" }, "qwen3.6": { "cost": [ @@ -50376,7 +65595,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-04-17" }, "qwen3.8-flash": { "cost": [ @@ -50385,7 +65607,9 @@ 0.0, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-08-26" } }, "name": "NaN" @@ -50399,7 +65623,10 @@ 0.2465, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 32768, + "open": true, + "released": "2025-11-24" }, "EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.0": { "cost": [ @@ -50408,7 +65635,10 @@ 1.003, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 16384, + "open": true, + "released": "2025-07-26" }, "EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1": { "cost": [ @@ -50417,7 +65647,10 @@ 1.003, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 16384, + "open": true, + "released": "2025-09-25" }, "EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2": { "cost": [ @@ -50426,7 +65659,10 @@ 0.3995, 0.0 ], - "limit": 16384 + "limit": 16384, + "max_output": 8192, + "open": true, + "released": "2025-07-26" }, "EVA-UNIT-01/EVA-Qwen2.5-72B-v0.2": { "cost": [ @@ -50435,7 +65671,10 @@ 0.3995, 0.0 ], - "limit": 16384 + "limit": 16384, + "max_output": 8192, + "open": true, + "released": "2025-09-25" }, "Envoid/Llama-3.05-NT-Storybreaker-Ministral-70B": { "cost": [ @@ -50444,7 +65683,10 @@ 0.2465, 0.0 ], - "limit": 16384 + "limit": 16384, + "max_output": 8192, + "open": true, + "released": "2024-01-01" }, "Envoid/Llama-3.05-Nemotron-Tenyxchat-Storybreaker-70B": { "cost": [ @@ -50453,7 +65695,10 @@ 0.2465, 0.0 ], - "limit": 16384 + "limit": 16384, + "max_output": 8192, + "open": true, + "released": "2024-01-01" }, "GLM-4.6-Derestricted-v5": { "cost": [ @@ -50462,7 +65707,10 @@ 0.2, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 8192, + "open": true, + "released": "2025-12-23" }, "GalrionSoftworks/MN-LooseCannon-12B-v1": { "cost": [ @@ -50471,7 +65719,10 @@ 0.2465, 0.0 ], - "limit": 16384 + "limit": 16384, + "max_output": 8192, + "open": true, + "released": "2024-01-01" }, "Gemma-4-26B-A4B-MeroMero": { "cost": [ @@ -50480,7 +65731,10 @@ 0.06, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-07-29" }, "Gemma-4-26B-A4B-MeroMero:thinking": { "cost": [ @@ -50489,7 +65743,46 @@ 0.06, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-07-29" + }, + "Gemma-4-31B-Agares-v1": { + "cost": [ + 0.306, + 0.306, + 0.0, + 0.0 + ], + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-05-15" + }, + "Gemma-4-31B-Animus-V14.1": { + "cost": [ + 0.306, + 0.306, + 0.0, + 0.0 + ], + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-05-15" + }, + "Gemma-4-31B-AssGuard": { + "cost": [ + 0.306, + 0.306, + 0.0, + 0.0 + ], + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-05-15" }, "Gemma-4-31B-Claude-4.6-Opus-Reasoning-Distilled": { "cost": [ @@ -50498,7 +65791,10 @@ 0.0306, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 16384, + "open": true, + "released": "2026-05-01" }, "Gemma-4-31B-Cognitive-Unshackled": { "cost": [ @@ -50507,7 +65803,22 @@ 0.153, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 16384, + "open": true, + "released": "2026-05-01" + }, + "Gemma-4-31B-Dark-Gemistry": { + "cost": [ + 0.306, + 0.306, + 0.0, + 0.0 + ], + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-05-15" }, "Gemma-4-31B-DarkIdol": { "cost": [ @@ -50516,7 +65827,22 @@ 0.153, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 16384, + "open": true, + "released": "2026-05-01" + }, + "Gemma-4-31B-Fabled": { + "cost": [ + 0.306, + 0.306, + 0.0, + 0.0 + ], + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-05-02" }, "Gemma-4-31B-GarnetV2": { "cost": [ @@ -50525,7 +65851,70 @@ 0.153, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 16384, + "open": true, + "released": "2026-05-01" + }, + "Gemma-4-31B-Gembrain-X-Core": { + "cost": [ + 0.306, + 0.306, + 0.0, + 0.0 + ], + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-05-15" + }, + "Gemma-4-31B-Gembrain-uncensored-heretic": { + "cost": [ + 0.306, + 0.306, + 0.0, + 0.0 + ], + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-05-15" + }, + "Gemma-4-31B-Isometry-RP": { + "cost": [ + 0.306, + 0.306, + 0.0, + 0.0 + ], + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-05-15" + }, + "Gemma-4-31B-K1-v5": { + "cost": [ + 0.306, + 0.306, + 0.0, + 0.0 + ], + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-05-02" + }, + "Gemma-4-31B-MeroMero": { + "cost": [ + 0.306, + 0.306, + 0.0, + 0.0 + ], + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-05-02" }, "Gemma-4-31B-MeroMero-v2": { "cost": [ @@ -50534,7 +65923,10 @@ 0.05, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-07-29" }, "Gemma-4-31B-MeroMero-v2:thinking": { "cost": [ @@ -50543,7 +65935,22 @@ 0.05, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-07-29" + }, + "Gemma-4-31B-Novelist": { + "cost": [ + 0.306, + 0.306, + 0.0, + 0.0 + ], + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-05-15" }, "Gemma-4-31B-Queen": { "cost": [ @@ -50552,7 +65959,34 @@ 0.153, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 16384, + "open": true, + "released": "2026-05-01" + }, + "Gemma-4-31B-SDFT-Heretic-RP": { + "cost": [ + 0.306, + 0.306, + 0.0, + 0.0 + ], + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-05-15" + }, + "Gemma-4-31B-StyleTune": { + "cost": [ + 0.306, + 0.306, + 0.0, + 0.0 + ], + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-05-15" }, "Gryphe/MythoMax-L2-13b": { "cost": [ @@ -50561,7 +65995,10 @@ 0.05015, 0.0 ], - "limit": 4096 + "limit": 4096, + "max_output": 3686, + "open": true, + "released": "2023-08-10" }, "LLM360/K2-Think": { "cost": [ @@ -50570,7 +66007,10 @@ 0.085, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 32768, + "open": true, + "released": "2025-07-26" }, "LatitudeGames/Wayfarer-Large-70B-Llama-3.3": { "cost": [ @@ -50579,7 +66019,10 @@ 0.35, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 16384, + "open": true, + "released": "2025-02-20" }, "MarinaraSpaghetti/NemoMix-Unleashed-12B": { "cost": [ @@ -50588,7 +66031,10 @@ 0.2465, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 8192, + "open": true, + "released": "2024-01-01" }, "Meta-Llama-3-1-8B-Instruct-FP8": { "cost": [ @@ -50597,7 +66043,10 @@ 0.01, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 16384, + "open": true, + "released": "2024-01-01" }, "MiniMax-M1": { "cost": [ @@ -50606,7 +66055,10 @@ 0.0697, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2025-01-08" }, "MiniMaxAI/MiniMax-M1-80k": { "cost": [ @@ -50615,7 +66067,10 @@ 0.3026, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2025-06-17" }, "NeverSleep/Lumimaid-v0.2-70B": { "cost": [ @@ -50624,7 +66079,10 @@ 0.5, 0.0 ], - "limit": 16384 + "limit": 16384, + "max_output": 8192, + "open": true, + "released": "2024-01-01" }, "NousResearch/hermes-3-llama-3.1-70b": { "cost": [ @@ -50633,7 +66091,11 @@ 0.204, 0.0 ], - "limit": 65536 + "knowledge": "2023-12-31", + "limit": 65536, + "max_output": 8192, + "open": true, + "released": "2024-08-18" }, "NousResearch/hermes-4-405b": { "cost": [ @@ -50642,7 +66104,11 @@ 0.15, 0.0 ], - "limit": 128000 + "knowledge": "2024-08-31", + "limit": 128000, + "max_output": 8192, + "open": true, + "released": "2025-08-26" }, "NousResearch/hermes-4-405b:thinking": { "cost": [ @@ -50651,7 +66117,23 @@ 0.15, 0.0 ], - "limit": 128000 + "knowledge": "2024-08-31", + "limit": 128000, + "max_output": 8192, + "open": true, + "released": "2025-08-26" + }, + "Qwen3.5-27B-Blossom-V6.4-Derestricted": { + "cost": [ + 0.306, + 0.306, + 0.0, + 0.0 + ], + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-05-15" }, "Qwen3.5-27B-BlueStar-v3-Derestricted": { "cost": [ @@ -50660,7 +66142,34 @@ 0.153, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 16384, + "open": true, + "released": "2026-04-30" + }, + "Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-Derestricted": { + "cost": [ + 0.306, + 0.306, + 0.0306, + 0.0 + ], + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-05-15" + }, + "Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-Derestricted-Lite": { + "cost": [ + 0.306, + 0.306, + 0.0306, + 0.0 + ], + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-05-15" }, "Qwen3.5-27B-Queen-Derestricted": { "cost": [ @@ -50669,7 +66178,10 @@ 0.153, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 16384, + "open": true, + "released": "2026-04-30" }, "ReadyArt/MS3.2-The-Omega-Directive-24B-Unslop-v2.0": { "cost": [ @@ -50678,7 +66190,10 @@ 0.25, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 32768, + "open": true, + "released": "2025-12-08" }, "Salesforce/Llama-xLAM-2-70b-fc-r": { "cost": [ @@ -50687,7 +66202,10 @@ 1.25, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 16384, + "open": true, + "released": "2025-04-13" }, "Sao10K/L3-8B-Stheno-v3.2": { "cost": [ @@ -50696,7 +66214,10 @@ 0.1003, 0.0 ], - "limit": 16384 + "limit": 16384, + "max_output": 8192, + "open": true, + "released": "2024-01-01" }, "Sao10K/L3.1-70B-Euryale-v2.2": { "cost": [ @@ -50705,7 +66226,11 @@ 0.153, 0.0 ], - "limit": 20480 + "knowledge": "2023-12-31", + "limit": 20480, + "max_output": 16384, + "open": true, + "released": "2024-08-28" }, "Sao10K/L3.1-70B-Hanami-x1": { "cost": [ @@ -50714,7 +66239,10 @@ 0.2465, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 16384, + "open": true, + "released": "2024-01-01" }, "Sao10K/L3.3-70B-Euryale-v2.3": { "cost": [ @@ -50723,7 +66251,11 @@ 0.2465, 0.0 ], - "limit": 20480 + "knowledge": "2023-12-31", + "limit": 20480, + "max_output": 16384, + "open": true, + "released": "2024-12-18" }, "Steelskull/L3.3-Cu-Mai-R1-70b": { "cost": [ @@ -50732,7 +66264,10 @@ 0.2465, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 16384, + "open": true, + "released": "2024-01-01" }, "Steelskull/L3.3-Electra-R1-70b": { "cost": [ @@ -50741,7 +66276,10 @@ 0.349945, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 16384, + "open": true, + "released": "2024-01-01" }, "Steelskull/L3.3-MS-Nevoria-70b": { "cost": [ @@ -50750,7 +66288,10 @@ 0.2465, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 16384, + "open": true, + "released": "2024-01-01" }, "Steelskull/L3.3-Nevoria-R1-70b": { "cost": [ @@ -50759,7 +66300,10 @@ 0.2465, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 16384, + "open": true, + "released": "2024-01-01" }, "TEE/deepseek-v3.2": { "cost": [ @@ -50768,7 +66312,11 @@ 0.25, 0.0 ], - "limit": 164000 + "knowledge": "2024-07", + "limit": 164000, + "max_output": 65536, + "open": true, + "released": "2025-12-01" }, "TEE/deepseek-v4.1-flash": { "cost": [ @@ -50777,7 +66325,11 @@ 0.13, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-09-10" }, "TEE/gemma-4-26b-a4b-uncensored": { "cost": [ @@ -50786,7 +66338,10 @@ 0.075, 0.0 ], - "limit": 65536 + "limit": 65536, + "max_output": 65536, + "open": true, + "released": "2026-05-23" }, "TEE/gemma-4-31b-it": { "cost": [ @@ -50795,7 +66350,11 @@ 0.075, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-02" }, "TEE/gemma4-31b": { "cost": [ @@ -50804,7 +66363,11 @@ 0.4, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 131072, + "open": true, + "released": "2026-04-02" }, "TEE/gemma4-31b:thinking": { "cost": [ @@ -50813,7 +66376,11 @@ 0.4, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 131072, + "open": true, + "released": "2026-04-02" }, "TEE/glm-5.1": { "cost": [ @@ -50822,7 +66389,10 @@ 0.18, 0.0 ], - "limit": 202752 + "limit": 202752, + "max_output": 65535, + "open": true, + "released": "2026-04-07" }, "TEE/glm-5.1-thinking": { "cost": [ @@ -50831,7 +66401,10 @@ 0.18, 0.0 ], - "limit": 202752 + "limit": 202752, + "max_output": 65535, + "open": true, + "released": "2026-04-07" }, "TEE/glm-5.2": { "cost": [ @@ -50840,7 +66413,10 @@ 0.7, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "TEE/glm-5.2:thinking": { "cost": [ @@ -50849,7 +66425,10 @@ 0.7, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "TEE/glm-5.3": { "cost": [ @@ -50858,7 +66437,10 @@ 0.26, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "TEE/glm-5.3-flash": { "cost": [ @@ -50867,7 +66449,10 @@ 0.03, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-08-26" }, "TEE/gpt-oss-120b": { "cost": [ @@ -50876,7 +66461,11 @@ 2.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 16384, + "open": true, + "released": "2025-08-05" }, "TEE/kimi-k2.6": { "cost": [ @@ -50885,7 +66474,11 @@ 0.375, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-04-20" }, "TEE/kimi-k2.7-code": { "cost": [ @@ -50894,7 +66487,11 @@ 0.19, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-06-12" }, "TEE/kimi-k3": { "cost": [ @@ -50903,7 +66500,10 @@ 1.5, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65535, + "open": true, + "released": "2026-07-16" }, "TEE/llama3-3-70b": { "cost": [ @@ -50912,7 +66512,11 @@ 1.75, 0.0 ], - "limit": 128000 + "knowledge": "2023-12", + "limit": 128000, + "max_output": 16384, + "open": true, + "released": "2024-12-06" }, "TEE/nemotron-3.5-lightning": { "cost": [ @@ -50921,7 +66525,11 @@ 0.04, 0.0 ], - "limit": 262144 + "knowledge": "2025-09", + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-08-11" }, "TEE/qwen2.5-vl-72b-instruct": { "cost": [ @@ -50930,7 +66538,11 @@ 0.35, 0.0 ], - "limit": 65536 + "knowledge": "2024-04", + "limit": 65536, + "max_output": 8192, + "open": true, + "released": "2025-01-26" }, "TEE/qwen3.5-27b": { "cost": [ @@ -50939,7 +66551,10 @@ 0.15, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-23" }, "TEE/qwen3.5-397b-a17b": { "cost": [ @@ -50948,7 +66563,10 @@ 0.275, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-15" }, "TEE/qwen3.6-27b": { "cost": [ @@ -50957,7 +66575,10 @@ 0.16, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-04-22" }, "TEE/qwen3.6-35b-a3b": { "cost": [ @@ -50966,7 +66587,10 @@ 0.1, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-17" }, "TEE/qwen3.8-27b": { "cost": [ @@ -50975,34 +66599,10 @@ 0.15, 0.0 ], - "limit": 262144 - }, - "THUDM/GLM-4-32B-0414": { - "cost": [ - 0.2, - 0.2, - 0.1, - 0.0 - ], - "limit": 128000 - }, - "THUDM/GLM-4-9B-0414": { - "cost": [ - 0.2, - 0.2, - 0.1, - 0.0 - ], - "limit": 32000 - }, - "THUDM/GLM-Z1-9B-0414": { - "cost": [ - 0.2, - 0.2, - 0.1, - 0.0 - ], - "limit": 32000 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-08-14" }, "TheDrummer/Anubis-70B-v1": { "cost": [ @@ -51011,7 +66611,10 @@ 0.155, 0.0 ], - "limit": 65536 + "limit": 65536, + "max_output": 16384, + "open": true, + "released": "2024-01-01" }, "TheDrummer/Anubis-70B-v1.1": { "cost": [ @@ -51020,7 +66623,10 @@ 0.155, 0.0 ], - "limit": 32000 + "limit": 32000, + "max_output": 16384, + "open": true, + "released": "2024-01-01" }, "TheDrummer/Artemis-v1.1": { "cost": [ @@ -51029,7 +66635,10 @@ 0.05, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-09-06" }, "TheDrummer/Cydonia-24B-v2": { "cost": [ @@ -51038,7 +66647,10 @@ 0.05015, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 32768, + "open": true, + "released": "2025-02-17" }, "TheDrummer/Cydonia-24B-v4": { "cost": [ @@ -51047,7 +66659,10 @@ 0.1003, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 32768, + "open": true, + "released": "2025-07-22" }, "TheDrummer/Cydonia-24B-v4.1": { "cost": [ @@ -51056,7 +66671,11 @@ 0.15, 0.0 ], - "limit": 131072 + "knowledge": "2024-04-30", + "limit": 131072, + "max_output": 117964, + "open": true, + "released": "2025-09-27" }, "TheDrummer/Cydonia-24B-v4.3": { "cost": [ @@ -51065,7 +66684,10 @@ 0.06, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-12-25" }, "TheDrummer/Magidonia-24B-v4.3": { "cost": [ @@ -51074,7 +66696,10 @@ 0.05015, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 32768, + "open": true, + "released": "2025-12-25" }, "TheDrummer/Rocinante-12B-v1.1": { "cost": [ @@ -51083,7 +66708,10 @@ 0.204, 0.0 ], - "limit": 16384 + "limit": 16384, + "max_output": 8192, + "open": true, + "released": "2024-01-01" }, "TheDrummer/UnslopNemo-12B-v4.1": { "cost": [ @@ -51092,25 +66720,10 @@ 0.2465, 0.0 ], - "limit": 8192 - }, - "TheDrummer/orion-26b-a4b-v1.1": { - "cost": [ - 0.1, - 0.45, - 0.05, - 0.0 - ], - "limit": 65536 - }, - "TheDrummer/skyfall-31b-v4.2": { - "cost": [ - 0.12, - 0.15, - 0.06, - 0.0 - ], - "limit": 16384 + "limit": 8192, + "max_output": 26214, + "open": true, + "released": "2024-01-01" }, "TheDrummer/skyfall-36b-v2": { "cost": [ @@ -51119,7 +66732,11 @@ 0.25, 0.0 ], - "limit": 32768 + "knowledge": "2024-06-30", + "limit": 32768, + "max_output": 29491, + "open": true, + "released": "2025-03-10" }, "VongolaChouko/Starcannon-Unleashed-12B-v1.0": { "cost": [ @@ -51128,7 +66745,10 @@ 0.2465, 0.0 ], - "limit": 16384 + "limit": 16384, + "max_output": 8192, + "open": true, + "released": "2024-01-01" }, "abacusai/Dracarys-72B-Instruct": { "cost": [ @@ -51137,7 +66757,10 @@ 0.2465, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 8192, + "open": true, + "released": "2025-08-02" }, "abliteration-ai/abliterated-model": { "cost": [ @@ -51146,7 +66769,9 @@ 0.1, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262134, + "released": "2026-08-27" }, "abliteration-ai/abliterated-model-large": { "cost": [ @@ -51155,7 +66780,9 @@ 0.3, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 999990, + "released": "2026-08-27" }, "abliteration-ai/abliterated-model-large-flash": { "cost": [ @@ -51164,7 +66791,9 @@ 0.1, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 262144, + "released": "2026-10-23" }, "abliteration-ai/abliterated-model-large-v2": { "cost": [ @@ -51173,7 +66802,9 @@ 0.3, 0.0 ], - "limit": 1000000 + "limit": 1048576, + "max_output": 999990, + "released": "2026-08-31" }, "agnes-3.0-flash": { "cost": [ @@ -51182,7 +66813,9 @@ 0.005, 0.0 ], - "limit": 524288 + "limit": 524288, + "max_output": 65536, + "released": "2026-09-09" }, "aion-labs/aion-2.0": { "cost": [ @@ -51191,7 +66824,9 @@ 0.2, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 32768, + "released": "2025-12-21" }, "aion-labs/aion-3.0": { "cost": [ @@ -51200,7 +66835,9 @@ 0.75, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 32768, + "released": "2026-05-05" }, "aion-labs/aion-3.0-mini": { "cost": [ @@ -51209,7 +66846,9 @@ 0.18, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 32768, + "released": "2026-05-14" }, "aion-labs/aion-3.5": { "cost": [ @@ -51218,7 +66857,9 @@ 0.75, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "released": "2026-09-23" }, "aion-labs/aion-3.5-mini": { "cost": [ @@ -51227,7 +66868,9 @@ 0.18, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "released": "2026-09-23" }, "aion-labs/aion-rp-llama-3.1-8b": { "cost": [ @@ -51236,16 +66879,48 @@ 0.4, 0.0 ], - "limit": 32768 + "knowledge": "2023-12-31", + "limit": 32768, + "max_output": 16384, + "open": true, + "released": "2025-02-04" }, - "aisingapore/Gemma-SEA-LION-v4-27B-IT": { + "aisingapore/gemma-sea-lion-v4-27b-it": { "cost": [ 0.24, 0.48, 0.0, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 128000, + "open": true, + "released": "2025-09-23" + }, + "aisingapore/qwen-sea-lion-v4-32b-it": { + "cost": [ + 0.3, + 0.6, + 0.0, + 0.0 + ], + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2026-10-15" + }, + "aleph-alpha/kolibri-1": { + "cost": [ + 0.168, + 0.588, + 0.0987, + 0.0 + ], + "knowledge": "2026-06-18", + "limit": 1048576, + "max_output": 943718, + "open": true, + "released": "2026-10-03" }, "amazon/nova-2-lite-v1": { "cost": [ @@ -51254,7 +66929,10 @@ 0.255, 0.0 ], - "limit": 1000000 + "knowledge": "2025-10", + "limit": 1000000, + "max_output": 65535, + "released": "2025-12-02" }, "amazon/nova-lite-v1": { "cost": [ @@ -51263,7 +66941,10 @@ 0.02975, 0.0 ], - "limit": 300000 + "knowledge": "2024-10-31", + "limit": 300000, + "max_output": 5120, + "released": "2024-12-05" }, "amazon/nova-pro-v1": { "cost": [ @@ -51272,7 +66953,10 @@ 0.3995, 0.0 ], - "limit": 300000 + "knowledge": "2024-10-31", + "limit": 300000, + "max_output": 32000, + "released": "2024-12-05" }, "anthracite-org/magnum-v2-72b": { "cost": [ @@ -51281,7 +66965,10 @@ 1.003, 0.0 ], - "limit": 16384 + "limit": 16384, + "max_output": 8192, + "open": true, + "released": "2024-01-01" }, "anthracite-org/magnum-v4-72b": { "cost": [ @@ -51290,7 +66977,11 @@ 1.003, 0.0 ], - "limit": 16384 + "knowledge": "2024-06-30", + "limit": 16384, + "max_output": 8192, + "open": true, + "released": "2024-10-22" }, "anthropic/claude-fable-5": { "cost": [ @@ -51299,7 +66990,10 @@ 1.0, 12.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-09" }, "anthropic/claude-fable-5.1": { "cost": [ @@ -51308,7 +67002,10 @@ 0.25, 12.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-01" }, "anthropic/claude-fable-latest": { "cost": [ @@ -51317,7 +67014,9 @@ 0.25, 12.5 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-09" }, "anthropic/claude-haiku-4.5": { "cost": [ @@ -51326,7 +67025,10 @@ 0.1, 0.0 ], - "limit": 200000 + "knowledge": "2025-02-28", + "limit": 200000, + "max_output": 64000, + "released": "2025-10-15" }, "anthropic/claude-haiku-4.5:thinking": { "cost": [ @@ -51335,7 +67037,10 @@ 0.1, 0.0 ], - "limit": 200000 + "knowledge": "2025-02-28", + "limit": 200000, + "max_output": 64000, + "released": "2025-10-15" }, "anthropic/claude-haiku-5.5": { "cost": [ @@ -51344,7 +67049,10 @@ 0.01, 0.125 ], + "knowledge": "2026-06", "limit": 1000000, + "max_output": 128000, + "released": "2026-10-07", "tiers": [ { "cost": [ @@ -51368,6 +67076,8 @@ 0.125 ], "limit": 1000000, + "max_output": 128000, + "released": "2026-03-29", "tiers": [ { "cost": [ @@ -51390,7 +67100,10 @@ 1.5, 0.0 ], - "limit": 200000 + "knowledge": "2025-03-31", + "limit": 200000, + "max_output": 32000, + "released": "2025-08-05" }, "anthropic/claude-opus-4.1:thinking": { "cost": [ @@ -51399,7 +67112,10 @@ 1.5, 0.0 ], - "limit": 200000 + "knowledge": "2025-03-31", + "limit": 200000, + "max_output": 32000, + "released": "2025-08-05" }, "anthropic/claude-opus-4.1:thinking:1024": { "cost": [ @@ -51408,7 +67124,10 @@ 1.5, 0.0 ], - "limit": 200000 + "knowledge": "2025-03-31", + "limit": 200000, + "max_output": 32000, + "released": "2025-08-05" }, "anthropic/claude-opus-4.1:thinking:32768": { "cost": [ @@ -51417,7 +67136,10 @@ 1.5, 0.0 ], - "limit": 200000 + "knowledge": "2025-03-31", + "limit": 200000, + "max_output": 32000, + "released": "2025-08-05" }, "anthropic/claude-opus-4.1:thinking:8192": { "cost": [ @@ -51426,7 +67148,10 @@ 1.5, 0.0 ], - "limit": 200000 + "knowledge": "2025-03-31", + "limit": 200000, + "max_output": 32000, + "released": "2025-08-05" }, "anthropic/claude-opus-4.5": { "cost": [ @@ -51435,7 +67160,10 @@ 0.5, 0.0 ], - "limit": 200000 + "knowledge": "2025-05", + "limit": 200000, + "max_output": 64000, + "released": "2025-11-24" }, "anthropic/claude-opus-4.5:thinking": { "cost": [ @@ -51444,7 +67172,10 @@ 0.5, 0.0 ], - "limit": 200000 + "knowledge": "2025-05", + "limit": 200000, + "max_output": 64000, + "released": "2025-11-24" }, "anthropic/claude-opus-4.6": { "cost": [ @@ -51453,7 +67184,10 @@ 0.5, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-05" }, "anthropic/claude-opus-4.6:thinking": { "cost": [ @@ -51462,7 +67196,10 @@ 0.5, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-05" }, "anthropic/claude-opus-4.6:thinking:low": { "cost": [ @@ -51471,7 +67208,10 @@ 0.5, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-05" }, "anthropic/claude-opus-4.6:thinking:max": { "cost": [ @@ -51480,7 +67220,10 @@ 0.5, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-05" }, "anthropic/claude-opus-4.6:thinking:medium": { "cost": [ @@ -51489,7 +67232,10 @@ 0.5, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-05" }, "anthropic/claude-opus-4.7": { "cost": [ @@ -51498,7 +67244,10 @@ 0.5, 0.0 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-16" }, "anthropic/claude-opus-4.7:thinking": { "cost": [ @@ -51507,7 +67256,10 @@ 0.5, 0.0 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-16" }, "anthropic/claude-opus-4.8": { "cost": [ @@ -51516,7 +67268,10 @@ 0.5, 0.0 ], - "limit": 1000000 + "knowledge": "2026-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-28" }, "anthropic/claude-opus-4.8:thinking": { "cost": [ @@ -51525,7 +67280,10 @@ 0.5, 0.0 ], - "limit": 1000000 + "knowledge": "2026-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-28" }, "anthropic/claude-opus-5": { "cost": [ @@ -51534,7 +67292,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-05", + "limit": 1000000, + "max_output": 128000, + "released": "2026-07-24" }, "anthropic/claude-opus-5.5": { "cost": [ @@ -51543,7 +67304,10 @@ 0.2, 5.0 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-22" }, "anthropic/claude-opus-latest": { "cost": [ @@ -51552,7 +67316,9 @@ 0.2, 5.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 128000, + "released": "2026-03-29" }, "anthropic/claude-sonnet-4.5": { "cost": [ @@ -51561,7 +67327,10 @@ 0.3, 0.0 ], - "limit": 200000 + "knowledge": "2025-07-31", + "limit": 200000, + "max_output": 64000, + "released": "2025-09-29" }, "anthropic/claude-sonnet-4.5:thinking": { "cost": [ @@ -51570,7 +67339,10 @@ 0.3, 0.0 ], - "limit": 200000 + "knowledge": "2025-07-31", + "limit": 200000, + "max_output": 64000, + "released": "2025-09-29" }, "anthropic/claude-sonnet-4.6": { "cost": [ @@ -51579,7 +67351,10 @@ 0.3, 0.0 ], - "limit": 1000000 + "knowledge": "2025-08-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-17" }, "anthropic/claude-sonnet-4.6:thinking": { "cost": [ @@ -51588,7 +67363,10 @@ 0.3, 0.0 ], - "limit": 1000000 + "knowledge": "2025-08-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-17" }, "anthropic/claude-sonnet-5": { "cost": [ @@ -51597,7 +67375,10 @@ 0.2, 2.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-30" }, "anthropic/claude-sonnet-5.5": { "cost": [ @@ -51606,7 +67387,10 @@ 0.1, 2.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-28" }, "anthropic/claude-sonnet-5.5:thinking": { "cost": [ @@ -51615,7 +67399,10 @@ 0.1, 2.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-28" }, "anthropic/claude-sonnet-5:thinking": { "cost": [ @@ -51624,7 +67411,10 @@ 0.2, 2.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-30" }, "anthropic/claude-sonnet-latest": { "cost": [ @@ -51633,7 +67423,9 @@ 0.1, 2.5 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 128000, + "released": "2026-03-01" }, "arcee-ai/trinity-large-thinking": { "cost": [ @@ -51642,7 +67434,10 @@ 0.125, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 80000, + "open": true, + "released": "2026-04-01" }, "asi1-mini": { "cost": [ @@ -51651,16 +67446,9 @@ 0.5, 0.0 ], - "limit": 128000 - }, - "ateron/gemma-4-dark-thoughts-v2-31b": { - "cost": [ - 0.1, - 0.45, - 0.05, - 0.0 - ], - "limit": 65536 + "limit": 128000, + "max_output": 16384, + "released": "2025-03-25" }, "auto-model": { "cost": [ @@ -51669,7 +67457,9 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 1000000, + "released": "2025-04-16" }, "auto-model-basic": { "cost": [ @@ -51678,7 +67468,9 @@ 4.998, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 1000000, + "released": "2025-04-16" }, "auto-model-premium": { "cost": [ @@ -51687,7 +67479,9 @@ 4.998, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 1000000, + "released": "2025-04-16" }, "auto-model-standard": { "cost": [ @@ -51696,7 +67490,9 @@ 4.998, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 1000000, + "released": "2025-04-16" }, "baseten/Kimi-K2-Instruct-FP4": { "cost": [ @@ -51706,6 +67502,9 @@ 0.0 ], "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2024-01-01", "status": "deprecated" }, "bytedance-seed/seed-2-1-turbo": { @@ -51715,7 +67514,9 @@ 0.25, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 235929, + "released": "2026-06-23" }, "bytedance-seed/seed-2.0-code": { "cost": [ @@ -51724,7 +67525,9 @@ 0.25, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 131072, + "released": "2026-02-14" }, "bytedance-seed/seed-2.0-lite": { "cost": [ @@ -51733,7 +67536,9 @@ 0.125, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 131072, + "released": "2026-02-14" }, "bytedance/doubao-seed-2.1-pro": { "cost": [ @@ -51742,7 +67547,9 @@ 0.5, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 128000, + "released": "2026-06-23" }, "bytedance/doubao-seed-2.1-turbo": { "cost": [ @@ -51751,7 +67558,9 @@ 0.25, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 128000, + "released": "2026-06-23" }, "bytedance/doubao-seed-character": { "cost": [ @@ -51760,7 +67569,9 @@ 0.03, 0.003 ], - "limit": 128000 + "limit": 128000, + "max_output": 32768, + "released": "2026-06-23" }, "celeris-1": { "cost": [ @@ -51769,7 +67580,9 @@ 1.0, 0.0 ], - "limit": 8192 + "limit": 8192, + "max_output": 8192, + "released": "2026-07-25" }, "claw-high": { "cost": [ @@ -51778,7 +67591,9 @@ 0.2, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-05-11" }, "claw-low": { "cost": [ @@ -51787,7 +67602,9 @@ 0.2, 0.08333 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-05-11" }, "claw-medium": { "cost": [ @@ -51796,7 +67613,9 @@ 0.2, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-05-11" }, "cohere/command-r-plus-08-2024": { "cost": [ @@ -51805,7 +67624,11 @@ 1.428, 0.0 ], - "limit": 128000 + "knowledge": "2024-06-01", + "limit": 128000, + "max_output": 4096, + "open": true, + "released": "2024-08-30" }, "command-a-reasoning-08-2025": { "cost": [ @@ -51814,7 +67637,11 @@ 1.25, 0.0 ], - "limit": 256000 + "knowledge": "2024-06-01", + "limit": 256000, + "max_output": 8192, + "open": true, + "released": "2025-08-21" }, "deepcogito/cogito-v1-preview-qwen-32B": { "cost": [ @@ -51823,7 +67650,10 @@ 0.9, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 32768, + "open": true, + "released": "2025-05-10" }, "deepseek-ai/DeepSeek-R1-0528": { "cost": [ @@ -51832,7 +67662,10 @@ 0.35, 0.0 ], - "limit": 163840 + "limit": 163840, + "max_output": 32768, + "open": true, + "released": "2025-05-28" }, "deepseek-ai/DeepSeek-V3.1": { "cost": [ @@ -51841,7 +67674,10 @@ 0.1, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 65536, + "open": true, + "released": "2025-08-21" }, "deepseek-ai/DeepSeek-V3.1-Terminus": { "cost": [ @@ -51850,7 +67686,10 @@ 0.125, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 65536, + "open": true, + "released": "2025-08-02" }, "deepseek-ai/DeepSeek-V3.1-Terminus:thinking": { "cost": [ @@ -51859,7 +67698,10 @@ 0.125, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 65536, + "open": true, + "released": "2024-01-01" }, "deepseek-ai/DeepSeek-V3.1:thinking": { "cost": [ @@ -51868,7 +67710,10 @@ 0.1, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 65536, + "open": true, + "released": "2025-08-21" }, "deepseek-ai/deepseek-v3.2-exp": { "cost": [ @@ -51877,7 +67722,10 @@ 0.14, 0.0 ], - "limit": 163840 + "limit": 163840, + "max_output": 65536, + "open": true, + "released": "2024-01-01" }, "deepseek-ai/deepseek-v3.2-exp-thinking": { "cost": [ @@ -51886,7 +67734,10 @@ 0.14, 0.0 ], - "limit": 163840 + "limit": 163840, + "max_output": 65536, + "open": true, + "released": "2024-01-01" }, "deepseek-chat": { "cost": [ @@ -51895,7 +67746,11 @@ 0.05, 0.0 ], - "limit": 128000 + "knowledge": "2025-09", + "limit": 128000, + "max_output": 8192, + "open": true, + "released": "2025-12-01" }, "deepseek-chat-cheaper": { "cost": [ @@ -51904,7 +67759,10 @@ 0.05, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 8192, + "open": true, + "released": "2025-04-15" }, "deepseek-v3-0324": { "cost": [ @@ -51913,16 +67771,22 @@ 0.135, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 8192, + "open": true, + "released": "2025-03-24" }, "deepseek/deepseek-latest": { "cost": [ - 0.22968, - 0.68904, - 0.007308, + 0.22704, + 0.68112, + 0.007224, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-05-03" }, "deepseek/deepseek-v3.2": { "cost": [ @@ -51931,7 +67795,11 @@ 0.0216, 0.0 ], - "limit": 163000 + "knowledge": "2024-07", + "limit": 163000, + "max_output": 65536, + "open": true, + "released": "2025-12-01" }, "deepseek/deepseek-v3.2:thinking": { "cost": [ @@ -51940,7 +67808,11 @@ 0.0216, 0.0 ], - "limit": 163000 + "knowledge": "2024-07", + "limit": 163000, + "max_output": 65536, + "open": true, + "released": "2025-12-01" }, "deepseek/deepseek-v4-flash": { "cost": [ @@ -51949,7 +67821,11 @@ 0.0028, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "deepseek/deepseek-v4-flash-0423": { "cost": [ @@ -51958,7 +67834,11 @@ 0.028, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-04-23" }, "deepseek/deepseek-v4-flash-0423:thinking": { "cost": [ @@ -51967,34 +67847,49 @@ 0.028, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-04-23" }, "deepseek/deepseek-v4-flash-0731": { "cost": [ - 0.05, - 0.16, - 0.013, + 0.04444, + 0.13332, + 0.001414, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-31" }, "deepseek/deepseek-v4-flash-0731:thinking": { "cost": [ - 0.05, - 0.16, - 0.013, + 0.04444, + 0.13332, + 0.001414, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-31" }, "deepseek/deepseek-v4-flash-latest": { "cost": [ 0.1, 0.6, - 0.003, + 0.005, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 393216, + "open": true, + "released": "2026-08-02" }, "deepseek/deepseek-v4-flash-vision-exp": { "cost": [ @@ -52003,7 +67898,10 @@ 0.00686, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-08-21" }, "deepseek/deepseek-v4-flash:thinking": { "cost": [ @@ -52012,7 +67910,11 @@ 0.0028, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "deepseek/deepseek-v4-pro": { "cost": [ @@ -52021,25 +67923,35 @@ 0.07, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "deepseek/deepseek-v4-pro-0813": { "cost": [ - 0.22968, - 0.68904, - 0.007308, + 0.22704, + 0.68112, + 0.007224, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-08-13" }, "deepseek/deepseek-v4-pro-0813:thinking": { "cost": [ - 0.22968, - 0.68904, - 0.007308, + 0.22704, + 0.68112, + 0.007224, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-08-13" }, "deepseek/deepseek-v4-pro:thinking": { "cost": [ @@ -52048,70 +67960,135 @@ 0.07, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "deepseek/deepseek-v4.1-flash": { "cost": [ - 0.0597, - 0.2388, - 0.001194, + 0.09, + 0.25, + 0.006, + 0.0 + ], + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-09-10" + }, + "deepseek/deepseek-v4.1-flash-0910-uncensored": { + "cost": [ + 0.33, + 1.32, + 0.00825, + 0.0 + ], + "limit": 524288, + "max_output": 32768, + "open": true, + "released": "2026-10-27" + }, + "deepseek/deepseek-v4.1-flash-0910-uncensored:thinking": { + "cost": [ + 0.33, + 1.32, + 0.00825, 0.0 ], - "limit": 1000000 + "limit": 524288, + "max_output": 32768, + "open": true, + "released": "2026-10-27" }, "deepseek/deepseek-v4.1-flash-1017": { "cost": [ 0.1, 0.6, - 0.003, + 0.005, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 393216, + "open": true, + "released": "2026-10-17" }, - "deepseek/deepseek-v4.1-flash-1017:thinking": { + "deepseek/deepseek-v4.1-flash-1017-uncensored": { "cost": [ - 0.1, - 0.6, - 0.003, + 0.33, + 1.32, + 0.00825, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 393216, + "open": true, + "released": "2026-10-27" }, - "deepseek/deepseek-v4.1-flash:thinking": { + "deepseek/deepseek-v4.1-flash-1017-uncensored:thinking": { + "cost": [ + 0.33, + 1.32, + 0.00825, + 0.0 + ], + "limit": 1048576, + "max_output": 393216, + "open": true, + "released": "2026-10-27" + }, + "deepseek/deepseek-v4.1-flash-1017:thinking": { "cost": [ - 0.0597, - 0.2388, - 0.001194, + 0.1, + 0.6, + 0.005, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 393216, + "open": true, + "released": "2026-10-17" }, - "doubao-1.5-pro-256k": { + "deepseek/deepseek-v4.1-flash-uncensored": { "cost": [ - 0.799, - 1.445, - 0.3995, + 0.33, + 1.32, + 0.00825, 0.0 ], - "limit": 256000 + "limit": 1048576, + "max_output": 393216, + "open": true, + "released": "2026-10-01" }, - "doubao-1.5-pro-32k": { + "deepseek/deepseek-v4.1-flash-uncensored:thinking": { "cost": [ - 0.1343, - 0.3349, - 0.06715, + 0.33, + 1.32, + 0.00825, 0.0 ], - "limit": 32000 + "limit": 1048576, + "max_output": 393216, + "open": true, + "released": "2026-10-01" }, - "doubao-1.5-vision-pro-32k": { + "deepseek/deepseek-v4.1-flash:thinking": { "cost": [ - 0.459, - 1.377, - 0.2295, + 0.09, + 0.25, + 0.006, 0.0 ], - "limit": 32000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-09-10" }, "doubao-seed-2-0-code-preview-260215": { "cost": [ @@ -52120,7 +68097,9 @@ 0.391, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 128000, + "released": "2026-02-14" }, "doubao-seed-2-0-lite-260215": { "cost": [ @@ -52129,7 +68108,9 @@ 0.0731, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 32000, + "released": "2026-02-14" }, "doubao-seed-2-0-mini-260215": { "cost": [ @@ -52138,7 +68119,9 @@ 0.02465, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 32000, + "released": "2026-02-14" }, "doubao-seed-2-0-pro-260215": { "cost": [ @@ -52147,7 +68130,9 @@ 0.391, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 128000, + "released": "2026-02-14" }, "elorian/glimpse": { "cost": [ @@ -52156,7 +68141,9 @@ 0.063, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 256000, + "released": "2026-10-17" }, "ernie-5.0-thinking-preview": { "cost": [ @@ -52165,7 +68152,9 @@ 0.5, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 16384, + "released": "2025-11-18" }, "ernie-5.1": { "cost": [ @@ -52174,7 +68163,9 @@ 0.75, 0.0 ], - "limit": 119000 + "limit": 119000, + "max_output": 64000, + "released": "2026-05-10" }, "ernie-5.1:thinking": { "cost": [ @@ -52183,7 +68174,9 @@ 0.75, 0.0 ], - "limit": 119000 + "limit": 119000, + "max_output": 64000, + "released": "2026-05-10" }, "failspy/Meta-Llama-3-70B-Instruct-abliterated-v3.5": { "cost": [ @@ -52192,7 +68185,10 @@ 0.35, 0.0 ], - "limit": 8192 + "limit": 8192, + "max_output": 8192, + "open": true, + "released": "2025-07-26" }, "fastgpt": { "cost": [ @@ -52201,7 +68197,9 @@ 0.0, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 32768, + "released": "2025-12-23" }, "featherless-ai/Qwerky-72B": { "cost": [ @@ -52210,7 +68208,10 @@ 0.25, 0.0 ], - "limit": 32000 + "limit": 32000, + "max_output": 8192, + "open": true, + "released": "2024-01-01" }, "fireworks/ember-1": { "cost": [ @@ -52219,7 +68220,9 @@ 0.3, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-09-22" }, "gemini-2.0-pro-exp-02-05": { "cost": [ @@ -52228,7 +68231,9 @@ 0.49725, 0.0 ], - "limit": 2097152 + "limit": 2097152, + "max_output": 8192, + "released": "2025-02-05" }, "gemini-2.0-pro-reasoner": { "cost": [ @@ -52237,7 +68242,9 @@ 0.323, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 65536, + "released": "2024-01-01" }, "gemini-2.5-flash": { "cost": [ @@ -52246,7 +68253,10 @@ 0.03, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2025-06-17" }, "gemini-2.5-flash-lite": { "cost": [ @@ -52255,7 +68265,10 @@ 0.01, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2025-06-17" }, "gemini-2.5-flash-lite-preview-06-17": { "cost": [ @@ -52264,7 +68277,10 @@ 0.015, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2025-06-17" }, "gemini-2.5-flash-lite-preview-09-2025": { "cost": [ @@ -52273,7 +68289,10 @@ 0.01, 0.0 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2025-09-25", "status": "deprecated" }, "gemini-2.5-flash-lite-preview-09-2025-thinking": { @@ -52283,7 +68302,10 @@ 0.01, 0.0 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2025-09-25", "status": "deprecated" }, "gemini-2.5-flash-nothinking": { @@ -52293,7 +68315,9 @@ 0.03, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65536, + "released": "2025-06-05" }, "gemini-2.5-flash-preview-04-17": { "cost": [ @@ -52303,6 +68327,8 @@ 0.0 ], "limit": 1048576, + "max_output": 65536, + "released": "2025-04-17", "status": "deprecated" }, "gemini-2.5-flash-preview-04-17:thinking": { @@ -52313,6 +68339,8 @@ 0.0 ], "limit": 1048576, + "max_output": 65536, + "released": "2025-04-17", "status": "deprecated" }, "gemini-2.5-flash-preview-05-20": { @@ -52322,7 +68350,10 @@ 0.015, 0.0 ], + "knowledge": "2025-01", "limit": 1048000, + "max_output": 65536, + "released": "2025-05-20", "status": "deprecated" }, "gemini-2.5-flash-preview-05-20:thinking": { @@ -52332,7 +68363,10 @@ 0.015, 0.0 ], + "knowledge": "2025-01", "limit": 1048000, + "max_output": 65536, + "released": "2025-05-20", "status": "deprecated" }, "gemini-2.5-flash-preview-09-2025": { @@ -52342,7 +68376,9 @@ 0.03, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65536, + "released": "2025-09-25" }, "gemini-2.5-flash-preview-09-2025-thinking": { "cost": [ @@ -52351,7 +68387,9 @@ 0.03, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65536, + "released": "2025-09-25" }, "gemini-2.5-pro": { "cost": [ @@ -52360,7 +68398,10 @@ 0.125, 0.375 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2025-06-17" }, "gemini-2.5-pro-exp-03-25": { "cost": [ @@ -52369,7 +68410,9 @@ 0.25, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65536, + "released": "2025-03-25" }, "gemini-2.5-pro-preview-03-25": { "cost": [ @@ -52378,7 +68421,9 @@ 0.25, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65536, + "released": "2025-03-25" }, "gemini-2.5-pro-preview-05-06": { "cost": [ @@ -52387,7 +68432,9 @@ 0.25, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65536, + "released": "2025-05-06" }, "gemini-2.5-pro-preview-06-05": { "cost": [ @@ -52396,7 +68443,10 @@ 0.25, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01-31", + "limit": 1048576, + "max_output": 65536, + "released": "2025-06-05" }, "gemini-3-pro-image-preview": { "cost": [ @@ -52405,7 +68455,10 @@ 0.2, 0.0 ], - "limit": 65536 + "knowledge": "2025-01", + "limit": 65536, + "max_output": 32768, + "released": "2025-11-20" }, "gemini-exp-1206": { "cost": [ @@ -52414,7 +68467,9 @@ 0.629, 0.0 ], - "limit": 2097152 + "limit": 2097152, + "max_output": 8192, + "released": "2024-12-06" }, "gemma-4-12b-it": { "cost": [ @@ -52423,7 +68478,10 @@ 0.025, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2026-06-09" }, "gemma-4-12b-it-semancer": { "cost": [ @@ -52432,7 +68490,22 @@ 0.025, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2026-09-09" + }, + "gemma-4-12b-it-starry-ocean": { + "cost": [ + 0.05, + 0.25, + 0.025, + 0.0 + ], + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2026-10-15" }, "gemma-4-12b-it-station-keeper": { "cost": [ @@ -52441,7 +68514,10 @@ 0.025, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2026-09-09" }, "gemma-4-26b-a4b-it-chimerax": { "cost": [ @@ -52450,7 +68526,10 @@ 0.06, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-07-29" }, "gemma-4-26b-a4b-it-chimeraxheretic": { "cost": [ @@ -52459,7 +68538,10 @@ 0.06, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-10-08" }, "gemma-4-26b-a4b-it-darksoul": { "cost": [ @@ -52468,7 +68550,10 @@ 0.06, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-07-29" }, "gemma-4-26b-a4b-it-luminous": { "cost": [ @@ -52477,7 +68562,10 @@ 0.06, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-07-29" }, "gemma-4-26b-a4b-it-moonlight": { "cost": [ @@ -52486,7 +68574,10 @@ 0.06, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-07-29" }, "gemma-4-26b-a4b-it-musica": { "cost": [ @@ -52495,7 +68586,10 @@ 0.06, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-07-29" }, "gemma-4-26b-a4b-it-opusdistill": { "cost": [ @@ -52504,7 +68598,10 @@ 0.06, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-07-29" }, "gemma-4-26b-a4b-it-shadowsiren": { "cost": [ @@ -52513,7 +68610,10 @@ 0.06, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-07-29" }, "gemma-4-31b-it-darkidol": { "cost": [ @@ -52522,7 +68622,10 @@ 0.05, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-07-29" }, "gemma-4-31b-it-fabled": { "cost": [ @@ -52531,7 +68634,10 @@ 0.05, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-07-29" }, "gemma-4-31b-it-garnet": { "cost": [ @@ -52540,7 +68646,10 @@ 0.05, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-07-29" }, "gemma-4-31b-it-gembrain": { "cost": [ @@ -52549,7 +68658,10 @@ 0.05, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-07-29" }, "gemma-4-31b-it-gemsicle": { "cost": [ @@ -52558,7 +68670,10 @@ 0.05, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-07-29" }, "gemma-4-31b-it-isometry": { "cost": [ @@ -52567,7 +68682,10 @@ 0.05, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-07-29" }, "gemma-4-31b-it-novelist": { "cost": [ @@ -52576,7 +68694,10 @@ 0.05, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-07-29" }, "gemma-4-31b-it-scarlet": { "cost": [ @@ -52585,16 +68706,10 @@ 0.05, 0.0 ], - "limit": 262144 - }, - "glm-4-air-0111": { - "cost": [ - 0.1394, - 0.1394, - 0.0697, - 0.0 - ], - "limit": 128000 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-10-08" }, "glm-4-long": { "cost": [ @@ -52603,43 +68718,9 @@ 0.1003, 0.0 ], - "limit": 1000000 - }, - "glm-4-plus-0111": { - "cost": [ - 9.996, - 9.996, - 4.998, - 0.0 - ], - "limit": 128000 - }, - "glm-4.1v-thinking-flash": { - "cost": [ - 0.3, - 0.3, - 0.15, - 0.0 - ], - "limit": 64000 - }, - "glm-4.1v-thinking-flashx": { - "cost": [ - 0.3, - 0.3, - 0.15, - 0.0 - ], - "limit": 64000 - }, - "glm-z1-airx": { - "cost": [ - 0.7, - 0.7, - 0.35, - 0.0 - ], - "limit": 32000 + "limit": 1000000, + "max_output": 4095, + "released": "2024-01-01" }, "google/diffusiongemma": { "cost": [ @@ -52648,7 +68729,11 @@ 0.025, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-06-09" }, "google/gemini-3-flash-preview": { "cost": [ @@ -52657,7 +68742,10 @@ 0.05, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2025-12-17" }, "google/gemini-3-flash-preview-thinking": { "cost": [ @@ -52666,7 +68754,10 @@ 0.05, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2025-12-17" }, "google/gemini-3.1-flash-lite": { "cost": [ @@ -52675,7 +68766,10 @@ 0.025, 0.08333 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-05-07" }, "google/gemini-3.1-pro-preview": { "cost": [ @@ -52684,7 +68778,10 @@ 0.2, 0.375 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-02-19" }, "google/gemini-3.1-pro-preview-customtools": { "cost": [ @@ -52693,7 +68790,10 @@ 0.2, 0.375 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-02-19" }, "google/gemini-3.1-pro-preview-high": { "cost": [ @@ -52702,7 +68802,10 @@ 0.2, 0.375 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-02-19" }, "google/gemini-3.1-pro-preview-low": { "cost": [ @@ -52711,7 +68814,10 @@ 0.2, 0.375 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-02-19" }, "google/gemini-3.5-flash": { "cost": [ @@ -52720,7 +68826,10 @@ 0.15, 0.083333 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-05-19" }, "google/gemini-3.5-flash-lite": { "cost": [ @@ -52729,7 +68838,10 @@ 0.03, 0.08333 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-07-21" }, "google/gemini-3.5-flash-thinking": { "cost": [ @@ -52738,7 +68850,10 @@ 0.15, 0.083333 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-05-19" }, "google/gemini-3.6-flash": { "cost": [ @@ -52747,7 +68862,10 @@ 0.075, 0.041667 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-07-21" }, "google/gemini-3.7-flash": { "cost": [ @@ -52756,7 +68874,10 @@ 0.075, 0.041667 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-08-13" }, "google/gemini-3.8-flash": { "cost": [ @@ -52765,7 +68886,9 @@ 0.075, 0.041667 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65536, + "released": "2026-09-02" }, "google/gemini-4-argon": { "cost": [ @@ -52774,7 +68897,10 @@ 0.1, 0.1875 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-10-13" }, "google/gemini-flash-latest": { "cost": [ @@ -52783,7 +68909,10 @@ 0.075, 0.041667 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-08-13" }, "google/gemini-flash-lite-latest": { "cost": [ @@ -52792,7 +68921,10 @@ 0.03, 0.08333 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-07-21" }, "google/gemini-pro-latest": { "cost": [ @@ -52801,16 +68933,21 @@ 0.2, 0.375 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65536, + "released": "2026-03-29" }, "google/gemma-4-26b-a4b-it": { "cost": [ - 0.09, - 0.3, - 0.05, + 0.07, + 0.24, + 0.046, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 131072, + "open": true, + "released": "2026-04-02" }, "google/gemma-4-26b-a4b-it-cybersecurity": { "cost": [ @@ -52819,16 +68956,22 @@ 0.0528, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-09-19" }, "google/gemma-4-26b-a4b-it:thinking": { "cost": [ - 0.09, - 0.3, - 0.05, + 0.07, + 0.24, + 0.046, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 131072, + "open": true, + "released": "2026-04-02" }, "google/gemma-4-31b-it": { "cost": [ @@ -52837,7 +68980,11 @@ 0.05, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 131072, + "open": true, + "released": "2026-04-02" }, "google/gemma-4-31b-it:thinking": { "cost": [ @@ -52846,7 +68993,11 @@ 0.1, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 131072, + "open": true, + "released": "2026-04-02" }, "google/gemma4-31b-splituntied": { "cost": [ @@ -52855,7 +69006,10 @@ 0.05, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-09-17" }, "heabsy/cyberheabsy": { "cost": [ @@ -52864,7 +69018,9 @@ 0.275, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65536, + "released": "2026-09-27" }, "heabsy/qwen3.8-27b-uncensored-fast": { "cost": [ @@ -52873,7 +69029,9 @@ 0.22, 0.0 ], - "limit": 1048576 + "limit": 524288, + "max_output": 235929, + "released": "2026-10-16" }, "hermes-high": { "cost": [ @@ -52882,7 +69040,9 @@ 0.2, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-05-11" }, "hermes-low": { "cost": [ @@ -52891,7 +69051,9 @@ 0.2, 0.08333 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-05-11" }, "hermes-medium": { "cost": [ @@ -52900,7 +69062,9 @@ 0.2, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-05-11" }, "holo3-35b-a3b": { "cost": [ @@ -52909,7 +69073,10 @@ 0.125, 0.0 ], - "limit": 65536 + "limit": 65536, + "max_output": 8192, + "open": true, + "released": "2024-01-01" }, "holo3-35b-a3b:thinking": { "cost": [ @@ -52918,7 +69085,10 @@ 0.125, 0.0 ], - "limit": 65536 + "limit": 65536, + "max_output": 8192, + "open": true, + "released": "2024-01-01" }, "huihui-ai/DeepSeek-R1-Distill-Llama-70B-abliterated": { "cost": [ @@ -52927,7 +69097,10 @@ 0.35, 0.0 ], - "limit": 16384 + "limit": 16384, + "max_output": 8192, + "open": true, + "released": "2024-01-01" }, "huihui-ai/DeepSeek-R1-Distill-Qwen-32B-abliterated": { "cost": [ @@ -52936,7 +69109,10 @@ 0.7, 0.0 ], - "limit": 16384 + "limit": 16384, + "max_output": 8192, + "open": true, + "released": "2024-01-01" }, "huihui-ai/Llama-3.3-70B-Instruct-abliterated": { "cost": [ @@ -52945,7 +69121,10 @@ 0.35, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 16384, + "open": true, + "released": "2025-08-08" }, "huihui-ai/Qwen2.5-32B-Instruct-abliterated": { "cost": [ @@ -52954,16 +69133,22 @@ 0.35, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 8192, + "open": true, + "released": "2025-01-06" }, "ibm-granite/granite-4.2-8b": { "cost": [ - 0.1, + 0.06, 0.15, - 0.05, + 0.015, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 117964, + "open": true, + "released": "2026-08-25" }, "inception/mercury-2.5-preview": { "cost": [ @@ -52972,7 +69157,9 @@ 0.004, 0.0 ], - "limit": 260000 + "limit": 260000, + "max_output": 65536, + "released": "2026-09-01" }, "inception/mercury-3": { "cost": [ @@ -52981,7 +69168,9 @@ 0.01, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-10-16" }, "inclusionai/ling-3.0-flash": { "cost": [ @@ -52990,7 +69179,10 @@ 0.015, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-07-23" }, "inclusionai/ling-3.0-flash-vl": { "cost": [ @@ -52999,7 +69191,10 @@ 0.012, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-09-10" }, "inclusionai/ling-3.0-flash:thinking": { "cost": [ @@ -53008,7 +69203,10 @@ 0.015, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-07-23" }, "inclusionai/ling-3.1-flash": { "cost": [ @@ -53017,7 +69215,10 @@ 0.015, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-09-29" }, "inference-net/schematron-v2-small": { "cost": [ @@ -53026,7 +69227,9 @@ 0.025, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 4096, + "released": "2026-04-16" }, "inference-net/schematron-v2-turbo": { "cost": [ @@ -53035,7 +69238,9 @@ 0.015, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 8192, + "released": "2026-04-16" }, "inflatebot/MN-12B-Mag-Mell-R1": { "cost": [ @@ -53044,7 +69249,10 @@ 0.2465, 0.0 ], - "limit": 16384 + "limit": 16384, + "max_output": 8192, + "open": true, + "released": "2024-01-01" }, "kimi-k2-instruct-fast": { "cost": [ @@ -53054,6 +69262,9 @@ 0.0 ], "limit": 131072, + "max_output": 16384, + "open": true, + "released": "2025-07-11", "status": "deprecated" }, "lightonai/LightOnOCR-2-1B": { @@ -53063,7 +69274,10 @@ 0.0, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 8192, + "open": true, + "released": "2026-09-10" }, "liquid/lfm-2.5-2.6b": { "cost": [ @@ -53072,7 +69286,10 @@ 0.05, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 32768, + "open": true, + "released": "2026-08-12" }, "liquid/lfm-2.5-24b-a2b": { "cost": [ @@ -53081,7 +69298,9 @@ 0.025, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 8192, + "released": "2026-10-14" }, "longcat-2.0": { "cost": [ @@ -53090,7 +69309,10 @@ 0.015, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-30" }, "longcat-2.0:thinking": { "cost": [ @@ -53099,16 +69321,10 @@ 0.015, 0.0 ], - "limit": 1000000 - }, - "longcat-2.5-preview": { - "cost": [ - 0.75, - 2.95, - 0.015, - 0.0 - ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-30" }, "meganova-ai/manta-flash-1.0": { "cost": [ @@ -53117,7 +69333,9 @@ 0.01, 0.0 ], - "limit": 16384 + "limit": 16384, + "max_output": 16384, + "released": "2025-09-20" }, "meganova-ai/manta-mini-1.0": { "cost": [ @@ -53126,7 +69344,9 @@ 0.01, 0.0 ], - "limit": 8192 + "limit": 8192, + "max_output": 8192, + "released": "2025-09-20" }, "meganova-ai/manta-pro-1.0": { "cost": [ @@ -53135,7 +69355,20 @@ 0.03, 0.0 ], - "limit": 65536 + "limit": 65536, + "max_output": 32768, + "released": "2025-09-20" + }, + "meituan/longcat-2.5-preview": { + "cost": [ + 0.75, + 2.95, + 0.015, + 0.0 + ], + "limit": 1000000, + "max_output": 131072, + "released": "2026-09-25" }, "mercury-2": { "cost": [ @@ -53144,7 +69377,9 @@ 0.025, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 50000, + "released": "2026-02-24" }, "mercury-coder-small": { "cost": [ @@ -53153,7 +69388,9 @@ 0.125, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 16384, + "released": "2024-01-01" }, "meta-llama/llama-3.1-8b-instruct": { "cost": [ @@ -53162,7 +69399,11 @@ 0.0272, 0.0 ], - "limit": 131072 + "knowledge": "2023-12", + "limit": 131072, + "max_output": 16384, + "open": true, + "released": "2024-07-23" }, "meta-llama/llama-3.2-3b-instruct": { "cost": [ @@ -53171,7 +69412,11 @@ 0.0153, 0.0 ], - "limit": 131072 + "knowledge": "2023-12", + "limit": 131072, + "max_output": 8192, + "open": true, + "released": "2024-09-25" }, "meta-llama/llama-3.3-70b-instruct": { "cost": [ @@ -53180,7 +69425,11 @@ 0.025, 0.0 ], - "limit": 131072 + "knowledge": "2023-12", + "limit": 131072, + "max_output": 16384, + "open": true, + "released": "2024-12-06" }, "meta-llama/llama-4-maverick": { "cost": [ @@ -53189,7 +69438,11 @@ 0.05, 0.0 ], - "limit": 1048576 + "knowledge": "2024-08", + "limit": 1048576, + "max_output": 65536, + "open": true, + "released": "2025-04-05" }, "meta-llama/llama-4-scout": { "cost": [ @@ -53198,7 +69451,11 @@ 0.0425, 0.0 ], - "limit": 328000 + "knowledge": "2024-08", + "limit": 328000, + "max_output": 65536, + "open": true, + "released": "2025-04-05" }, "meta/muse-glimmer-30b": { "cost": [ @@ -53207,7 +69464,11 @@ 0.04, 0.0 ], - "limit": 131072 + "knowledge": "2026-01-04", + "limit": 131072, + "max_output": 117964, + "open": true, + "released": "2026-08-10" }, "meta/muse-spark-1.1": { "cost": [ @@ -53216,7 +69477,9 @@ 0.15, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 65536, + "released": "2026-04-08" }, "meta/muse-spark-1.2": { "cost": [ @@ -53225,7 +69488,9 @@ 0.15, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 65536, + "released": "2026-08-05" }, "meta/muse-spark-1.2-contributor": { "cost": [ @@ -53234,7 +69499,9 @@ 0.002, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 65536, + "released": "2026-08-05" }, "meta/muse-spark-1.3": { "cost": [ @@ -53243,7 +69510,9 @@ 0.15, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 943718, + "released": "2026-09-02" }, "meta/muse-spark-1.3-contributor": { "cost": [ @@ -53252,7 +69521,9 @@ 0.002, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 943718, + "released": "2026-09-02" }, "meta/muse-spark-open": { "cost": [ @@ -53261,7 +69532,22 @@ 0.15, 0.0 ], - "limit": 1048576 + "knowledge": "2026-01-04", + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-10-15" + }, + "meta/muse-wonder": { + "cost": [ + 4.0, + 20.0, + 0.2, + 0.0 + ], + "limit": 1048576, + "max_output": 1048576, + "released": "2026-10-12" }, "microsoft/wizardlm-2-8x22b": { "cost": [ @@ -53270,7 +69556,10 @@ 0.2465, 0.0 ], - "limit": 65536 + "limit": 65536, + "max_output": 8192, + "open": true, + "released": "2024-04-15" }, "minimax/minimax-01": { "cost": [ @@ -53279,7 +69568,9 @@ 0.0697, 0.0 ], - "limit": 1000192 + "limit": 1000192, + "max_output": 16384, + "released": "2024-01-01" }, "minimax/minimax-latest": { "cost": [ @@ -53288,7 +69579,10 @@ 0.05, 0.0 ], - "limit": 512000 + "limit": 512000, + "max_output": 80000, + "open": true, + "released": "2026-05-03" }, "minimax/minimax-m2": { "cost": [ @@ -53297,7 +69591,10 @@ 0.085, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 131072, + "open": true, + "released": "2025-10-27" }, "minimax/minimax-m2-her": { "cost": [ @@ -53306,16 +69603,21 @@ 0.151, 0.0 ], - "limit": 65532 + "limit": 65532, + "max_output": 2048, + "released": "2026-01-23" }, "minimax/minimax-m2.1": { "cost": [ - 0.33, - 1.32, + 0.3, + 1.2, 0.03, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 131072, + "open": true, + "released": "2025-12-23" }, "minimax/minimax-m2.5": { "cost": [ @@ -53324,7 +69626,10 @@ 0.027, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-02-12" }, "minimax/minimax-m2.7": { "cost": [ @@ -53333,7 +69638,10 @@ 0.042, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-03-18" }, "minimax/minimax-m2.7-turbo": { "cost": [ @@ -53342,7 +69650,10 @@ 0.06, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-03-18" }, "minimax/minimax-m3": { "cost": [ @@ -53351,7 +69662,10 @@ 0.05, 0.0 ], - "limit": 512000 + "limit": 512000, + "max_output": 80000, + "open": true, + "released": "2026-06-01" }, "minimax/minimax-m3.1-flash": { "cost": [ @@ -53360,7 +69674,9 @@ 0.015, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 524288, + "released": "2026-10-19" }, "minimax/minimax-m3:thinking": { "cost": [ @@ -53369,7 +69685,10 @@ 0.05, 0.0 ], - "limit": 512000 + "limit": 512000, + "max_output": 80000, + "open": true, + "released": "2026-06-01" }, "mistral-code-agent-latest": { "cost": [ @@ -53378,7 +69697,10 @@ 0.2, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-06-02" }, "mistral-code-latest": { "cost": [ @@ -53387,7 +69709,9 @@ 0.15, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 32768, + "released": "2026-06-02" }, "mistralai/codestral-2508": { "cost": [ @@ -53396,7 +69720,9 @@ 0.15, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 32768, + "released": "2025-07-30" }, "mistralai/devstral-2-123b-instruct-2512": { "cost": [ @@ -53405,7 +69731,11 @@ 0.2, 0.0 ], - "limit": 262144 + "knowledge": "2025-12", + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2025-12-09" }, "mistralai/devstral-small-2505": { "cost": [ @@ -53414,7 +69744,10 @@ 0.03, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 8192, + "open": true, + "released": "2025-08-02" }, "mistralai/ministral-14b-2512": { "cost": [ @@ -53423,7 +69756,10 @@ 0.1, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2025-12-02" }, "mistralai/ministral-14b-instruct-2512": { "cost": [ @@ -53432,7 +69768,10 @@ 0.05, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2025-12-02" }, "mistralai/ministral-3b-2512": { "cost": [ @@ -53441,7 +69780,10 @@ 0.05, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-12-02" }, "mistralai/ministral-8b-2512": { "cost": [ @@ -53450,7 +69792,10 @@ 0.075, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2025-12-02" }, "mistralai/mistral-large": { "cost": [ @@ -53459,7 +69804,10 @@ 0.2, 0.0 ], - "limit": 128000 + "knowledge": "2024-11-30", + "limit": 128000, + "max_output": 102400, + "released": "2024-02-26" }, "mistralai/mistral-large-4": { "cost": [ @@ -53468,7 +69816,9 @@ 0.07, 0.0 ], - "limit": 524288 + "limit": 524288, + "max_output": 262144, + "released": "2026-10-06" }, "mistralai/mistral-medium-3": { "cost": [ @@ -53477,7 +69827,10 @@ 0.2, 0.0 ], - "limit": 131072 + "knowledge": "2025-03-31", + "limit": 131072, + "max_output": 32768, + "released": "2025-05-07" }, "mistralai/mistral-medium-3.1": { "cost": [ @@ -53486,7 +69839,10 @@ 0.2, 0.0 ], - "limit": 131072 + "knowledge": "2025-06-30", + "limit": 131072, + "max_output": 32768, + "released": "2025-08-12" }, "mistralai/mistral-medium-3.5": { "cost": [ @@ -53495,7 +69851,10 @@ 0.75, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 32768, + "open": true, + "released": "2026-04-29" }, "mistralai/mistral-medium-3.5:thinking": { "cost": [ @@ -53504,7 +69863,10 @@ 0.75, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 32768, + "open": true, + "released": "2026-04-30" }, "mistralai/mistral-nemo-instruct-2407": { "cost": [ @@ -53513,7 +69875,11 @@ 0.05015, 0.0 ], - "limit": 16384 + "knowledge": "2024-07", + "limit": 16384, + "max_output": 8192, + "open": true, + "released": "2024-07-18" }, "mistralai/mistral-saba": { "cost": [ @@ -53522,7 +69888,10 @@ 0.09945, 0.0 ], - "limit": 32768 + "knowledge": "2024-09-30", + "limit": 32768, + "max_output": 26214, + "released": "2025-02-17" }, "mistralai/mistral-small-24b-instruct-2501": { "cost": [ @@ -53531,7 +69900,11 @@ 0.0, 0.0 ], - "limit": 32768 + "knowledge": "2023-10-31", + "limit": 32768, + "max_output": 8192, + "open": true, + "released": "2025-01-30" }, "mistralai/mistral-small-3.1-24b-instruct": { "cost": [ @@ -53540,7 +69913,11 @@ 0.05, 0.0 ], - "limit": 128000 + "knowledge": "2023-10-31", + "limit": 128000, + "max_output": 102400, + "open": true, + "released": "2025-03-17" }, "mistralai/mistral-small-3.2-24b-instruct": { "cost": [ @@ -53549,7 +69926,11 @@ 0.1, 0.0 ], - "limit": 128000 + "knowledge": "2023-10-31", + "limit": 128000, + "max_output": 16384, + "open": true, + "released": "2025-06-20" }, "mistralai/mistral-small-4-119b-2603": { "cost": [ @@ -53558,7 +69939,11 @@ 0.2, 0.0 ], - "limit": 262144 + "knowledge": "2025-06", + "limit": 262144, + "max_output": 16384, + "open": true, + "released": "2026-03-16" }, "mistralai/mistral-small-4-119b-2603:thinking": { "cost": [ @@ -53567,7 +69952,11 @@ 0.2, 0.0 ], - "limit": 262144 + "knowledge": "2025-06", + "limit": 262144, + "max_output": 16384, + "open": true, + "released": "2026-03-16" }, "mistralai/mixtral-8x22b-instruct-v0.1": { "cost": [ @@ -53576,7 +69965,11 @@ 0.2, 0.0 ], - "limit": 65536 + "knowledge": "2024-01-31", + "limit": 65536, + "max_output": 52428, + "open": true, + "released": "2024-04-17" }, "mlabonne/NeuralDaredevil-8B-abliterated": { "cost": [ @@ -53585,7 +69978,10 @@ 0.22, 0.0 ], - "limit": 8192 + "limit": 8192, + "max_output": 8192, + "open": true, + "released": "2024-01-01" }, "moondream/moondream3-preview": { "cost": [ @@ -53594,7 +69990,9 @@ 0.0, 0.0 ], - "limit": 32000 + "limit": 32000, + "max_output": 4096, + "released": "2026-10-16" }, "moondream/moondream3.1-9b-a2b": { "cost": [ @@ -53603,7 +70001,9 @@ 0.0, 0.0 ], - "limit": 32000 + "limit": 32000, + "max_output": 4096, + "released": "2026-10-16" }, "moonshotai/Kimi-K2-Instruct-0905": { "cost": [ @@ -53612,7 +70012,10 @@ 0.2, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 100352, + "open": true, + "released": "2025-09-05" }, "moonshotai/kimi-k2-instruct": { "cost": [ @@ -53621,7 +70024,10 @@ 0.2, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 8192, + "open": true, + "released": "2025-07-11" }, "moonshotai/kimi-k2-instruct-0711": { "cost": [ @@ -53630,7 +70036,10 @@ 0.2, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 8192, + "open": true, + "released": "2025-07-11" }, "moonshotai/kimi-k2-thinking": { "cost": [ @@ -53639,7 +70048,11 @@ 0.15, 0.0 ], - "limit": 262144 + "knowledge": "2024-08", + "limit": 262144, + "max_output": 98304, + "open": true, + "released": "2025-11-06" }, "moonshotai/kimi-k2.5": { "cost": [ @@ -53648,7 +70061,11 @@ 0.07, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-01-27" }, "moonshotai/kimi-k2.5:thinking": { "cost": [ @@ -53657,34 +70074,50 @@ 0.07, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-01-27" }, "moonshotai/kimi-k2.6": { "cost": [ - 0.44935, - 1.892, - 0.07568, + 0.3895, + 1.64, + 0.0656, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-04-20" }, "moonshotai/kimi-k2.6:thinking": { "cost": [ - 0.44935, - 1.892, - 0.07568, + 0.3895, + 1.64, + 0.0656, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-04-20" }, "moonshotai/kimi-k2.7-code": { "cost": [ - 0.6712, - 3.35, - 0.15, + 0.6, + 3.0, + 0.12, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-06-12" }, "moonshotai/kimi-k2.7-code-highspeed": { "cost": [ @@ -53693,25 +70126,56 @@ 0.32, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-06-12" }, "moonshotai/kimi-k3": { "cost": [ - 1.2, - 5.5, - 0.2, + 1.65, + 8.25, + 0.165, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 943718, + "open": true, + "released": "2026-07-16" + }, + "moonshotai/kimi-k3.1-pro": { + "cost": [ + 2.0, + 10.0, + 0.2, + 2.0 + ], + "limit": 1048576, + "max_output": 1048576, + "released": "2026-10-23" + }, + "moonshotai/kimi-k3.1-pro-highspeed": { + "cost": [ + 4.0, + 20.0, + 0.2, + 4.0 + ], + "limit": 1048576, + "max_output": 1048576, + "released": "2026-10-24" }, "moonshotai/kimi-latest": { "cost": [ - 1.2, - 5.5, + 2.0, + 10.0, 0.2, - 0.0 + 2.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 943718, + "released": "2026-05-03" }, "nano-gpt-help": { "cost": [ @@ -53720,7 +70184,9 @@ 0.0, 0.0 ], - "limit": 6000 + "limit": 6000, + "max_output": 512, + "released": "2026-06-06" }, "nanogpt/coding-router": { "cost": [ @@ -53729,7 +70195,9 @@ 0.11, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-12" }, "nanogpt/coding-router:high": { "cost": [ @@ -53738,7 +70206,9 @@ 0.11, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-12" }, "nanogpt/coding-router:low": { "cost": [ @@ -53747,7 +70217,9 @@ 0.028, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-12" }, "nanogpt/coding-router:max": { "cost": [ @@ -53756,7 +70228,9 @@ 0.5, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-12" }, "nanogpt/coding-router:medium": { "cost": [ @@ -53765,34 +70239,33 @@ 0.028, 0.0 ], - "limit": 1000000 - }, - "nbeerbower/gemma4-gutenberg-31b": { - "cost": [ - 0.1, - 0.45, - 0.05, - 0.0 - ], - "limit": 65536 + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-12" }, - "nimbz/gemma-4-giftige-blume-31b-v2": { + "nex-agi/nex-n2.5-mini": { "cost": [ + 0.025, 0.1, - 0.45, - 0.05, + 0.0025, 0.0 ], - "limit": 65536 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-09-22" }, - "nimbz/schattenblume-31b": { + "nex-agi/nex-n2.5-pro": { "cost": [ - 0.1, - 0.45, - 0.05, + 0.075, + 0.25, + 0.015, 0.0 ], - "limit": 65536 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-09-22" }, "nothingiisreal/L3.1-70B-Celeste-V0.1-BF16": { "cost": [ @@ -53801,7 +70274,10 @@ 0.2465, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 16384, + "open": true, + "released": "2024-01-01" }, "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF": { "cost": [ @@ -53810,7 +70286,10 @@ 0.1785, 0.0 ], - "limit": 16384 + "limit": 16384, + "max_output": 8192, + "open": true, + "released": "2025-04-15" }, "nvidia/Llama-3.3-Nemotron-Super-49B-v1": { "cost": [ @@ -53819,7 +70298,10 @@ 0.075, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 16384, + "open": true, + "released": "2025-03-18" }, "nvidia/nemotron-3-nano-30b-a3b": { "cost": [ @@ -53828,7 +70310,11 @@ 0.085, 0.0 ], - "limit": 262144 + "knowledge": "2025-06-25", + "limit": 262144, + "max_output": 235929, + "open": true, + "released": "2025-12-15" }, "nvidia/nemotron-3-super-120b-a12b": { "cost": [ @@ -53837,7 +70323,11 @@ 0.025, 0.0 ], - "limit": 262144 + "knowledge": "2025-06", + "limit": 262144, + "max_output": 16384, + "open": true, + "released": "2026-03-11" }, "nvidia/nemotron-3-super-120b-a12b:thinking": { "cost": [ @@ -53846,7 +70336,11 @@ 0.025, 0.0 ], - "limit": 262144 + "knowledge": "2025-06", + "limit": 262144, + "max_output": 16384, + "open": true, + "released": "2026-03-11" }, "nvidia/nemotron-3-ultra-550b-a55b": { "cost": [ @@ -53855,7 +70349,11 @@ 0.25, 0.0 ], - "limit": 1000000 + "knowledge": "2025-09", + "limit": 1000000, + "max_output": 65536, + "open": true, + "released": "2026-06-04" }, "nvidia/nemotron-3-ultra-550b-a55b:thinking": { "cost": [ @@ -53864,7 +70362,11 @@ 0.25, 0.0 ], - "limit": 1000000 + "knowledge": "2025-09", + "limit": 1000000, + "max_output": 65536, + "open": true, + "released": "2026-06-04" }, "nvidia/nemotron-3.5-content-safety": { "cost": [ @@ -53873,7 +70375,10 @@ 0.025, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2026-06-02" }, "nvidia/nemotron-3.5-lightning": { "cost": [ @@ -53882,7 +70387,11 @@ 0.01, 0.0 ], - "limit": 1000000 + "knowledge": "2025-09", + "limit": 1000000, + "max_output": 65536, + "open": true, + "released": "2026-08-11" }, "nvidia/nemotron-3.5-lightning:thinking": { "cost": [ @@ -53891,7 +70400,11 @@ 0.01, 0.0 ], - "limit": 1000000 + "knowledge": "2025-09", + "limit": 1000000, + "max_output": 65536, + "open": true, + "released": "2026-08-11" }, "nvidia/nemotron-3.5-super-vl": { "cost": [ @@ -53900,16 +70413,10 @@ 0.02, 0.0 ], - "limit": 262144 - }, - "openai/gpt-3.5-turbo": { - "cost": [ - 0.5, - 1.5, - 0.0, - 0.0 - ], - "limit": 16385 + "limit": 262144, + "max_output": 16384, + "open": true, + "released": "2026-10-15" }, "openai/gpt-4-turbo": { "cost": [ @@ -53918,7 +70425,10 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2023-12", + "limit": 128000, + "max_output": 4096, + "released": "2023-11-06" }, "openai/gpt-4.1": { "cost": [ @@ -53927,7 +70437,10 @@ 0.5, 0.0 ], - "limit": 1047576 + "knowledge": "2024-04", + "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14" }, "openai/gpt-4.1-mini": { "cost": [ @@ -53936,7 +70449,10 @@ 0.1, 0.0 ], - "limit": 1047576 + "knowledge": "2024-04", + "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14" }, "openai/gpt-4.1-nano": { "cost": [ @@ -53945,7 +70461,10 @@ 0.025, 0.0 ], - "limit": 1047576 + "knowledge": "2024-04", + "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14" }, "openai/gpt-4o": { "cost": [ @@ -53954,7 +70473,10 @@ 1.25, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-05-13" }, "openai/gpt-4o-2024-08-06": { "cost": [ @@ -53963,7 +70485,10 @@ 1.25, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-08-06" }, "openai/gpt-4o-2024-11-20": { "cost": [ @@ -53972,7 +70497,10 @@ 1.25, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-11-20" }, "openai/gpt-4o-mini": { "cost": [ @@ -53981,7 +70509,10 @@ 0.075, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-07-18" }, "openai/gpt-5": { "cost": [ @@ -53990,7 +70521,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "openai/gpt-5-mini": { "cost": [ @@ -53999,7 +70533,10 @@ 0.025, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "openai/gpt-5-nano": { "cost": [ @@ -54008,7 +70545,10 @@ 0.005, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "openai/gpt-5-pro": { "cost": [ @@ -54017,7 +70557,10 @@ 1.5, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-10-06" }, "openai/gpt-5.1": { "cost": [ @@ -54026,7 +70569,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "openai/gpt-5.1-2025-11-13": { "cost": [ @@ -54035,7 +70581,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "openai/gpt-5.1-codex": { "cost": [ @@ -54044,7 +70593,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "openai/gpt-5.1-codex-max": { "cost": [ @@ -54053,7 +70605,10 @@ 0.25, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "openai/gpt-5.1-codex-mini": { "cost": [ @@ -54062,7 +70617,10 @@ 0.025, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "openai/gpt-5.2": { "cost": [ @@ -54071,7 +70629,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "openai/gpt-5.2-codex": { "cost": [ @@ -54080,7 +70641,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "openai/gpt-5.3-codex": { "cost": [ @@ -54089,7 +70653,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-02-05" }, "openai/gpt-5.4": { "cost": [ @@ -54098,7 +70665,10 @@ 0.25, 0.0 ], - "limit": 1050000 + "knowledge": "2025-08-31", + "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05" }, "openai/gpt-5.4-mini": { "cost": [ @@ -54107,7 +70677,10 @@ 0.075, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "openai/gpt-5.4-nano": { "cost": [ @@ -54116,7 +70689,10 @@ 0.02, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "openai/gpt-5.5": { "cost": [ @@ -54125,7 +70701,10 @@ 0.5, 0.0 ], - "limit": 1050000 + "knowledge": "2025-12-01", + "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23" }, "openai/gpt-5.6-luna": { "cost": [ @@ -54134,7 +70713,10 @@ 0.02, 0.25 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "openai/gpt-5.6-luna-pro": { "cost": [ @@ -54143,7 +70725,10 @@ 0.02, 0.25 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "openai/gpt-5.6-sol": { "cost": [ @@ -54152,7 +70737,10 @@ 0.2, 2.5 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "openai/gpt-5.6-sol-pro": { "cost": [ @@ -54161,7 +70749,10 @@ 0.2, 2.5 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "openai/gpt-5.6-terra": { "cost": [ @@ -54170,7 +70761,10 @@ 0.2, 2.5 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "openai/gpt-5.6-terra-pro": { "cost": [ @@ -54179,7 +70773,10 @@ 0.2, 2.5 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "openai/gpt-6-astra": { "cost": [ @@ -54188,7 +70785,10 @@ 1.0, 12.5 ], - "limit": 1050000 + "knowledge": "2026-04-30", + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-04" }, "openai/gpt-6-astra-pro": { "cost": [ @@ -54197,7 +70797,9 @@ 1.0, 12.5 ], - "limit": 1050000 + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-04" }, "openai/gpt-6-luna": { "cost": [ @@ -54206,7 +70808,10 @@ 0.01, 0.125 ], - "limit": 1050000 + "knowledge": "2026-05-18", + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22" }, "openai/gpt-6-luna-pro": { "cost": [ @@ -54215,7 +70820,9 @@ 0.01, 0.125 ], - "limit": 1050000 + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22" }, "openai/gpt-6-sol": { "cost": [ @@ -54224,7 +70831,10 @@ 0.2, 2.5 ], - "limit": 1050000 + "knowledge": "2026-04-20", + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22" }, "openai/gpt-6-sol-pro": { "cost": [ @@ -54233,7 +70843,9 @@ 0.2, 2.5 ], - "limit": 1050000 + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22" }, "openai/gpt-6.1-sol": { "cost": [ @@ -54242,7 +70854,10 @@ 0.1, 2.5 ], - "limit": 1050000 + "knowledge": "2026-04-30", + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-29" }, "openai/gpt-6.1-sol-pro": { "cost": [ @@ -54251,7 +70866,32 @@ 0.1, 2.5 ], - "limit": 1050000 + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-29" + }, + "openai/gpt-6.1-terra": { + "cost": [ + 1.0, + 5.0, + 0.05, + 1.25 + ], + "knowledge": "2026-06-01", + "limit": 1050000, + "max_output": 128000, + "released": "2026-10-26" + }, + "openai/gpt-6.1-terra-pro": { + "cost": [ + 1.0, + 5.0, + 0.05, + 1.25 + ], + "limit": 1050000, + "max_output": 128000, + "released": "2026-10-27" }, "openai/gpt-astra-latest": { "cost": [ @@ -54260,16 +70900,20 @@ 1.0, 12.5 ], - "limit": 1050000 + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-11" }, "openai/gpt-chat-latest": { "cost": [ 2.0, 10.0, - 0.2, + 0.1, 2.5 ], - "limit": 1050000 + "limit": 1050000, + "max_output": 128000, + "released": "2026-05-03" }, "openai/gpt-latest": { "cost": [ @@ -54278,7 +70922,9 @@ 1.0, 12.5 ], - "limit": 1050000 + "limit": 1050000, + "max_output": 128000, + "released": "2026-03-29" }, "openai/gpt-luna-latest": { "cost": [ @@ -54287,7 +70933,9 @@ 0.01, 0.125 ], - "limit": 1050000 + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-11" }, "openai/gpt-oss-120b": { "cost": [ @@ -54296,7 +70944,11 @@ 0.03, 0.0 ], - "limit": 128000 + "knowledge": "2024-06", + "limit": 128000, + "max_output": 16384, + "open": true, + "released": "2025-08-05" }, "openai/gpt-oss-20b": { "cost": [ @@ -54305,7 +70957,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 16384, + "open": true, + "released": "2025-08-05" }, "openai/gpt-oss-safeguard-20b": { "cost": [ @@ -54314,7 +70970,10 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 16384, + "open": true, + "released": "2025-10-29" }, "openai/gpt-sol-latest": { "cost": [ @@ -54323,16 +70982,20 @@ 0.1, 2.5 ], - "limit": 1050000 + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-11" }, "openai/gpt-terra-latest": { "cost": [ - 2.0, - 12.0, - 0.2, - 2.5 + 1.0, + 5.0, + 0.05, + 1.25 ], - "limit": 1050000 + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-11" }, "openai/o1": { "cost": [ @@ -54341,7 +71004,10 @@ 7.5, 0.0 ], - "limit": 200000 + "knowledge": "2023-09", + "limit": 200000, + "max_output": 100000, + "released": "2024-12-05" }, "openai/o1-pro": { "cost": [ @@ -54350,7 +71016,10 @@ 75.0, 0.0 ], - "limit": 200000 + "knowledge": "2023-09", + "limit": 200000, + "max_output": 100000, + "released": "2025-03-19" }, "openai/o3": { "cost": [ @@ -54359,7 +71028,10 @@ 1.0, 0.0 ], - "limit": 200000 + "knowledge": "2024-05", + "limit": 200000, + "max_output": 100000, + "released": "2025-04-16" }, "openai/o3-mini": { "cost": [ @@ -54368,7 +71040,10 @@ 0.55, 0.0 ], - "limit": 200000 + "knowledge": "2024-05", + "limit": 200000, + "max_output": 100000, + "released": "2024-12-20" }, "openai/o3-mini-high": { "cost": [ @@ -54377,7 +71052,10 @@ 0.55, 0.0 ], - "limit": 200000 + "knowledge": "2024-05", + "limit": 200000, + "max_output": 100000, + "released": "2024-12-20" }, "openai/o3-mini-low": { "cost": [ @@ -54386,7 +71064,10 @@ 0.55, 0.0 ], - "limit": 200000 + "knowledge": "2024-05", + "limit": 200000, + "max_output": 100000, + "released": "2024-12-20" }, "openai/o3-pro-2025-06-10": { "cost": [ @@ -54395,7 +71076,10 @@ 11.0, 0.0 ], - "limit": 200000 + "knowledge": "2024-05", + "limit": 200000, + "max_output": 100000, + "released": "2025-06-10" }, "openai/o4-mini": { "cost": [ @@ -54404,7 +71088,10 @@ 0.55, 0.0 ], - "limit": 200000 + "knowledge": "2024-05", + "limit": 200000, + "max_output": 100000, + "released": "2025-04-16" }, "openai/o4-mini-high": { "cost": [ @@ -54413,16 +71100,22 @@ 0.55, 0.0 ], - "limit": 200000 + "knowledge": "2024-05", + "limit": 200000, + "max_output": 100000, + "released": "2025-04-16" }, "ornith-ai/ornith-1.5-122b": { "cost": [ - 0.2, - 0.8, - 0.05, + 0.26, + 2.08, + 0.07, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-10-20" }, "ornith-ai/ornith-1.5-35b-a3b": { "cost": [ @@ -54431,7 +71124,10 @@ 0.05, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-07-29" }, "ornith-ai/ornith-1.5-35b-a3b:thinking": { "cost": [ @@ -54440,7 +71136,10 @@ 0.05, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-07-29" }, "pamanseau/OpenReasoning-Nemotron-32B": { "cost": [ @@ -54449,7 +71148,10 @@ 0.05, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 65536, + "open": true, + "released": "2025-08-21" }, "perceptron/perceptron-mk1": { "cost": [ @@ -54458,7 +71160,9 @@ 0.075, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 8192, + "released": "2026-05-12" }, "perceptron/perceptron-mk1.5": { "cost": [ @@ -54467,7 +71171,9 @@ 0.0, 0.0 ], - "limit": 36864 + "limit": 36864, + "max_output": 8192, + "released": "2026-09-25" }, "phi-4-mini-instruct": { "cost": [ @@ -54476,7 +71182,11 @@ 0.085, 0.0 ], - "limit": 128000 + "knowledge": "2024-06", + "limit": 128000, + "max_output": 16384, + "open": true, + "released": "2025-02-26" }, "phi-4-multimodal-instruct": { "cost": [ @@ -54485,7 +71195,11 @@ 0.035, 0.0 ], - "limit": 128000 + "knowledge": "2024-06", + "limit": 128000, + "max_output": 16384, + "open": true, + "released": "2025-02-26" }, "pokee-isaac": { "cost": [ @@ -54494,7 +71208,9 @@ 0.075, 0.0 ], - "limit": 10000000 + "limit": 10000000, + "max_output": 60000, + "released": "2026-08-04" }, "poolside/laguna-s-2.1": { "cost": [ @@ -54503,7 +71219,10 @@ 0.01, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-21" }, "poolside/laguna-s-2.1:thinking": { "cost": [ @@ -54512,7 +71231,10 @@ 0.01, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-21" }, "prism-ml/ternary-bonsai-2-27b": { "cost": [ @@ -54521,7 +71243,10 @@ 0.0375, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-09-18" }, "prism-ml/ternary-bonsai-2-9b": { "cost": [ @@ -54530,7 +71255,10 @@ 0.04, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-10-23" }, "qvq-max": { "cost": [ @@ -54539,7 +71267,10 @@ 0.6, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 8192, + "open": true, + "released": "2025-03-28" }, "qwen/qwen-2.5-72b-instruct": { "cost": [ @@ -54548,7 +71279,10 @@ 0.1785, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 8192, + "open": true, + "released": "2025-07-03" }, "qwen/qwen-long": { "cost": [ @@ -54557,7 +71291,9 @@ 0.05015, 0.0 ], - "limit": 10000000 + "limit": 10000000, + "max_output": 8192, + "released": "2024-08-01" }, "qwen/qwen-max": { "cost": [ @@ -54566,7 +71302,10 @@ 0.79985, 0.0 ], - "limit": 32000 + "knowledge": "2024-04", + "limit": 32000, + "max_output": 8192, + "released": "2024-04-03" }, "qwen/qwen-plus": { "cost": [ @@ -54575,7 +71314,10 @@ 0.19975, 0.0 ], - "limit": 995904 + "knowledge": "2024-04", + "limit": 995904, + "max_output": 32768, + "released": "2024-01-25" }, "qwen/qwen-turbo": { "cost": [ @@ -54584,7 +71326,10 @@ 0.02499, 0.0 ], - "limit": 1000000 + "knowledge": "2024-04", + "limit": 1000000, + "max_output": 8192, + "released": "2024-11-01" }, "qwen/qwen2.5-coder-32b-instruct": { "cost": [ @@ -54593,7 +71338,22 @@ 0.1003, 0.0 ], - "limit": 32000 + "limit": 32000, + "max_output": 8192, + "open": true, + "released": "2024-11-12" + }, + "qwen/qwen2.5-vl-72b-instruct": { + "cost": [ + 0.69989, + 0.69989, + 0.0, + 0.0 + ], + "limit": 32000, + "max_output": 32000, + "open": true, + "released": "2025-05-10" }, "qwen/qwen3-14b": { "cost": [ @@ -54602,7 +71362,10 @@ 0.04, 0.0 ], - "limit": 41000 + "limit": 41000, + "max_output": 32768, + "open": true, + "released": "2024-01-01" }, "qwen/qwen3-235b-a22b": { "cost": [ @@ -54611,7 +71374,11 @@ 0.0175, 0.0 ], - "limit": 262144 + "knowledge": "2025-04", + "limit": 262144, + "max_output": 16384, + "open": true, + "released": "2025-04-28" }, "qwen/qwen3-235b-a22b-instruct-2507": { "cost": [ @@ -54620,7 +71387,10 @@ 0.0175, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 16384, + "open": true, + "released": "2025-07-21" }, "qwen/qwen3-235b-a22b-thinking-2507": { "cost": [ @@ -54629,7 +71399,10 @@ 0.0, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 81920, + "open": true, + "released": "2025-07-25" }, "qwen/qwen3-30b-a3b": { "cost": [ @@ -54638,7 +71411,10 @@ 0.05, 0.0 ], - "limit": 41000 + "limit": 41000, + "max_output": 32768, + "open": true, + "released": "2025-04-28" }, "qwen/qwen3-30b-a3b-instruct-2507": { "cost": [ @@ -54647,16 +71423,23 @@ 0.1, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 32768, + "open": true, + "released": "2025-07-28" }, "qwen/qwen3-32b": { "cost": [ - 0.1, - 0.3, + 0.08, + 0.24, 0.05, 0.0 ], - "limit": 41000 + "knowledge": "2025-04", + "limit": 41000, + "max_output": 32768, + "open": true, + "released": "2025-04-28" }, "qwen/qwen3-8b": { "cost": [ @@ -54665,7 +71448,10 @@ 0.235, 0.0 ], - "limit": 41000 + "limit": 41000, + "max_output": 32768, + "open": true, + "released": "2025-04-29" }, "qwen/qwen3-coder": { "cost": [ @@ -54674,7 +71460,11 @@ 0.065, 0.0 ], - "limit": 262000 + "knowledge": "2025-04", + "limit": 262000, + "max_output": 65536, + "open": true, + "released": "2025-07-22" }, "qwen/qwen3-coder-30b-a3b-instruct": { "cost": [ @@ -54683,7 +71473,11 @@ 0.05, 0.0 ], - "limit": 128000 + "knowledge": "2025-04", + "limit": 128000, + "max_output": 65536, + "open": true, + "released": "2025-07-31" }, "qwen/qwen3-coder-flash": { "cost": [ @@ -54692,7 +71486,10 @@ 0.15, 0.0 ], - "limit": 128000 + "knowledge": "2025-04", + "limit": 128000, + "max_output": 65536, + "released": "2025-07-28" }, "qwen/qwen3-coder-next": { "cost": [ @@ -54701,34 +71498,24 @@ 0.079764, 0.0 ], - "limit": 262144 - }, - "qwen/qwen3-max": { - "cost": [ - 1.2002, - 6.001, - 0.6001, - 0.0 - ], - "limit": 256000 - }, - "qwen/qwen3-max-2026-01-23": { - "cost": [ - 1.2002, - 6.001, - 0.6001, - 0.0 - ], - "limit": 256000 + "knowledge": "2025-09", + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-03" }, "qwen/qwen3-next-80b-a3b-instruct": { "cost": [ - 0.1, + 0.09, 1.1, 0.07, 0.0 ], - "limit": 262144 + "knowledge": "2025-04", + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2025-09" }, "qwen/qwen3-next-80b-a3b-thinking": { "cost": [ @@ -54737,7 +71524,11 @@ 0.075, 0.0 ], - "limit": 256000 + "knowledge": "2025-04", + "limit": 256000, + "max_output": 32768, + "open": true, + "released": "2025-09" }, "qwen/qwen3-vl-235b-a22b-instruct": { "cost": [ @@ -54746,7 +71537,11 @@ 0.15, 0.0 ], - "limit": 131072 + "knowledge": "2025-03-31", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-09-23" }, "qwen/qwen3-vl-235b-a22b-thinking": { "cost": [ @@ -54755,7 +71550,11 @@ 0.25, 0.0 ], - "limit": 131072 + "knowledge": "2025-03-31", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-09-23" }, "qwen/qwen3.5-122b-a10b": { "cost": [ @@ -54764,7 +71563,10 @@ 0.103788, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-02-23" }, "qwen/qwen3.5-122b-a10b:thinking": { "cost": [ @@ -54773,7 +71575,10 @@ 0.103788, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-02-23" }, "qwen/qwen3.5-27b": { "cost": [ @@ -54782,7 +71587,10 @@ 0.135, 0.0 ], - "limit": 260096 + "limit": 260096, + "max_output": 65536, + "open": true, + "released": "2026-02-23" }, "qwen/qwen3.5-27b:thinking": { "cost": [ @@ -54791,7 +71599,10 @@ 0.135, 0.0 ], - "limit": 260096 + "limit": 260096, + "max_output": 65536, + "open": true, + "released": "2026-02-23" }, "qwen/qwen3.5-35b-a3b": { "cost": [ @@ -54800,7 +71611,10 @@ 0.05, 0.0 ], - "limit": 260096 + "limit": 260096, + "max_output": 65536, + "open": true, + "released": "2026-02-23" }, "qwen/qwen3.5-35b-a3b:thinking": { "cost": [ @@ -54809,7 +71623,10 @@ 0.05, 0.0 ], - "limit": 260096 + "limit": 260096, + "max_output": 65536, + "open": true, + "released": "2026-02-23" }, "qwen/qwen3.5-397b-a17b": { "cost": [ @@ -54818,7 +71635,10 @@ 0.3, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-15" }, "qwen/qwen3.5-397b-a17b:thinking": { "cost": [ @@ -54827,7 +71647,10 @@ 0.3, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-15" }, "qwen/qwen3.5-9b": { "cost": [ @@ -54836,7 +71659,10 @@ 0.025, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-23" }, "qwen/qwen3.5-flash": { "cost": [ @@ -54845,7 +71671,9 @@ 0.05, 0.0 ], - "limit": 991808 + "limit": 991808, + "max_output": 65536, + "released": "2026-02-23" }, "qwen/qwen3.5-flash:thinking": { "cost": [ @@ -54854,7 +71682,9 @@ 0.05, 0.0 ], - "limit": 991808 + "limit": 991808, + "max_output": 65536, + "released": "2026-02-23" }, "qwen/qwen3.5-plus": { "cost": [ @@ -54863,7 +71693,10 @@ 0.04, 0.0 ], - "limit": 983616 + "knowledge": "2025-04", + "limit": 983616, + "max_output": 65536, + "released": "2026-02-16" }, "qwen/qwen3.5-plus:thinking": { "cost": [ @@ -54872,7 +71705,10 @@ 0.04, 0.0 ], - "limit": 983616 + "knowledge": "2025-04", + "limit": 983616, + "max_output": 65536, + "released": "2026-02-16" }, "qwen/qwen3.6-27b": { "cost": [ @@ -54881,7 +71717,10 @@ 0.1015, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-04-22" }, "qwen/qwen3.6-27b:thinking": { "cost": [ @@ -54890,7 +71729,10 @@ 0.1015, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-04-22" }, "qwen/qwen3.6-35b-a3b": { "cost": [ @@ -54899,7 +71741,10 @@ 0.056, 0.0 ], - "limit": 262144 + "limit": 1048576, + "max_output": 16384, + "open": true, + "released": "2026-04-17" }, "qwen/qwen3.6-35b-a3b:thinking": { "cost": [ @@ -54908,7 +71753,10 @@ 0.056, 0.0 ], - "limit": 262144 + "limit": 1048576, + "max_output": 16384, + "open": true, + "released": "2026-04-17" }, "qwen/qwen3.6-flash": { "cost": [ @@ -54917,7 +71765,9 @@ 0.02, 0.24 ], - "limit": 991808 + "limit": 991808, + "max_output": 65536, + "released": "2026-04-27" }, "qwen/qwen3.6-max-preview": { "cost": [ @@ -54926,7 +71776,10 @@ 0.52, 0.0 ], - "limit": 245760 + "knowledge": "2025-04", + "limit": 245760, + "max_output": 65536, + "released": "2026-04-20" }, "qwen/qwen3.6-plus": { "cost": [ @@ -54935,7 +71788,10 @@ 0.0325, 0.40625 ], - "limit": 991808 + "knowledge": "2025-04", + "limit": 991808, + "max_output": 65536, + "released": "2026-04-02" }, "qwen/qwen3.7-flash": { "cost": [ @@ -54944,7 +71800,9 @@ 0.006, 0.038 ], - "limit": 991808 + "limit": 991808, + "max_output": 65536, + "released": "2026-07-15" }, "qwen/qwen3.7-flash:thinking": { "cost": [ @@ -54953,7 +71811,9 @@ 0.006, 0.038 ], - "limit": 983616 + "limit": 983616, + "max_output": 65536, + "released": "2026-07-15" }, "qwen/qwen3.7-max": { "cost": [ @@ -54962,7 +71822,9 @@ 0.295, 1.84375 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 65536, + "released": "2026-05-21" }, "qwen/qwen3.7-max:thinking": { "cost": [ @@ -54971,7 +71833,9 @@ 0.295, 1.84375 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 65536, + "released": "2026-05-21" }, "qwen/qwen3.7-plus": { "cost": [ @@ -54980,7 +71844,10 @@ 0.08, 0.5 ], - "limit": 991808 + "knowledge": "2025-04", + "limit": 991808, + "max_output": 65536, + "released": "2026-06-02" }, "qwen/qwen3.7-plus:thinking": { "cost": [ @@ -54989,7 +71856,10 @@ 0.08, 0.5 ], - "limit": 983616 + "knowledge": "2025-04", + "limit": 983616, + "max_output": 65536, + "released": "2026-06-02" }, "qwen/qwen3.8-27b": { "cost": [ @@ -54998,7 +71868,10 @@ 0.04, 0.0 ], - "limit": 1001536 + "limit": 1048576, + "max_output": 32768, + "open": true, + "released": "2026-08-14" }, "qwen/qwen3.8-27b-antislop": { "cost": [ @@ -55007,7 +71880,10 @@ 0.05, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-10-05" }, "qwen/qwen3.8-27b-cybersecurity": { "cost": [ @@ -55016,7 +71892,10 @@ 0.05, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-09-19" }, "qwen/qwen3.8-27b-darkidol": { "cost": [ @@ -55025,7 +71904,10 @@ 0.05, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-10-05" }, "qwen/qwen3.8-27b-fable": { "cost": [ @@ -55034,7 +71916,10 @@ 0.125, 0.0 ], - "limit": 524288 + "limit": 524288, + "max_output": 32768, + "open": true, + "released": "2026-07-29" }, "qwen/qwen3.8-27b-fimi": { "cost": [ @@ -55043,7 +71928,10 @@ 0.05, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-10-05" }, "qwen/qwen3.8-27b-hemmingway": { "cost": [ @@ -55052,7 +71940,10 @@ 0.125, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-09-21" }, "qwen/qwen3.8-27b-kimiko": { "cost": [ @@ -55061,7 +71952,10 @@ 0.05, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-10-05" }, "qwen/qwen3.8-27b-kiwen": { "cost": [ @@ -55070,7 +71964,10 @@ 0.05, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-10-05" }, "qwen/qwen3.8-27b-novelist": { "cost": [ @@ -55079,25 +71976,10 @@ 0.05, 0.0 ], - "limit": 262144 - }, - "qwen/qwen3.8-27b-obliterated": { - "cost": [ - 0.25, - 1.75, - 0.225, - 0.0 - ], - "limit": 524288 - }, - "qwen/qwen3.8-27b-obliterated:thinking": { - "cost": [ - 0.25, - 1.75, - 0.225, - 0.0 - ], - "limit": 524288 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-10-05" }, "qwen/qwen3.8-27b-queen": { "cost": [ @@ -55106,7 +71988,10 @@ 0.125, 0.0 ], - "limit": 524288 + "limit": 524288, + "max_output": 32768, + "open": true, + "released": "2026-09-09" }, "qwen/qwen3.8-27b-swift": { "cost": [ @@ -55115,7 +72000,10 @@ 0.05, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-10-05" }, "qwen/qwen3.8-27b-synthia": { "cost": [ @@ -55124,7 +72012,10 @@ 0.05, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-10-05" }, "qwen/qwen3.8-27b-uncensored": { "cost": [ @@ -55133,7 +72024,10 @@ 0.22, 0.0 ], - "limit": 1010000 + "limit": 1048576, + "max_output": 65536, + "open": true, + "released": "2026-07-29" }, "qwen/qwen3.8-27b-uncensored:thinking": { "cost": [ @@ -55142,7 +72036,10 @@ 0.22, 0.0 ], - "limit": 1010000 + "limit": 1048576, + "max_output": 65536, + "open": true, + "released": "2026-07-29" }, "qwen/qwen3.8-27b:thinking": { "cost": [ @@ -55151,7 +72048,10 @@ 0.04, 0.0 ], - "limit": 1001536 + "limit": 1048576, + "max_output": 32768, + "open": true, + "released": "2026-08-14" }, "qwen/qwen3.8-flash": { "cost": [ @@ -55160,7 +72060,9 @@ 0.016, 0.2 ], - "limit": 991808 + "limit": 991808, + "max_output": 131072, + "released": "2026-08-26" }, "qwen/qwen3.8-max": { "cost": [ @@ -55169,7 +72071,9 @@ 0.25, 2.5 ], - "limit": 991000 + "limit": 991000, + "max_output": 65536, + "released": "2026-08-03" }, "qwen/qwen3.8-max-0902": { "cost": [ @@ -55178,7 +72082,9 @@ 0.25, 2.5 ], - "limit": 991808 + "limit": 991808, + "max_output": 131072, + "released": "2026-09-02" }, "qwen/qwen3.8-max-prime": { "cost": [ @@ -55187,7 +72093,9 @@ 0.5, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-09-23" }, "qwen/qwen3.8-max:thinking": { "cost": [ @@ -55196,7 +72104,9 @@ 0.25, 2.5 ], - "limit": 991000 + "limit": 991000, + "max_output": 131072, + "released": "2026-08-03" }, "qwen/qwen3.8-omni-flash": { "cost": [ @@ -55205,7 +72115,9 @@ 0.016, 0.0 ], - "limit": 991808 + "limit": 991808, + "max_output": 131072, + "released": "2026-09-17" }, "qwen3-vl-235b-a22b-instruct-original": { "cost": [ @@ -55214,7 +72126,11 @@ 0.15, 0.0 ], - "limit": 32768 + "knowledge": "2025-03-31", + "limit": 32768, + "max_output": 32768, + "open": true, + "released": "2025-09-23" }, "reflection/beam-1.0": { "cost": [ @@ -55223,7 +72139,11 @@ 0.05, 0.0 ], - "limit": 1048576 + "knowledge": "2026-06-30", + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-10-05" }, "reka/reka-edge-2603": { "cost": [ @@ -55232,7 +72152,10 @@ 0.0, 0.0 ], - "limit": 16384 + "limit": 16384, + "max_output": 16384, + "open": true, + "released": "2026-03-11" }, "reka/reka-flash-3": { "cost": [ @@ -55241,7 +72164,11 @@ 0.0, 0.0 ], - "limit": 65536 + "knowledge": "2025-01-31", + "limit": 65536, + "max_output": 65536, + "open": true, + "released": "2025-03-10" }, "sakana/fugu-max": { "cost": [ @@ -55250,7 +72177,9 @@ 0.25, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-11" }, "sakana/fugu-ultra": { "cost": [ @@ -55259,7 +72188,9 @@ 0.5, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 16384, + "released": "2026-06-15" }, "sakana/fugu-ultra-v1.1": { "cost": [ @@ -55268,7 +72199,9 @@ 0.5, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 16384, + "released": "2026-07-24" }, "sarvam-105b": { "cost": [ @@ -55277,7 +72210,10 @@ 0.0336, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 4096, + "open": true, + "released": "2026-02-18" }, "shisa-ai/shisa-v2-llama3.3-70b": { "cost": [ @@ -55286,7 +72222,10 @@ 0.25, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 16384, + "open": true, + "released": "2025-07-26" }, "shisa-ai/shisa-v2.1-llama3.3-70b": { "cost": [ @@ -55295,7 +72234,22 @@ 0.25, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 4096, + "open": true, + "released": "2024-01-01" + }, + "soob3123/GrayLine-Qwen3-8B": { + "cost": [ + 0.3, + 0.3, + 0.0, + 0.0 + ], + "limit": 32768, + "max_output": 32768, + "open": true, + "released": "2025-09-25" }, "soob3123/Veiled-Calla-12B": { "cost": [ @@ -55304,7 +72258,10 @@ 0.15, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 8192, + "open": true, + "released": "2025-04-13" }, "soob3123/amoral-gemma3-27B-v2": { "cost": [ @@ -55313,7 +72270,22 @@ 0.15, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 8192, + "open": true, + "released": "2025-05-23" + }, + "speakleash/bielik-11b-v3.0-instruct": { + "cost": [ + 0.48, + 0.48, + 0.0, + 0.0 + ], + "limit": 32768, + "max_output": 32768, + "open": true, + "released": "2026-10-15" }, "stepfun-ai/step-3.5-flash": { "cost": [ @@ -55322,7 +72294,11 @@ 0.05, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-01-29" }, "stepfun-ai/step-3.5-flash-2603": { "cost": [ @@ -55331,7 +72307,11 @@ 0.05, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-04-02" }, "stepfun/step-3.7-flash:thinking": { "cost": [ @@ -55340,7 +72320,11 @@ 0.04, 0.0 ], - "limit": 262144 + "knowledge": "2026-03-01", + "limit": 262144, + "max_output": 256000, + "open": true, + "released": "2026-05-29" }, "stepfun/step-5-preview": { "cost": [ @@ -55349,7 +72333,32 @@ 0.05, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 65536, + "open": true, + "released": "2026-09-16" + }, + "synth-2.5-flash": { + "cost": [ + 0.03, + 0.1, + 0.0, + 0.0 + ], + "limit": 30000, + "max_output": 30000, + "released": "2026-09-05" + }, + "synth-2.5-pro": { + "cost": [ + 0.1, + 0.2, + 0.0, + 0.0 + ], + "limit": 30000, + "max_output": 30000, + "released": "2026-09-05" }, "tencent/hy3": { "cost": [ @@ -55358,7 +72367,10 @@ 0.029, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 128000, + "open": true, + "released": "2026-07-06" }, "tencent/hy4-preview": { "cost": [ @@ -55367,7 +72379,10 @@ 0.042, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 64000, + "open": true, + "released": "2026-08-28" }, "thinkingmachines/Inkling-Small": { "cost": [ @@ -55376,7 +72391,10 @@ 0.1, 0.0 ], - "limit": 524288 + "limit": 524288, + "max_output": 32768, + "open": true, + "released": "2026-07-30" }, "thinkingmachines/Inkling-Small:thinking": { "cost": [ @@ -55385,7 +72403,10 @@ 0.1, 0.0 ], - "limit": 524288 + "limit": 524288, + "max_output": 32768, + "open": true, + "released": "2026-07-30" }, "thinkingmachines/inkling": { "cost": [ @@ -55394,7 +72415,10 @@ 0.17, 0.0 ], - "limit": 1048000 + "limit": 1048000, + "max_output": 32768, + "open": true, + "released": "2026-07-15" }, "thinkingmachines/inkling:thinking": { "cost": [ @@ -55403,7 +72427,10 @@ 0.17, 0.0 ], - "limit": 1048000 + "limit": 1040000, + "max_output": 32768, + "open": true, + "released": "2026-07-15" }, "unbiased/pareto-26.10": { "cost": [ @@ -55412,7 +72439,9 @@ 0.03, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-10-01" }, "unbiased/pareto-26.9": { "cost": [ @@ -55421,7 +72450,9 @@ 0.25, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 131072, + "released": "2026-09-18" }, "undi95/remm-slerp-l2-13b": { "cost": [ @@ -55430,7 +72461,11 @@ 0.3995, 0.0 ], - "limit": 6144 + "knowledge": "2023-06-30", + "limit": 6144, + "max_output": 4096, + "open": true, + "released": "2023-07-22" }, "universal-summarizer": { "cost": [ @@ -55439,7 +72474,9 @@ 0.0, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 32768, + "released": "2025-12-23" }, "unsloth/gemma-3-12b-it": { "cost": [ @@ -55448,7 +72485,11 @@ 0.136, 0.0 ], - "limit": 131072 + "knowledge": "2024-08", + "limit": 131072, + "max_output": 16384, + "open": true, + "released": "2025-03-12" }, "unsloth/gemma-3-27b-it": { "cost": [ @@ -55457,7 +72498,11 @@ 0.1496, 0.0 ], - "limit": 128000 + "knowledge": "2024-08", + "limit": 128000, + "max_output": 96000, + "open": true, + "released": "2025-03-12" }, "unsloth/gemma-3-4b-it": { "cost": [ @@ -55466,7 +72511,11 @@ 0.1003, 0.0 ], - "limit": 128000 + "knowledge": "2024-08", + "limit": 128000, + "max_output": 8192, + "open": true, + "released": "2025-03-12" }, "upstage/solar-mini4": { "cost": [ @@ -55475,7 +72524,10 @@ 0.005, 0.0 ], - "limit": 524288 + "knowledge": "2026-02", + "limit": 524288, + "max_output": 131072, + "released": "2026-09-22" }, "upstage/solar-mini4:thinking": { "cost": [ @@ -55484,7 +72536,10 @@ 0.005, 0.0 ], - "limit": 524288 + "knowledge": "2026-02", + "limit": 524288, + "max_output": 131072, + "released": "2026-09-22" }, "upstage/solar-pro-3": { "cost": [ @@ -55493,7 +72548,10 @@ 0.015, 0.0 ], - "limit": 131072 + "knowledge": "2025-07", + "limit": 131072, + "max_output": 117964, + "released": "2026-01-26" }, "upstage/solar-pro4": { "cost": [ @@ -55502,7 +72560,10 @@ 0.006, 0.0 ], - "limit": 524288 + "knowledge": "2026-02", + "limit": 524288, + "max_output": 131072, + "released": "2026-08-06" }, "upstage/solar-pro4:thinking": { "cost": [ @@ -55511,7 +72572,10 @@ 0.006, 0.0 ], - "limit": 524288 + "knowledge": "2026-02", + "limit": 524288, + "max_output": 131072, + "released": "2026-08-06" }, "venice-uncensored": { "cost": [ @@ -55520,7 +72584,10 @@ 0.4, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 8192, + "open": true, + "released": "2025-10-01" }, "x-ai/grok-4.20": { "cost": [ @@ -55529,7 +72596,9 @@ 0.2, 0.0 ], - "limit": 2000000 + "limit": 2000000, + "max_output": 131072, + "released": "2026-03-31" }, "x-ai/grok-4.20-multi-agent": { "cost": [ @@ -55538,7 +72607,9 @@ 0.2, 0.0 ], - "limit": 2000000 + "limit": 2000000, + "max_output": 131072, + "released": "2026-03-31" }, "x-ai/grok-4.3": { "cost": [ @@ -55547,7 +72618,9 @@ 0.2, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 900000, + "released": "2026-04-17" }, "x-ai/grok-4.5": { "cost": [ @@ -55556,7 +72629,9 @@ 0.3, 0.0 ], - "limit": 500000 + "limit": 500000, + "max_output": 450000, + "released": "2026-07-08" }, "x-ai/grok-4.6": { "cost": [ @@ -55565,7 +72640,10 @@ 0.5, 0.0 ], - "limit": 500000 + "knowledge": "2026-02-01", + "limit": 500000, + "max_output": 450000, + "released": "2026-08-12" }, "x-ai/grok-4.7": { "cost": [ @@ -55574,7 +72652,10 @@ 0.5, 0.0 ], - "limit": 500000 + "knowledge": "2026-05", + "limit": 500000, + "max_output": 500000, + "released": "2026-09-21" }, "x-ai/grok-build-0.1": { "cost": [ @@ -55583,7 +72664,9 @@ 0.2, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 230400, + "released": "2026-04-16" }, "x-ai/grok-latest": { "cost": [ @@ -55592,7 +72675,9 @@ 0.5, 0.0 ], - "limit": 500000 + "limit": 500000, + "max_output": 450000, + "released": "2026-05-03" }, "xiaomi/mimo-v2.5": { "cost": [ @@ -55601,7 +72686,11 @@ 0.0028, 0.0 ], - "limit": 1048576 + "knowledge": "2024-12", + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-04-22" }, "xiaomi/mimo-v2.5-pro": { "cost": [ @@ -55610,7 +72699,11 @@ 0.0036, 0.0 ], - "limit": 1048576 + "knowledge": "2024-12", + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-04-22" }, "xiaomi/mimo-v2.5-pro:thinking": { "cost": [ @@ -55619,7 +72712,11 @@ 0.0036, 0.0 ], - "limit": 1048576 + "knowledge": "2024-12", + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-04-22" }, "xiaomi/mimo-v2.5:thinking": { "cost": [ @@ -55628,7 +72725,11 @@ 0.0028, 0.0 ], - "limit": 1048576 + "knowledge": "2024-12", + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-04-22" }, "xiaomi/mimo-v2.6-flash": { "cost": [ @@ -55637,7 +72738,10 @@ 0.0028, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-09-22" }, "xiaomi/mimo-v2.6-flash-abliterated": { "cost": [ @@ -55646,7 +72750,10 @@ 0.275, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65536, + "open": true, + "released": "2026-09-25" }, "xiaomi/mimo-v2.6-flash-uncensored": { "cost": [ @@ -55655,7 +72762,10 @@ 0.1995, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65536, + "open": true, + "released": "2026-09-25" }, "xiaomi/mimo-v2.6-flash-uncensored:thinking": { "cost": [ @@ -55664,7 +72774,10 @@ 0.1995, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65536, + "open": true, + "released": "2026-09-26" }, "xiaomi/mimo-v2.6-pro": { "cost": [ @@ -55673,7 +72786,10 @@ 0.0036, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-09-22" }, "xiaomi/mimo-v2.6-pro-ultraspeed": { "cost": [ @@ -55682,25 +72798,48 @@ 0.036, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-09-21" + }, + "xingchen-agi/xing4.0-29b-a4b": { + "cost": [ + 0.22, + 0.9, + 0.011, + 0.0 + ], + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-10-24" }, "z-ai/GLM-4.5-Air": { "cost": [ - 0.12, - 0.8, - 0.06, + 0.13, + 0.85, + 0.025, 0.0 ], - "limit": 128000 + "knowledge": "2025-04", + "limit": 128000, + "max_output": 98304, + "open": true, + "released": "2025-07-28" }, "z-ai/GLM-4.5-Air:thinking": { "cost": [ - 0.12, - 0.8, - 0.06, + 0.13, + 0.85, + 0.025, 0.0 ], - "limit": 128000 + "knowledge": "2025-04", + "limit": 128000, + "max_output": 98304, + "open": true, + "released": "2025-07-28" }, "z-ai/GLM-4.5:thinking": { "cost": [ @@ -55709,7 +72848,11 @@ 0.15, 0.0 ], - "limit": 128000 + "knowledge": "2025-04", + "limit": 128000, + "max_output": 65536, + "open": true, + "released": "2025-07-28" }, "z-ai/GLM-4.6-turbo": { "cost": [ @@ -55718,7 +72861,10 @@ 0.5, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-10-02" }, "z-ai/GLM-4.6-turbo:thinking": { "cost": [ @@ -55727,7 +72873,10 @@ 0.5, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-10-02" }, "z-ai/glm-4.5": { "cost": [ @@ -55736,7 +72885,11 @@ 0.15, 0.0 ], - "limit": 128000 + "knowledge": "2025-04", + "limit": 128000, + "max_output": 65536, + "open": true, + "released": "2025-07-28" }, "z-ai/glm-4.5v": { "cost": [ @@ -55745,7 +72898,11 @@ 0.3, 0.0 ], - "limit": 65536 + "knowledge": "2025-04", + "limit": 65536, + "max_output": 16384, + "open": true, + "released": "2025-08-11" }, "z-ai/glm-4.5v:thinking": { "cost": [ @@ -55754,7 +72911,11 @@ 0.3, 0.0 ], - "limit": 65536 + "knowledge": "2025-04", + "limit": 65536, + "max_output": 16384, + "open": true, + "released": "2025-08-11" }, "z-ai/glm-4.6": { "cost": [ @@ -55763,7 +72924,11 @@ 0.1, 0.0 ], - "limit": 200000 + "knowledge": "2025-04", + "limit": 200000, + "max_output": 65535, + "open": true, + "released": "2025-09-30" }, "z-ai/glm-4.6-original": { "cost": [ @@ -55772,7 +72937,11 @@ 0.1, 0.0 ], - "limit": 256000 + "knowledge": "2025-04", + "limit": 256000, + "max_output": 65535, + "open": true, + "released": "2025-09-30" }, "z-ai/glm-4.6:thinking": { "cost": [ @@ -55781,7 +72950,11 @@ 0.1, 0.0 ], - "limit": 200000 + "knowledge": "2025-04", + "limit": 200000, + "max_output": 65535, + "open": true, + "released": "2025-09-30" }, "z-ai/glm-4.6v": { "cost": [ @@ -55790,7 +72963,11 @@ 0.15, 0.0 ], - "limit": 128000 + "knowledge": "2025-04", + "limit": 128000, + "max_output": 24000, + "open": true, + "released": "2025-12-08" }, "z-ai/glm-4.6v-original": { "cost": [ @@ -55799,7 +72976,11 @@ 0.3, 0.0 ], - "limit": 128000 + "knowledge": "2025-04", + "limit": 128000, + "max_output": 24000, + "open": true, + "released": "2025-12-08" }, "z-ai/glm-4.7": { "cost": [ @@ -55808,7 +72989,11 @@ 0.08008, 0.0 ], - "limit": 200000 + "knowledge": "2025-04", + "limit": 200000, + "max_output": 65535, + "open": true, + "released": "2025-12-22" }, "z-ai/glm-4.7-flash": { "cost": [ @@ -55817,7 +73002,11 @@ 0.01, 0.0 ], - "limit": 200000 + "knowledge": "2025-04", + "limit": 200000, + "max_output": 128000, + "open": true, + "released": "2026-01-19" }, "z-ai/glm-4.7-flash:thinking": { "cost": [ @@ -55826,25 +73015,37 @@ 0.01, 0.0 ], - "limit": 200000 + "knowledge": "2025-04", + "limit": 200000, + "max_output": 128000, + "open": true, + "released": "2026-01-19" }, "z-ai/glm-4.7-original": { "cost": [ - 0.6, - 2.2, - 0.11, + 0.4004, + 1.9292, + 0.08008, 0.0 ], - "limit": 200000 + "knowledge": "2025-04", + "limit": 200000, + "max_output": 65535, + "open": true, + "released": "2025-12-22" }, "z-ai/glm-4.7-original:thinking": { "cost": [ - 0.6, - 2.2, - 0.11, + 0.4004, + 1.9292, + 0.08008, 0.0 ], - "limit": 200000 + "knowledge": "2025-04", + "limit": 200000, + "max_output": 65535, + "open": true, + "released": "2025-12-22" }, "z-ai/glm-4.7:thinking": { "cost": [ @@ -55853,7 +73054,11 @@ 0.08008, 0.0 ], - "limit": 200000 + "knowledge": "2025-04", + "limit": 200000, + "max_output": 65535, + "open": true, + "released": "2025-12-22" }, "z-ai/glm-5": { "cost": [ @@ -55862,7 +73067,10 @@ 0.1, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 128000, + "open": true, + "released": "2026-02-12" }, "z-ai/glm-5-original": { "cost": [ @@ -55871,7 +73079,10 @@ 0.1, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 128000, + "open": true, + "released": "2026-02-12" }, "z-ai/glm-5-original:thinking": { "cost": [ @@ -55880,7 +73091,10 @@ 0.1, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 128000, + "open": true, + "released": "2026-02-12" }, "z-ai/glm-5-turbo": { "cost": [ @@ -55889,7 +73103,9 @@ 0.24, 0.0 ], - "limit": 202800 + "limit": 202800, + "max_output": 131072, + "released": "2026-03-16" }, "z-ai/glm-5.1": { "cost": [ @@ -55898,7 +73114,10 @@ 0.18, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 131072, + "open": true, + "released": "2026-04-07" }, "z-ai/glm-5.1:thinking": { "cost": [ @@ -55907,25 +73126,34 @@ 0.18, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 131072, + "open": true, + "released": "2026-04-07" }, "z-ai/glm-5.2": { "cost": [ - 0.42, - 1.32, - 0.078, + 0.189, + 0.594, + 0.0351, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "z-ai/glm-5.2:thinking": { "cost": [ - 0.42, - 1.32, - 0.078, + 0.189, + 0.594, + 0.0351, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "z-ai/glm-5.3": { "cost": [ @@ -55934,7 +73162,10 @@ 0.2, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "z-ai/glm-5.3-flash": { "cost": [ @@ -55943,7 +73174,10 @@ 0.025, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-08-26" }, "z-ai/glm-5.3-flash-apex": { "cost": [ @@ -55952,7 +73186,10 @@ 0.075, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 32768, + "open": true, + "released": "2026-10-05" }, "z-ai/glm-5.3-flash-apex-abliterated": { "cost": [ @@ -55961,7 +73198,10 @@ 0.075, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 32768, + "open": true, + "released": "2026-10-05" }, "z-ai/glm-5.3-flash-cybersecurity": { "cost": [ @@ -55970,7 +73210,10 @@ 0.075, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 32768, + "open": true, + "released": "2026-09-19" }, "z-ai/glm-5.3-flash-uncensored": { "cost": [ @@ -55979,7 +73222,10 @@ 0.07, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 32768, + "open": true, + "released": "2026-07-29" }, "z-ai/glm-5.3-uncensored": { "cost": [ @@ -55988,7 +73234,10 @@ 0.3, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-09-26" }, "z-ai/glm-5.3:thinking": { "cost": [ @@ -55997,7 +73246,10 @@ 0.2, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "z-ai/glm-5:thinking": { "cost": [ @@ -56006,7 +73258,10 @@ 0.1, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 128000, + "open": true, + "released": "2026-02-12" }, "z-ai/glm-5v-turbo": { "cost": [ @@ -56015,7 +73270,9 @@ 0.24, 0.0 ], - "limit": 202800 + "limit": 202800, + "max_output": 131072, + "released": "2026-04-01" }, "z-ai/glm-5v-turbo:thinking": { "cost": [ @@ -56024,7 +73281,9 @@ 0.24, 0.0 ], - "limit": 202800 + "limit": 202800, + "max_output": 131072, + "released": "2026-04-01" }, "z-ai/glm-latest": { "cost": [ @@ -56033,7 +73292,10 @@ 0.2, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-05-03" } }, "name": "NanoGPT" @@ -56047,7 +73309,11 @@ 0.0, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 1024, + "open": true, + "released": "2025-06-05", + "type": "embedding" }, "Qwen/Qwen3-Reranker-0.6B": { "cost": [ @@ -56056,7 +73322,11 @@ 0.0, 0.0 ], - "limit": 40960 + "limit": 40960, + "max_output": 1024, + "open": true, + "released": "2025-06-05", + "type": "reranking" }, "Qwen/Qwen3-VL-30B-A3B-Instruct": { "cost": [ @@ -56065,7 +73335,10 @@ 0.03, 0.0 ], - "limit": 16384 + "limit": 16384, + "max_output": 8192, + "open": true, + "released": "2025-10-04" }, "Qwen/Qwen3.6-35B-A3B-FP8": { "cost": [ @@ -56074,7 +73347,10 @@ 0.056, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 8192, + "open": true, + "released": "2026-04-17" }, "Qwen/Qwen3.8-27B": { "cost": [ @@ -56083,7 +73359,10 @@ 0.018, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-08-14" }, "anthropic/claude-fable-5": { "cost": [ @@ -56092,7 +73371,10 @@ 1.0, 0.0 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-09" }, "anthropic/claude-fable-5-1": { "cost": [ @@ -56101,7 +73383,10 @@ 0.25, 0.0 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-01" }, "anthropic/claude-haiku-4-5": { "cost": [ @@ -56110,7 +73395,10 @@ 0.1, 1.25 ], - "limit": 200000 + "knowledge": "2025-02-28", + "limit": 200000, + "max_output": 64000, + "released": "2025-10-15" }, "anthropic/claude-haiku-5-5": { "cost": [ @@ -56119,7 +73407,10 @@ 0.01, 0.125 ], + "knowledge": "2026-06", "limit": 1000000, + "max_output": 128000, + "released": "2026-10-07", "tiers": [ { "cost": [ @@ -56142,7 +73433,10 @@ 0.5, 6.25 ], - "limit": 200000 + "knowledge": "2025-05-31", + "limit": 200000, + "max_output": 128000, + "released": "2026-02-05" }, "anthropic/claude-opus-4-7": { "cost": [ @@ -56151,7 +73445,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-16" }, "anthropic/claude-opus-4-8": { "cost": [ @@ -56160,7 +73457,10 @@ 0.5, 0.0 ], - "limit": 1000000 + "knowledge": "2026-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-28" }, "anthropic/claude-opus-5": { "cost": [ @@ -56169,7 +73469,10 @@ 0.5, 0.0 ], - "limit": 1000000 + "knowledge": "2026-05", + "limit": 1000000, + "max_output": 128000, + "released": "2026-07-24" }, "anthropic/claude-opus-5-5": { "cost": [ @@ -56178,7 +73481,10 @@ 0.2, 0.0 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-22" }, "anthropic/claude-sonnet-4-5": { "cost": [ @@ -56187,7 +73493,10 @@ 0.3, 3.75 ], - "limit": 200000 + "knowledge": "2025-07-31", + "limit": 200000, + "max_output": 64000, + "released": "2025-09-29" }, "anthropic/claude-sonnet-4-6": { "cost": [ @@ -56196,7 +73505,10 @@ 0.3, 3.75 ], - "limit": 1000000 + "knowledge": "2025-08-31", + "limit": 1000000, + "max_output": 64000, + "released": "2026-02-17" }, "anthropic/claude-sonnet-5": { "cost": [ @@ -56205,7 +73517,10 @@ 0.2, 0.0 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-30" }, "anthropic/claude-sonnet-5-5": { "cost": [ @@ -56214,7 +73529,10 @@ 0.1, 0.0 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-28" }, "deepseek/deepseek-v3.2": { "cost": [ @@ -56223,7 +73541,11 @@ 0.55, 0.0 ], - "limit": 128000 + "knowledge": "2024-07", + "limit": 128000, + "max_output": 64000, + "open": true, + "released": "2025-12-01" }, "deepseek/deepseek-v4.1-flash-1017": { "cost": [ @@ -56232,7 +73554,11 @@ 0.006, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-10-17" }, "google/gemini-2.5-flash": { "cost": [ @@ -56241,7 +73567,10 @@ 0.03, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2025-06-17" }, "google/gemini-2.5-flash-lite": { "cost": [ @@ -56250,7 +73579,10 @@ 0.01, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2025-06-17" }, "google/gemini-2.5-pro": { "cost": [ @@ -56259,7 +73591,10 @@ 0.125, 0.0 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2025-06-17", "tiers": [ { "cost": [ @@ -56282,7 +73617,10 @@ 0.025, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-05-07" }, "google/gemini-3.5-flash": { "cost": [ @@ -56291,7 +73629,10 @@ 0.15, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-05-19" }, "google/gemini-3.8-flash": { "cost": [ @@ -56300,7 +73641,9 @@ 0.075, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65536, + "released": "2026-09-02" }, "moonshotai/kimi-k2.6": { "cost": [ @@ -56309,7 +73652,11 @@ 0.41, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-20" }, "moonshotai/kimi-k3": { "cost": [ @@ -56318,7 +73665,21 @@ 0.33, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-16" + }, + "moonshotai/kimi-k3.1-pro": { + "cost": [ + 2.0, + 10.0, + 0.2, + 0.0 + ], + "limit": 1048576, + "max_output": 131072, + "released": "2026-10-23" }, "openai/gpt-4.1": { "cost": [ @@ -56327,7 +73688,10 @@ 0.5, 0.0 ], - "limit": 1047576 + "knowledge": "2024-04", + "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14" }, "openai/gpt-4.1-mini": { "cost": [ @@ -56336,16 +73700,10 @@ 0.1, 0.0 ], - "limit": 1047576 - }, - "openai/gpt-4.1-nano": { - "cost": [ - 0.1, - 0.4, - 0.025, - 0.0 - ], - "limit": 1047576 + "knowledge": "2024-04", + "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14" }, "openai/gpt-5": { "cost": [ @@ -56354,7 +73712,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "openai/gpt-5-mini": { "cost": [ @@ -56363,7 +73724,10 @@ 0.025, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "openai/gpt-5-nano": { "cost": [ @@ -56372,7 +73736,10 @@ 0.005, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "openai/gpt-5.1": { "cost": [ @@ -56381,7 +73748,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "openai/gpt-5.2": { "cost": [ @@ -56390,7 +73760,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "openai/gpt-5.4": { "cost": [ @@ -56399,7 +73772,10 @@ 0.25, 0.0 ], + "knowledge": "2025-08-31", "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05", "tiers": [ { "cost": [ @@ -56422,7 +73798,10 @@ 0.075, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "openai/gpt-5.4-nano": { "cost": [ @@ -56431,7 +73810,10 @@ 0.02, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "openai/gpt-5.5": { "cost": [ @@ -56440,7 +73822,10 @@ 0.5, 0.0 ], + "knowledge": "2025-12-01", "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23", "tiers": [ { "cost": [ @@ -56463,7 +73848,10 @@ 0.02, 0.0 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "openai/gpt-5.6-sol": { "cost": [ @@ -56472,7 +73860,10 @@ 0.4, 0.0 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "openai/gpt-6-astra": { "cost": [ @@ -56481,7 +73872,10 @@ 1.0, 0.0 ], - "limit": 1050000 + "knowledge": "2026-04-30", + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-04" }, "openai/gpt-6-luna": { "cost": [ @@ -56490,7 +73884,10 @@ 0.01, 0.0 ], - "limit": 1050000 + "knowledge": "2026-05-18", + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22" }, "openai/gpt-6-sol": { "cost": [ @@ -56499,7 +73896,10 @@ 0.2, 0.0 ], - "limit": 1050000 + "knowledge": "2026-04-20", + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22" }, "openai/gpt-6.1-sol": { "cost": [ @@ -56508,7 +73908,10 @@ 0.1, 0.0 ], - "limit": 1050000 + "knowledge": "2026-04-30", + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-29" }, "openai/o3": { "cost": [ @@ -56517,7 +73920,10 @@ 0.5, 0.0 ], - "limit": 200000 + "knowledge": "2024-05", + "limit": 200000, + "max_output": 100000, + "released": "2025-04-16" }, "openai/o3-mini": { "cost": [ @@ -56526,7 +73932,10 @@ 0.55, 0.0 ], - "limit": 200000 + "knowledge": "2024-05", + "limit": 200000, + "max_output": 100000, + "released": "2024-12-20" }, "openai/o4-mini": { "cost": [ @@ -56535,7 +73944,10 @@ 0.275, 0.0 ], - "limit": 200000 + "knowledge": "2024-05", + "limit": 200000, + "max_output": 100000, + "released": "2025-04-16" }, "openai/whisper-large-v3": { "cost": [ @@ -56544,7 +73956,11 @@ 0.0, 0.0 ], - "limit": 448 + "limit": 448, + "max_output": 448, + "open": true, + "released": "2023-11-06", + "type": "transcription" }, "qwen/qwen3.5-397b-a17b": { "cost": [ @@ -56553,7 +73969,10 @@ 0.25, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-15" }, "qwen/qwen3.7-max": { "cost": [ @@ -56562,7 +73981,9 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-05-21" }, "x-ai/grok-4.6": { "cost": [ @@ -56571,7 +73992,10 @@ 0.5, 0.0 ], - "limit": 500000 + "knowledge": "2026-02-01", + "limit": 500000, + "max_output": 500000, + "released": "2026-08-12" }, "x-ai/grok-4.7": { "cost": [ @@ -56580,7 +74004,10 @@ 0.5, 0.0 ], - "limit": 500000 + "knowledge": "2026-05", + "limit": 500000, + "max_output": 500000, + "released": "2026-09-21" }, "z-ai/glm-5.3": { "cost": [ @@ -56589,7 +74016,10 @@ 0.45, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "z-ai/glm-5.3-flash": { "cost": [ @@ -56598,7 +74028,10 @@ 0.012, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-26" } }, "name": "NEAR AI Cloud" @@ -56612,7 +74045,21 @@ 0.06, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-06-01" + }, + "MiniMaxAI/MiniMax-M3.1-Flash": { + "cost": [ + 0.15, + 0.6, + 0.015, + 0.0 + ], + "limit": 1048576, + "max_output": 1048576, + "released": "2026-10-19" }, "NousResearch/Hermes-4-405B": { "cost": [ @@ -56621,7 +74068,11 @@ 1.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-08-31", + "limit": 131072, + "max_output": 8192, + "open": true, + "released": "2025-08-26" }, "Qwen/Qwen3-235B-A22B-Instruct-2507": { "cost": [ @@ -56630,7 +74081,11 @@ 0.2, 0.0 ], - "limit": 262144 + "knowledge": "2025-07", + "limit": 262144, + "max_output": 8192, + "open": true, + "released": "2025-07-21" }, "Qwen/Qwen3-30B-A3B-Instruct-2507": { "cost": [ @@ -56639,7 +74094,11 @@ 0.1, 0.0 ], - "limit": 262144 + "knowledge": "2025-12", + "limit": 262144, + "max_output": 8192, + "open": true, + "released": "2025-07-28" }, "Qwen/Qwen3-Embedding-8B": { "cost": [ @@ -56648,7 +74107,11 @@ 0.0, 0.0 ], - "limit": 40960 + "knowledge": "2025-10", + "limit": 40960, + "open": true, + "released": "2025-06-05", + "type": "embedding" }, "Qwen/Qwen3.5-397B-A17B": { "cost": [ @@ -56657,7 +74120,11 @@ 0.12, 0.0 ], - "limit": 262144 + "knowledge": "2025-07", + "limit": 262144, + "max_output": 8192, + "open": true, + "released": "2026-02-15" }, "Qwen/Qwen3.8-27B": { "cost": [ @@ -56666,7 +74133,10 @@ 0.1, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-08-14" }, "deepseek-ai/DeepSeek-V4-Flash-0731": { "cost": [ @@ -56675,7 +74145,11 @@ 0.01, 0.0 ], - "limit": 1024000 + "knowledge": "2025-05", + "limit": 1024000, + "max_output": 1024000, + "open": true, + "released": "2026-07-31" }, "deepseek-ai/DeepSeek-V4-Pro": { "cost": [ @@ -56684,7 +74158,11 @@ 1.75, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-04-24" }, "deepseek-ai/DeepSeek-V4-Pro-0813": { "cost": [ @@ -56693,7 +74171,10 @@ 0.04, 0.0 ], - "limit": 979000 + "limit": 979000, + "max_output": 979000, + "open": true, + "released": "2026-08-13" }, "deepseek-ai/DeepSeek-V4.1-Flash": { "cost": [ @@ -56702,7 +74183,24 @@ 0.01, 0.0 ], - "limit": 1048000 + "knowledge": "2025-05", + "limit": 1048000, + "max_output": 1048000, + "open": true, + "released": "2026-09-10" + }, + "deepseek-ai/DeepSeek-V4.1-Flash-1017": { + "cost": [ + 0.3, + 1.2, + 0.006, + 0.0 + ], + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-10-17" }, "google/gemma-3-27b-it": { "cost": [ @@ -56711,7 +74209,11 @@ 0.1, 0.0 ], - "limit": 110000 + "knowledge": "2024-08", + "limit": 110000, + "max_output": 8192, + "open": true, + "released": "2025-03-12" }, "meta-models/muse-spark-open": { "cost": [ @@ -56720,7 +74222,11 @@ 0.15, 0.0 ], - "limit": 1048576 + "knowledge": "2026-01-04", + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-10-15" }, "moonshotai/Kimi-K2.7-Code": { "cost": [ @@ -56729,7 +74235,11 @@ 0.15, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 8000, + "open": true, + "released": "2026-06-12" }, "moonshotai/Kimi-K3": { "cost": [ @@ -56738,7 +74248,10 @@ 0.3, 0.0 ], - "limit": 1024000 + "limit": 1024000, + "max_output": 8000, + "open": true, + "released": "2026-07-16" }, "nvidia/Nemotron-3-Ultra-550b-a55b": { "cost": [ @@ -56747,7 +74260,11 @@ 0.12, 0.0 ], - "limit": 1048576 + "knowledge": "2025-09", + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-06-04" }, "nvidia/Nemotron-3.5-Super-VL": { "cost": [ @@ -56756,7 +74273,10 @@ 0.06, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-10-15" }, "nvidia/Nemotron-3_5-Lightning": { "cost": [ @@ -56765,7 +74285,11 @@ 0.06, 0.0 ], - "limit": 1048576 + "knowledge": "2025-09", + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-08-11" }, "nvidia/nemotron-3-super-120b-a12b": { "cost": [ @@ -56774,7 +74298,11 @@ 0.06, 0.0 ], - "limit": 262144 + "knowledge": "2025-06", + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-03-11" }, "openai/gpt-oss-120b": { "cost": [ @@ -56783,7 +74311,11 @@ 0.15, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 8192, + "open": true, + "released": "2025-08-05" }, "reflection/beam": { "cost": [ @@ -56792,7 +74324,11 @@ 0.05, 0.0 ], - "limit": 1048576 + "knowledge": "2026-06-30", + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-10-05" }, "zai-org/GLM-5.2": { "cost": [ @@ -56801,7 +74337,10 @@ 0.14, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-06-13" }, "zai-org/GLM-5.3": { "cost": [ @@ -56810,7 +74349,10 @@ 0.26, 0.0 ], - "limit": 1024000 + "limit": 1024000, + "max_output": 1024000, + "open": true, + "released": "2026-08-14" }, "zai-org/GLM-5.3-Flash": { "cost": [ @@ -56819,7 +74361,10 @@ 0.03, 0.0 ], - "limit": 1024000 + "limit": 1024000, + "max_output": 1024000, + "open": true, + "released": "2026-08-26" } }, "name": "Nebius Token Factory" @@ -56833,7 +74378,10 @@ 1.0, 12.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-09" }, "claude-fable-5-1": { "cost": [ @@ -56842,7 +74390,10 @@ 0.25, 12.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-01" }, "claude-haiku-4-5": { "cost": [ @@ -56851,7 +74402,10 @@ 0.1, 1.25 ], - "limit": 200000 + "knowledge": "2025-02-28", + "limit": 200000, + "max_output": 64000, + "released": "2025-10-15" }, "claude-haiku-5-5": { "cost": [ @@ -56860,7 +74414,10 @@ 0.01, 0.125 ], + "knowledge": "2026-06", "limit": 1000000, + "max_output": 128000, + "released": "2026-10-07", "tiers": [ { "cost": [ @@ -56883,7 +74440,10 @@ 1.5, 18.75 ], - "limit": 200000 + "knowledge": "2025-03-31", + "limit": 200000, + "max_output": 32000, + "released": "2025-08-05" }, "claude-opus-4-5": { "cost": [ @@ -56892,7 +74452,10 @@ 0.5, 6.25 ], - "limit": 200000 + "knowledge": "2025-05", + "limit": 200000, + "max_output": 64000, + "released": "2025-11-24" }, "claude-opus-4-6": { "cost": [ @@ -56901,7 +74464,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2025-05-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-05" }, "claude-opus-4-7": { "cost": [ @@ -56910,7 +74476,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-16" }, "claude-opus-4-8": { "cost": [ @@ -56919,7 +74488,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-28" }, "claude-opus-5": { "cost": [ @@ -56928,7 +74500,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-05", + "limit": 1000000, + "max_output": 128000, + "released": "2026-07-24" }, "claude-opus-5-5": { "cost": [ @@ -56937,7 +74512,10 @@ 0.2, 5.0 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-22" }, "claude-sonnet-4-5": { "cost": [ @@ -56946,7 +74524,10 @@ 0.3, 3.75 ], - "limit": 200000 + "knowledge": "2025-07-31", + "limit": 200000, + "max_output": 64000, + "released": "2025-09-29" }, "claude-sonnet-4-6": { "cost": [ @@ -56955,7 +74536,10 @@ 0.3, 3.75 ], - "limit": 1000000 + "knowledge": "2025-08-31", + "limit": 1000000, + "max_output": 64000, + "released": "2026-02-17" }, "claude-sonnet-5": { "cost": [ @@ -56964,7 +74548,10 @@ 0.2, 2.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-30" }, "claude-sonnet-5-5": { "cost": [ @@ -56973,7 +74560,10 @@ 0.2, 2.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-28" }, "deepseek-v4-1-flash": { "cost": [ @@ -56982,7 +74572,11 @@ 0.03, 0.0 ], + "knowledge": "2025-05", "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-09-10", "status": "deprecated" }, "gemini-3-1-flash-lite": { @@ -56992,7 +74586,10 @@ 0.025, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-03-03" }, "gemini-3-1-pro": { "cost": [ @@ -57001,7 +74598,10 @@ 0.2, 0.0 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2026-02-19", "tiers": [ { "cost": [ @@ -57024,7 +74624,10 @@ 0.15, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-05-19" }, "gemini-3-5-flash-lite": { "cost": [ @@ -57033,7 +74636,10 @@ 0.03, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-07-21" }, "gemini-3-6-flash": { "cost": [ @@ -57042,7 +74648,10 @@ 0.15, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-07-21" }, "gemini-3-7-flash": { "cost": [ @@ -57051,7 +74660,10 @@ 0.15, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-08-13" }, "gemini-3-8-flash": { "cost": [ @@ -57060,7 +74672,9 @@ 0.15, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65536, + "released": "2026-09-02" }, "gemini-3-flash": { "cost": [ @@ -57069,7 +74683,22 @@ 0.05, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2025-12-17" + }, + "gemini-4-argon": { + "cost": [ + 4.0, + 20.0, + 0.2, + 0.0 + ], + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-10-13" }, "gemma-3-12b": { "cost": [ @@ -57078,7 +74707,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-08-31", + "limit": 131072, + "max_output": 8192, + "open": true, + "released": "2025-03-12" }, "glm-5-2": { "cost": [ @@ -57087,7 +74720,10 @@ 0.26, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 65536, + "open": true, + "released": "2026-06-13" }, "glm-5-3": { "cost": [ @@ -57096,7 +74732,10 @@ 0.26, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "glm-5-3-flash": { "cost": [ @@ -57105,7 +74744,10 @@ 0.03, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-08-26" }, "gpt-5": { "cost": [ @@ -57114,7 +74756,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "gpt-5-1": { "cost": [ @@ -57123,7 +74768,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "gpt-5-2": { "cost": [ @@ -57132,7 +74780,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "gpt-5-3-codex": { "cost": [ @@ -57141,7 +74792,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-02-05" }, "gpt-5-4": { "cost": [ @@ -57150,7 +74804,10 @@ 0.25, 0.0 ], + "knowledge": "2025-08-31", "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05", "tiers": [ { "cost": [ @@ -57173,7 +74830,10 @@ 0.075, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "gpt-5-4-nano": { "cost": [ @@ -57182,7 +74842,10 @@ 0.02, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "gpt-5-5": { "cost": [ @@ -57191,7 +74854,10 @@ 0.5, 0.0 ], + "knowledge": "2025-12-01", "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23", "tiers": [ { "cost": [ @@ -57214,7 +74880,10 @@ 0.0, 0.0 ], + "knowledge": "2025-12-01", "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23", "tiers": [ { "cost": [ @@ -57237,7 +74906,10 @@ 0.02, 0.25 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -57260,7 +74932,10 @@ 0.5, 6.25 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -57283,7 +74958,10 @@ 0.2, 2.5 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -57306,7 +74984,10 @@ 0.025, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "gpt-5-nano": { "cost": [ @@ -57315,7 +74996,10 @@ 0.01, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "gpt-6-1-sol": { "cost": [ @@ -57324,7 +75008,10 @@ 0.1, 2.5 ], + "knowledge": "2026-04-30", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-29", "tiers": [ { "cost": [ @@ -57347,7 +75034,10 @@ 1.0, 12.5 ], + "knowledge": "2026-04-30", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-04", "tiers": [ { "cost": [ @@ -57370,7 +75060,10 @@ 0.01, 0.125 ], + "knowledge": "2026-05-18", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -57393,7 +75086,10 @@ 0.2, 2.5 ], + "knowledge": "2026-04-20", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -57416,7 +75112,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 25000, + "open": true, + "released": "2025-08-05" }, "gpt-oss-20b": { "cost": [ @@ -57425,7 +75125,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 25000, + "open": true, + "released": "2025-08-05" }, "grok-4-6": { "cost": [ @@ -57434,7 +75138,10 @@ 0.5, 0.0 ], - "limit": 500000 + "knowledge": "2026-02-01", + "limit": 500000, + "max_output": 524288, + "released": "2026-08-12" }, "grok-4-7": { "cost": [ @@ -57443,7 +75150,10 @@ 0.5, 0.0 ], - "limit": 500000 + "knowledge": "2026-05", + "limit": 500000, + "max_output": 500000, + "released": "2026-09-21" }, "inkling": { "cost": [ @@ -57453,6 +75163,9 @@ 0.0 ], "limit": 1048576, + "max_output": 65536, + "open": true, + "released": "2026-07-15", "status": "deprecated" }, "kimi-k3": { @@ -57462,7 +75175,10 @@ 0.3, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65536, + "open": true, + "released": "2026-07-16" }, "llama-4-maverick": { "cost": [ @@ -57471,7 +75187,11 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2024-08", + "limit": 1000000, + "max_output": 8192, + "open": true, + "released": "2025-04-05" }, "meta-llama-3-1-8b-instruct": { "cost": [ @@ -57480,7 +75200,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2023-12-31", + "limit": 131072, + "max_output": 8192, + "open": true, + "released": "2024-07-23" }, "meta-llama-3-3-70b-instruct": { "cost": [ @@ -57489,7 +75213,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2023-12", + "limit": 128000, + "max_output": 8192, + "open": true, + "released": "2024-12-06" }, "qwen3-next-80b-a3b-instruct": { "cost": [ @@ -57498,7 +75226,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2025-04", + "limit": 131072, + "max_output": 10000, + "open": true, + "released": "2025-09" }, "qwen35-122b-a10b": { "cost": [ @@ -57507,7 +75239,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 25000, + "open": true, + "released": "2026-02-23" } }, "name": "Neon" @@ -57521,7 +75256,9 @@ 0.22, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-26" }, "neosmith.intelligent-maestro": { "cost": [ @@ -57530,7 +75267,9 @@ 0.35, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 128000, + "released": "2026-08-03" }, "neosmith.intelligent-pro": { "cost": [ @@ -57539,7 +75278,9 @@ 0.3, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-26" }, "neosmith.neolite": { "cost": [ @@ -57548,7 +75289,9 @@ 0.08, 0.0 ], - "limit": 512000 + "limit": 512000, + "max_output": 64000, + "released": "2026-06-20" } }, "name": "NeoSmith" @@ -57562,7 +75305,11 @@ 0.028, 0.0 ], - "limit": 1048560 + "knowledge": "2025-05", + "limit": 1048560, + "max_output": 393216, + "open": true, + "released": "2026-04-24" }, "deepseek-v4-flash-flex": { "cost": [ @@ -57571,7 +75318,11 @@ 0.0182, 0.0 ], - "limit": 1048560 + "knowledge": "2025-05", + "limit": 1048560, + "max_output": 393216, + "open": true, + "released": "2026-04-24" }, "deepseek-v4-flash-speed": { "cost": [ @@ -57580,7 +75331,11 @@ 0.028, 0.0 ], - "limit": 1048560 + "knowledge": "2025-05", + "limit": 1048560, + "max_output": 393216, + "open": true, + "released": "2026-07-31" }, "deepseek-v4.1-flash": { "cost": [ @@ -57589,7 +75344,11 @@ 0.015, 0.0 ], - "limit": 1048560 + "knowledge": "2025-05", + "limit": 1048560, + "max_output": 393216, + "open": true, + "released": "2026-10-17" }, "deepseek-v4.1-flash-flex": { "cost": [ @@ -57598,7 +75357,11 @@ 0.00975, 0.0 ], - "limit": 1048560 + "knowledge": "2025-05", + "limit": 1048560, + "max_output": 393216, + "open": true, + "released": "2026-10-17" }, "gemma-4-31b": { "cost": [ @@ -57607,7 +75370,11 @@ 0.0144, 0.0 ], - "limit": 262128 + "knowledge": "2025-01", + "limit": 262128, + "max_output": 16384, + "open": true, + "released": "2026-04-02" }, "glm-5.3": { "cost": [ @@ -57616,7 +75383,10 @@ 0.145, 0.0 ], - "limit": 1048560 + "limit": 1048560, + "max_output": 1048560, + "open": true, + "released": "2026-08-14" }, "glm-5.3-flash": { "cost": [ @@ -57625,7 +75395,10 @@ 0.03, 0.0 ], - "limit": 1048560 + "limit": 1048560, + "max_output": 1048560, + "open": true, + "released": "2026-08-26" }, "glm-5.3-flash-flex": { "cost": [ @@ -57634,7 +75407,10 @@ 0.0195, 0.0 ], - "limit": 1048560 + "limit": 1048560, + "max_output": 1048560, + "open": true, + "released": "2026-08-26" }, "glm-5.3-flex": { "cost": [ @@ -57643,7 +75419,10 @@ 0.09425, 0.0 ], - "limit": 1048560 + "limit": 1048560, + "max_output": 1048560, + "open": true, + "released": "2026-08-14" }, "kimi-k2.7-code": { "cost": [ @@ -57652,7 +75431,11 @@ 0.095, 0.0 ], + "knowledge": "2025-01", "limit": 262128, + "max_output": 262128, + "open": true, + "released": "2026-06-12", "status": "deprecated" }, "kimi-k2.7-code-fast": { @@ -57662,7 +75445,11 @@ 0.095, 0.0 ], + "knowledge": "2025-01", "limit": 262128, + "max_output": 262128, + "open": true, + "released": "2026-06-12", "status": "deprecated" }, "kimi-k2.7-code-flex": { @@ -57672,7 +75459,11 @@ 0.06175, 0.0 ], + "knowledge": "2025-01", "limit": 262128, + "max_output": 262128, + "open": true, + "released": "2026-06-12", "status": "deprecated" }, "kimi-k3": { @@ -57682,7 +75473,10 @@ 0.3, 0.0 ], - "limit": 1048560 + "limit": 1048560, + "max_output": 1048560, + "open": true, + "released": "2026-07-16" }, "kimi-k3-fast": { "cost": [ @@ -57691,7 +75485,10 @@ 0.3, 0.0 ], - "limit": 1048560 + "limit": 1048560, + "max_output": 1048560, + "open": true, + "released": "2026-07-16" }, "kimi-k3-flex": { "cost": [ @@ -57700,7 +75497,10 @@ 0.195, 0.0 ], - "limit": 1048560 + "limit": 1048560, + "max_output": 1048560, + "open": true, + "released": "2026-07-16" }, "mimo-v2.6-pro": { "cost": [ @@ -57709,7 +75509,10 @@ 0.036, 0.0 ], - "limit": 1048560 + "limit": 1048560, + "max_output": 393216, + "open": true, + "released": "2026-09-22" }, "mimo-v2.6-pro-flex": { "cost": [ @@ -57718,7 +75521,10 @@ 0.0234, 0.0 ], - "limit": 1048560 + "limit": 1048560, + "max_output": 393216, + "open": true, + "released": "2026-09-22" }, "qwen-3.8-27b": { "cost": [ @@ -57727,7 +75533,10 @@ 0.25, 0.0 ], - "limit": 262128 + "limit": 262128, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "qwen-3.8-27b-flex": { "cost": [ @@ -57736,7 +75545,10 @@ 0.1625, 0.0 ], - "limit": 262128 + "limit": 262128, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "qwen3.6-35b": { "cost": [ @@ -57745,7 +75557,10 @@ 0.029, 0.0 ], - "limit": 131056 + "limit": 131056, + "max_output": 131056, + "open": true, + "released": "2026-04-17" }, "qwen3.6-35b-fast": { "cost": [ @@ -57754,7 +75569,10 @@ 0.029, 0.0 ], - "limit": 131056 + "limit": 131056, + "max_output": 131056, + "open": true, + "released": "2026-04-17" }, "qwen3.6-35b-flex": { "cost": [ @@ -57763,7 +75581,10 @@ 0.01885, 0.0 ], - "limit": 131056 + "limit": 131056, + "max_output": 131056, + "open": true, + "released": "2026-04-17" } }, "name": "Neuralwatt" @@ -57777,7 +75598,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-10", + "limit": 1000000, + "max_output": 64000, + "released": "2025-12-02" }, "nova-2-pro-v1": { "cost": [ @@ -57786,7 +75610,9 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 64000, + "released": "2025-12-03" } }, "name": "Nova" @@ -57800,7 +75626,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-08-24" }, "baai/bge-m3": { "cost": [ @@ -57809,7 +75638,10 @@ 0.0, 0.0 ], - "limit": 8192 + "limit": 8192, + "open": true, + "released": "2024-01-30", + "type": "embedding" }, "baai/bge-reranker-v2-m3": { "cost": [ @@ -57818,7 +75650,10 @@ 0.0, 0.0 ], - "limit": 8000 + "limit": 8000, + "open": true, + "released": "2024-03-15", + "type": "reranking" }, "baichuan/baichuan-m2-32b": { "cost": [ @@ -57827,7 +75662,10 @@ 0.0, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2025-08-13" }, "baidu/cobuddy": { "cost": [ @@ -57836,7 +75674,9 @@ 0.07, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 65536, + "released": "2026-05-06" }, "baidu/ernie-4.5-21B-a3b": { "cost": [ @@ -57845,7 +75685,10 @@ 0.0, 0.0 ], - "limit": 120000 + "limit": 120000, + "max_output": 8000, + "open": true, + "released": "2025-06-30" }, "deepseek/deepseek-ocr-2": { "cost": [ @@ -57854,7 +75697,10 @@ 0.0, 0.0 ], - "limit": 8192 + "limit": 8192, + "max_output": 8192, + "open": true, + "released": "2026-01-27" }, "deepseek/deepseek-r1-0528": { "cost": [ @@ -57863,7 +75709,10 @@ 0.35, 0.0 ], - "limit": 163840 + "limit": 163840, + "max_output": 32768, + "open": true, + "released": "2025-05-28" }, "deepseek/deepseek-r1-0528-qwen3-8b": { "cost": [ @@ -57872,7 +75721,10 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 32000, + "open": true, + "released": "2025-05-29" }, "deepseek/deepseek-r1-turbo": { "cost": [ @@ -57881,7 +75733,11 @@ 0.0, 0.0 ], - "limit": 64000 + "knowledge": "2024-07", + "limit": 64000, + "max_output": 16000, + "open": true, + "released": "2025-01-20" }, "deepseek/deepseek-v4-flash-0731": { "cost": [ @@ -57890,7 +75746,11 @@ 0.028, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 393216, + "open": true, + "released": "2026-07-31" }, "deepseek/deepseek-v4-pro": { "cost": [ @@ -57899,7 +75759,11 @@ 0.135, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 393216, + "open": true, + "released": "2026-04-24" }, "deepseek/deepseek-v4-pro-0813": { "cost": [ @@ -57908,7 +75772,10 @@ 0.044, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 393216, + "open": true, + "released": "2026-08-13" }, "deepseek/deepseek-v4.1-flash": { "cost": [ @@ -57917,7 +75784,11 @@ 0.006, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 393216, + "open": true, + "released": "2026-09-10" }, "deepseek/deepseek-v4.1-flash-1017": { "cost": [ @@ -57926,7 +75797,11 @@ 0.006, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 393216, + "open": true, + "released": "2026-10-17" }, "deepseek/deepseek_v3": { "cost": [ @@ -57935,7 +75810,10 @@ 0.0, 0.0 ], - "limit": 64000 + "limit": 64000, + "max_output": 16000, + "open": true, + "released": "2024-12-26" }, "google/gemma-3-12b-it": { "cost": [ @@ -57944,7 +75822,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-08", + "limit": 131072, + "max_output": 8192, + "open": true, + "released": "2025-03-12" }, "google/gemma-3-27b-it": { "cost": [ @@ -57953,7 +75835,11 @@ 0.0, 0.0 ], - "limit": 98304 + "knowledge": "2024-08", + "limit": 98304, + "max_output": 16384, + "open": true, + "released": "2025-03-12" }, "google/gemma-4-26b-a4b-it": { "cost": [ @@ -57962,7 +75848,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 131072, + "open": true, + "released": "2026-04-02" }, "google/gemma-4-31b-it": { "cost": [ @@ -57971,7 +75860,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 131072, + "open": true, + "released": "2026-04-02" }, "gryphe/mythomax-l2-13b": { "cost": [ @@ -57980,7 +75873,10 @@ 0.0, 0.0 ], - "limit": 4096 + "limit": 4096, + "max_output": 3200, + "open": true, + "released": "2023-08-10" }, "inclusionai/ling-3.0-flash": { "cost": [ @@ -57989,7 +75885,10 @@ 0.012, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-07-23" }, "inclusionai/ling-3.0-flash-fin": { "cost": [ @@ -57998,7 +75897,10 @@ 0.015, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-08-27" }, "inclusionai/ling-3.0-flash-sante": { "cost": [ @@ -58007,7 +75909,9 @@ 0.015, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "released": "2026-09-04" }, "inclusionai/ling-3.0-flash-vl": { "cost": [ @@ -58016,7 +75920,10 @@ 0.015, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-09-10" }, "inclusionai/ling-3.1-flash": { "cost": [ @@ -58025,7 +75932,10 @@ 0.06, 0.0 ], - "limit": 262144 + "limit": 1000000, + "max_output": 262144, + "open": true, + "released": "2026-09-29" }, "meta-llama/llama-3.1-8b-instruct": { "cost": [ @@ -58034,7 +75944,11 @@ 0.0, 0.0 ], - "limit": 16384 + "knowledge": "2023-12", + "limit": 16384, + "max_output": 16384, + "open": true, + "released": "2024-07-23" }, "meta-llama/llama-3.2-1b-instruct": { "cost": [ @@ -58043,7 +75957,11 @@ 0.0, 0.0 ], - "limit": 131000 + "knowledge": "2023-12", + "limit": 131000, + "max_output": 32000, + "open": true, + "released": "2024-09-25" }, "meta-llama/llama-3.3-70b-instruct": { "cost": [ @@ -58052,7 +75970,11 @@ 0.0, 0.0 ], - "limit": 12288 + "knowledge": "2023-12", + "limit": 12288, + "max_output": 12288, + "open": true, + "released": "2024-12-06" }, "meta-llama/llama-4-maverick-17b-128e-instruct-fp8": { "cost": [ @@ -58061,7 +75983,11 @@ 0.0, 0.0 ], - "limit": 1048576 + "knowledge": "2024-08", + "limit": 1048576, + "max_output": 8192, + "open": true, + "released": "2025-04-05" }, "meta-llama/llama-4-scout-17b-16e-instruct": { "cost": [ @@ -58070,7 +75996,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-08", + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2025-04-05" }, "microsoft/wizardlm-2-8x22b": { "cost": [ @@ -58079,7 +76009,10 @@ 0.0, 0.0 ], - "limit": 65535 + "limit": 65535, + "max_output": 8000, + "open": true, + "released": "2024-04-15" }, "mindai/macaron-v1-tall": { "cost": [ @@ -58088,7 +76021,10 @@ 0.044, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-07-21" }, "mindai/macaron-v1-venti": { "cost": [ @@ -58097,7 +76033,10 @@ 0.165, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-21" }, "minimax/minimax-m2.5": { "cost": [ @@ -58106,7 +76045,10 @@ 0.03, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 131100, + "open": true, + "released": "2026-02-12" }, "minimax/minimax-m2.7": { "cost": [ @@ -58115,7 +76057,10 @@ 0.06, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-03-18" }, "minimax/minimax-m2.7-highspeed": { "cost": [ @@ -58124,7 +76069,10 @@ 0.06, 0.375 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-03-18" }, "minimax/minimax-m3": { "cost": [ @@ -58134,6 +76082,9 @@ 0.0 ], "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-01", "tiers": [ { "cost": [ @@ -58156,7 +76107,9 @@ 0.015, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 524288, + "released": "2026-10-19" }, "minimaxai/minimax-m1-80k": { "cost": [ @@ -58165,7 +76118,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 40000, + "open": true, + "released": "2025-06-17" }, "moonshotai/kimi-k2-0905": { "cost": [ @@ -58174,7 +76130,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 98304, + "open": true, + "released": "2025-09-05" }, "moonshotai/kimi-k2-instruct": { "cost": [ @@ -58183,7 +76142,10 @@ 0.0, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 98304, + "open": true, + "released": "2025-07-11" }, "moonshotai/kimi-k2-thinking": { "cost": [ @@ -58192,7 +76154,11 @@ 0.15, 0.0 ], - "limit": 262144 + "knowledge": "2024-08", + "limit": 262144, + "max_output": 98304, + "open": true, + "released": "2025-11-06" }, "moonshotai/kimi-k2.5": { "cost": [ @@ -58201,7 +76167,11 @@ 0.1, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-01-27" }, "moonshotai/kimi-k2.6": { "cost": [ @@ -58210,7 +76180,11 @@ 0.16, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-20" }, "moonshotai/kimi-k2.7-code": { "cost": [ @@ -58219,16 +76193,45 @@ 0.19, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-06-12" }, "moonshotai/kimi-k3": { "cost": [ 3.0, 15.0, 0.3, - 0.0 + 3.0 + ], + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-07-16" + }, + "moonshotai/kimi-k3.1-pro": { + "cost": [ + 2.0, + 10.0, + 0.2, + 2.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "released": "2026-10-23" + }, + "moonshotai/kimi-k3.1-pro-highspeed": { + "cost": [ + 4.0, + 20.0, + 0.2, + 4.0 + ], + "limit": 1048576, + "max_output": 1048576, + "released": "2026-10-23" }, "nousresearch/hermes-2-pro-llama-3-8b": { "cost": [ @@ -58237,7 +76240,10 @@ 0.0, 0.0 ], - "limit": 8192 + "limit": 8192, + "max_output": 8192, + "open": true, + "released": "2024-04-30" }, "nvidia/nemotron-3-nano-30b-a3b": { "cost": [ @@ -58246,7 +76252,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-06-25", + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2025-12-15" }, "openai/gpt-oss-120b": { "cost": [ @@ -58255,7 +76265,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "paddlepaddle/paddleocr-vl": { "cost": [ @@ -58264,7 +76278,10 @@ 0.0, 0.0 ], - "limit": 16384 + "limit": 16384, + "max_output": 16384, + "open": true, + "released": "2025-10-16" }, "qwen/qwen-mt-plus": { "cost": [ @@ -58273,7 +76290,9 @@ 0.0, 0.0 ], - "limit": 16384 + "limit": 16384, + "max_output": 8192, + "released": "2025-07-24" }, "qwen/qwen3-embedding-8b": { "cost": [ @@ -58282,7 +76301,10 @@ 0.0, 0.0 ], - "limit": 32768 + "limit": 32768, + "open": true, + "released": "2025-06-05", + "type": "embedding" }, "qwen/qwen3-omni-30b-a3b-thinking": { "cost": [ @@ -58291,7 +76313,10 @@ 0.0, 0.0 ], - "limit": 65536 + "limit": 65536, + "max_output": 16384, + "open": true, + "released": "2025-09-22" }, "qwen/qwen3-reranker-8b": { "cost": [ @@ -58300,7 +76325,10 @@ 0.0, 0.0 ], - "limit": 32768 + "limit": 32768, + "open": true, + "released": "2025-06-05", + "type": "reranking" }, "qwen/qwen3-vl-30b-a3b-instruct": { "cost": [ @@ -58309,7 +76337,10 @@ 0.0, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-10-04" }, "qwen/qwen3.5-122b-a10b": { "cost": [ @@ -58318,7 +76349,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-23" }, "qwen/qwen3.5-27b": { "cost": [ @@ -58327,7 +76361,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-23" }, "qwen/qwen3.5-35b-a3b": { "cost": [ @@ -58336,7 +76373,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-23" }, "qwen/qwen3.5-397b-a17b": { "cost": [ @@ -58345,7 +76385,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-15" }, "qwen/qwen3.6-27b": { "cost": [ @@ -58354,7 +76397,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-04-22" }, "qwen/qwen3.6-35b-a3b": { "cost": [ @@ -58363,7 +76409,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-04-17" }, "qwen/qwen3.7-max": { "cost": [ @@ -58372,7 +76421,9 @@ 0.25, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 65536, + "released": "2026-05-21" }, "qwen/qwen3.8-2.4t-a95b": { "cost": [ @@ -58381,7 +76432,10 @@ 0.25, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-12" }, "qwen/qwen3.8-27b": { "cost": [ @@ -58390,7 +76444,10 @@ 0.085, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "qwen/qwen3.8-flash": { "cost": [ @@ -58399,7 +76456,9 @@ 0.016, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-08-26" }, "qwen/qwen3.8-max": { "cost": [ @@ -58408,7 +76467,9 @@ 0.25, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-08-03" }, "stepfun/step-3.7-flash": { "cost": [ @@ -58417,7 +76478,11 @@ 0.04, 0.0 ], - "limit": 262144 + "knowledge": "2026-03-01", + "limit": 262144, + "max_output": 256000, + "open": true, + "released": "2026-05-29" }, "stepfun/step-5-preview": { "cost": [ @@ -58426,7 +76491,10 @@ 0.1, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 64000, + "open": true, + "released": "2026-09-16" }, "tencent/hy3": { "cost": [ @@ -58435,7 +76503,10 @@ 0.035, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-07-06" }, "tencent/hy4-preview": { "cost": [ @@ -58444,7 +76515,10 @@ 0.042, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 64000, + "open": true, + "released": "2026-08-28" }, "xiaomimimo/mimo-v2.5": { "cost": [ @@ -58453,7 +76527,11 @@ 0.0034, 0.0 ], - "limit": 1048576 + "knowledge": "2024-12", + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-04-22" }, "xiaomimimo/mimo-v2.5-pro": { "cost": [ @@ -58462,7 +76540,11 @@ 0.0043, 0.0 ], - "limit": 1048576 + "knowledge": "2024-12", + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-04-22" }, "xiaomimimo/mimo-v2.6-flash": { "cost": [ @@ -58471,7 +76553,10 @@ 0.0028, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-09-22" }, "xiaomimimo/mimo-v2.6-pro": { "cost": [ @@ -58480,7 +76565,10 @@ 0.0036, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-09-22" }, "zai-org/autoglm-phone-9b-multilingual": { "cost": [ @@ -58489,7 +76577,10 @@ 0.0, 0.0 ], - "limit": 65536 + "limit": 65536, + "max_output": 65536, + "open": true, + "released": "2025-12-10" }, "zai-org/glm-4.5-air": { "cost": [ @@ -58498,7 +76589,11 @@ 0.025, 0.0 ], - "limit": 131072 + "knowledge": "2025-04", + "limit": 131072, + "max_output": 98304, + "open": true, + "released": "2025-07-28" }, "zai-org/glm-4.5v": { "cost": [ @@ -58507,7 +76602,11 @@ 0.11, 0.0 ], - "limit": 65536 + "knowledge": "2025-04", + "limit": 65536, + "max_output": 16384, + "open": true, + "released": "2025-08-11" }, "zai-org/glm-4.6": { "cost": [ @@ -58516,7 +76615,11 @@ 0.11, 0.0 ], - "limit": 204800 + "knowledge": "2025-04", + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-09-30" }, "zai-org/glm-4.6v": { "cost": [ @@ -58525,7 +76628,11 @@ 0.055, 0.0 ], - "limit": 131072 + "knowledge": "2025-04", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-12-08" }, "zai-org/glm-4.7": { "cost": [ @@ -58534,7 +76641,11 @@ 0.11, 0.0 ], - "limit": 204800 + "knowledge": "2025-04", + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-12-22" }, "zai-org/glm-4.7-flash": { "cost": [ @@ -58543,7 +76654,11 @@ 0.01, 0.0 ], - "limit": 200000 + "knowledge": "2025-04", + "limit": 200000, + "max_output": 128000, + "open": true, + "released": "2026-01-19" }, "zai-org/glm-5": { "cost": [ @@ -58552,7 +76667,10 @@ 0.2, 0.0 ], - "limit": 202800 + "limit": 202800, + "max_output": 131072, + "open": true, + "released": "2026-02-12" }, "zai-org/glm-5.1": { "cost": [ @@ -58561,7 +76679,10 @@ 0.26, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-04-07" }, "zai-org/glm-5.2": { "cost": [ @@ -58570,7 +76691,10 @@ 0.26, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "zai-org/glm-5.3": { "cost": [ @@ -58579,7 +76703,10 @@ 0.26, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "zai-org/glm-5.3-flash": { "cost": [ @@ -58588,7 +76715,10 @@ 0.03, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-08-26" } }, "name": "Novita AI" @@ -58601,7 +76731,11 @@ 0.0, 0.0, 0.0 - ] + ], + "knowledge": "2024-08", + "open": true, + "released": "2024-08-01", + "type": "image" }, "black-forest-labs/flux_1-kontext-dev": { "cost": [ @@ -58609,7 +76743,10 @@ 0.0, 0.0, 0.0 - ] + ], + "open": true, + "released": "2025-05-29", + "type": "image" }, "black-forest-labs/flux_1-schnell": { "cost": [ @@ -58617,7 +76754,11 @@ 0.0, 0.0, 0.0 - ] + ], + "knowledge": "2024-07", + "open": true, + "released": "2024-08-01", + "type": "image" }, "black-forest-labs/flux_2-klein-4b": { "cost": [ @@ -58625,7 +76766,11 @@ 0.0, 0.0, 0.0 - ] + ], + "knowledge": "2025-06", + "open": true, + "released": "2026-01-15", + "type": "image" }, "deepseek-ai/deepseek-v4.1-flash": { "cost": [ @@ -58634,7 +76779,11 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-09-10" }, "google/diffusiongemma-26b-a4b-it": { "cost": [ @@ -58643,7 +76792,11 @@ 0.0, 0.0 ], - "limit": 250000 + "knowledge": "2025-01", + "limit": 250000, + "max_output": 32768, + "open": true, + "released": "2026-06-09" }, "google/gemma-3-12b-it": { "cost": [ @@ -58652,7 +76805,11 @@ 0.0, 0.0 ], + "knowledge": "2024-08", "limit": 131072, + "max_output": 16384, + "open": true, + "released": "2025-03-12", "status": "deprecated" }, "google/gemma-3-4b-it": { @@ -58662,7 +76819,11 @@ 0.0, 0.0 ], + "knowledge": "2024-08", "limit": 131072, + "max_output": 16384, + "open": true, + "released": "2025-03-12", "status": "deprecated" }, "google/gemma-4-31b-it": { @@ -58672,7 +76833,11 @@ 0.0, 0.0 ], - "limit": 256000 + "knowledge": "2025-01", + "limit": 256000, + "max_output": 16384, + "open": true, + "released": "2026-04-02" }, "google/google-paligemma": { "cost": [ @@ -58681,7 +76846,10 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 8192, + "open": true, + "released": "2024-05-14" }, "meta/llama-3.2-11b-vision-instruct": { "cost": [ @@ -58690,7 +76858,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2023-12", + "limit": 128000, + "max_output": 4096, + "open": true, + "released": "2024-09-25" }, "meta/llama-3.2-90b-vision-instruct": { "cost": [ @@ -58699,7 +76871,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2023-12", + "limit": 128000, + "max_output": 8192, + "open": true, + "released": "2024-09-25" }, "meta/llama-guard-4-12b": { "cost": [ @@ -58708,7 +76884,10 @@ 0.0, 0.0 ], - "limit": 163840 + "limit": 163840, + "max_output": 16384, + "open": true, + "released": "2025-04-29" }, "meta/muse-glimmer-30b": { "cost": [ @@ -58717,7 +76896,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2026-01-04", + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2026-08-10" }, "minimaxai/minimax-m3.1-flash": { "cost": [ @@ -58726,7 +76909,9 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "released": "2026-10-19" }, "mistralai/magistral-small-2506": { "cost": [ @@ -58736,6 +76921,9 @@ 0.0 ], "limit": 32768, + "max_output": 32768, + "open": true, + "released": "2025-06-10", "status": "deprecated" }, "mistralai/mistral-7b-instruct-v0.3": { @@ -58746,6 +76934,9 @@ 0.0 ], "limit": 65536, + "max_output": 65536, + "open": true, + "released": "2024-05-22", "status": "deprecated" }, "mistralai/mistral-medium-3-instruct": { @@ -58755,7 +76946,10 @@ 0.0, 0.0 ], + "knowledge": "2025-03-31", "limit": 131072, + "max_output": 32768, + "released": "2025-05-07", "status": "deprecated" }, "moonshotai/kimi-k2.6": { @@ -58765,7 +76959,11 @@ 0.0, 0.0 ], + "knowledge": "2025-01", "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-20", "status": "deprecated" }, "moonshotai/kimi-k3": { @@ -58776,6 +76974,9 @@ 0.0 ], "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-16", "status": "deprecated" }, "nvidia/active-speaker-detection": { @@ -58784,7 +76985,10 @@ 0.0, 0.0, 0.0 - ] + ], + "max_output": 4096, + "open": true, + "released": "2026-04-16" }, "nvidia/bevformer": { "cost": [ @@ -58793,7 +76997,10 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 8192, + "open": true, + "released": "2025-03-18" }, "nvidia/cosmos-reason2-8b": { "cost": [ @@ -58803,6 +77010,9 @@ 0.0 ], "limit": 131072, + "max_output": 16384, + "open": true, + "released": "2025-12-01", "status": "deprecated" }, "nvidia/cosmos-transfer2_5-2b": { @@ -58811,7 +77021,11 @@ 0.0, 0.0, 0.0 - ] + ], + "max_output": 4096, + "open": true, + "released": "2026-02-26", + "type": "video" }, "nvidia/llama-3.1-nemotron-70b-instruct": { "cost": [ @@ -58821,6 +77035,9 @@ 0.0 ], "limit": 128000, + "max_output": 8192, + "open": true, + "released": "2025-04-15", "status": "deprecated" }, "nvidia/llama-3.1-nemotron-safety-guard-8b-v3": { @@ -58830,7 +77047,10 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 4096, + "open": true, + "released": "2025-10-28" }, "nvidia/llama-3.1-nemotron-ultra-253b-v1": { "cost": [ @@ -58840,6 +77060,9 @@ 0.0 ], "limit": 128000, + "max_output": 16384, + "open": true, + "released": "2025-04-07", "status": "deprecated" }, "nvidia/llama-nemotron-embed-vl-1b-v2": { @@ -58849,7 +77072,11 @@ 0.0, 0.0 ], - "limit": 8192 + "limit": 8192, + "max_output": 2048, + "open": true, + "released": "2025-12-18", + "type": "embedding" }, "nvidia/llama-nemotron-rerank-vl-1b-v2": { "cost": [ @@ -58858,7 +77085,11 @@ 0.0, 0.0 ], - "limit": 10240 + "limit": 10240, + "max_output": 4096, + "open": true, + "released": "2025-12-18", + "type": "reranking" }, "nvidia/magpie-tts-zeroshot": { "cost": [ @@ -58866,7 +77097,11 @@ 0.0, 0.0, 0.0 - ] + ], + "max_output": 4096, + "open": true, + "released": "2025-05-22", + "type": "speech" }, "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning": { "cost": [ @@ -58875,7 +77110,10 @@ 0.0, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 65536, + "open": true, + "released": "2026-04-28" }, "nvidia/nemotron-3-ultra-550b-a55b": { "cost": [ @@ -58884,7 +77122,11 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-09", + "limit": 1000000, + "max_output": 65536, + "open": true, + "released": "2026-06-04" }, "nvidia/nemotron-3.5-content-safety": { "cost": [ @@ -58893,7 +77135,10 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 8192, + "open": true, + "released": "2026-06-02" }, "nvidia/nemotron-3.5-lightning-30b-a3b": { "cost": [ @@ -58902,7 +77147,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-09", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-08-11" }, "nvidia/nemotron-3.5-super-vl-120b-a12b": { "cost": [ @@ -58911,7 +77160,10 @@ 0.0, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 8192, + "open": true, + "released": "2026-10-15" }, "nvidia/nemotron-voicechat": { "cost": [ @@ -58920,7 +77172,10 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 8192, + "open": true, + "released": "2026-03-16" }, "nvidia/rerank-qa-mistral-4b": { "cost": [ @@ -58930,7 +77185,11 @@ 0.0 ], "limit": 128000, - "status": "deprecated" + "max_output": 4096, + "open": true, + "released": "2024-03-17", + "status": "deprecated", + "type": "reranking" }, "nvidia/riva-translate-4b-instruct-v1.1": { "cost": [ @@ -58940,6 +77199,9 @@ 0.0 ], "limit": 128000, + "max_output": 4096, + "open": true, + "released": "2025-12-12", "status": "deprecated" }, "nvidia/sparsedrive": { @@ -58949,7 +77211,10 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 8192, + "open": true, + "released": "2025-03-18" }, "nvidia/streampetr": { "cost": [ @@ -58958,7 +77223,10 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 8192, + "open": true, + "released": "2025-11-13" }, "nvidia/studiovoice": { "cost": [ @@ -58966,7 +77234,9 @@ 0.0, 0.0, 0.0 - ] + ], + "open": true, + "released": "2024-10-03" }, "nvidia/synthetic-video-detector": { "cost": [ @@ -58974,7 +77244,10 @@ 0.0, 0.0, 0.0 - ] + ], + "max_output": 4096, + "open": true, + "released": "2026-04-16" }, "nvidia/usdcode": { "cost": [ @@ -58984,6 +77257,8 @@ 0.0 ], "limit": 128000, + "max_output": 4096, + "released": "2026-01-01", "status": "deprecated" }, "nvidia/usdvalidate": { @@ -58993,6 +77268,9 @@ 0.0, 0.0 ], + "max_output": 4096, + "open": true, + "released": "2024-07-24", "status": "deprecated" }, "openai/gpt-oss-20b": { @@ -59002,7 +77280,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "openai/whisper-large-v3": { "cost": [ @@ -59011,7 +77293,12 @@ 0.0, 0.0 ], - "limit": 448 + "knowledge": "2023-09", + "limit": 448, + "max_output": 4096, + "open": true, + "released": "2023-11-06", + "type": "transcription" }, "poolside/laguna-xs-2.1": { "cost": [ @@ -59020,7 +77307,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 16384, + "open": true, + "released": "2026-07-02" }, "qwen/qwen-image": { "cost": [ @@ -59028,7 +77318,9 @@ 0.0, 0.0, 0.0 - ] + ], + "released": "2025-08-07", + "type": "image" }, "qwen/qwen-image-edit": { "cost": [ @@ -59036,7 +77328,9 @@ 0.0, 0.0, 0.0 - ] + ], + "released": "2025-08-19", + "type": "image" }, "stepfun-ai/step-5-preview": { "cost": [ @@ -59045,7 +77339,10 @@ 0.0, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-09-16" }, "z-ai/glm-5.3": { "cost": [ @@ -59054,7 +77351,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "z-ai/glm-5.3-flash": { "cost": [ @@ -59063,7 +77363,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-26" } }, "name": "Nvidia" @@ -59077,7 +77380,11 @@ 0.0, 0.0 ], + "knowledge": "2023-12", "limit": 128000, + "max_output": 4096, + "open": true, + "released": "2024-12-06", "status": "deprecated" }, "meta.llama-4-maverick-17b-128e-instruct-fp8": { @@ -59087,7 +77394,11 @@ 0.0, 0.0 ], - "limit": 512000 + "knowledge": "2024-08", + "limit": 512000, + "max_output": 16384, + "open": true, + "released": "2025-04-05" }, "meta.llama-4-scout-17b-16e-instruct": { "cost": [ @@ -59096,7 +77407,11 @@ 0.0, 0.0 ], - "limit": 192000 + "knowledge": "2024-08", + "limit": 192000, + "max_output": 16384, + "open": true, + "released": "2025-04-05" }, "openai.gpt-oss-120b": { "cost": [ @@ -59105,7 +77420,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-06", + "limit": 128000, + "max_output": 16384, + "open": true, + "released": "2025-08-05" }, "openai.gpt-oss-20b": { "cost": [ @@ -59114,7 +77433,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-06", + "limit": 128000, + "max_output": 16384, + "open": true, + "released": "2025-08-05" }, "xai.grok-4.20-non-reasoning": { "cost": [ @@ -59124,6 +77447,8 @@ 0.0 ], "limit": 1000000, + "max_output": 30000, + "released": "2026-03-09", "tiers": [ { "cost": [ @@ -59147,6 +77472,8 @@ 0.0 ], "limit": 1000000, + "max_output": 30000, + "released": "2026-03-09", "tiers": [ { "cost": [ @@ -59170,6 +77497,8 @@ 0.0 ], "limit": 1000000, + "max_output": 30000, + "released": "2026-04-17", "tiers": [ { "cost": [ @@ -59192,7 +77521,10 @@ 0.5, 0.0 ], + "knowledge": "2026-02-01", "limit": 500000, + "max_output": 500000, + "released": "2026-08-12", "tiers": [ { "cost": [ @@ -59220,7 +77552,10 @@ 1.0, 12.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-09" }, "anthropic/claude-fable-5.1": { "cost": [ @@ -59229,7 +77564,10 @@ 0.25, 12.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-01" }, "anthropic/claude-haiku-4.5": { "cost": [ @@ -59238,7 +77576,10 @@ 0.1, 1.25 ], - "limit": 200000 + "knowledge": "2025-02-28", + "limit": 200000, + "max_output": 64000, + "released": "2025-10-15" }, "anthropic/claude-haiku-5.5": { "cost": [ @@ -59247,7 +77588,10 @@ 0.01, 0.125 ], + "knowledge": "2026-06", "limit": 1000000, + "max_output": 128000, + "released": "2026-10-07", "tiers": [ { "cost": [ @@ -59270,7 +77614,10 @@ 0.5, 6.25 ], + "knowledge": "2025-05", "limit": 200000, + "max_output": 64000, + "released": "2025-11-24", "status": "deprecated" }, "anthropic/claude-opus-4.6": { @@ -59280,7 +77627,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2025-05-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-05" }, "anthropic/claude-opus-4.7": { "cost": [ @@ -59289,7 +77639,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-16" }, "anthropic/claude-opus-4.8": { "cost": [ @@ -59298,7 +77651,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-28" }, "anthropic/claude-opus-5": { "cost": [ @@ -59307,7 +77663,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-05", + "limit": 1000000, + "max_output": 128000, + "released": "2026-07-24" }, "anthropic/claude-opus-5.5": { "cost": [ @@ -59316,7 +77675,10 @@ 0.2, 5.0 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-22" }, "anthropic/claude-sonnet-4.5": { "cost": [ @@ -59325,7 +77687,10 @@ 0.3, 3.75 ], + "knowledge": "2025-07-31", "limit": 200000, + "max_output": 64000, + "released": "2025-09-29", "status": "deprecated" }, "anthropic/claude-sonnet-4.6": { @@ -59335,7 +77700,10 @@ 0.3, 3.75 ], - "limit": 1000000 + "knowledge": "2025-08-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-17" }, "anthropic/claude-sonnet-5": { "cost": [ @@ -59344,7 +77712,10 @@ 0.2, 2.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-30" }, "anthropic/claude-sonnet-5.5": { "cost": [ @@ -59353,7 +77724,10 @@ 0.2, 2.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-28" }, "bailian/qwen-flash": { "cost": [ @@ -59362,7 +77736,10 @@ 0.0043, 0.027 ], - "limit": 1000000 + "knowledge": "2024-04", + "limit": 1000000, + "max_output": 32768, + "released": "2025-07-28" }, "bailian/qwen-max": { "cost": [ @@ -59371,7 +77748,10 @@ 0.069, 0.0 ], - "limit": 32768 + "knowledge": "2024-04", + "limit": 32768, + "max_output": 8192, + "released": "2024-04-03" }, "bailian/qwen-plus": { "cost": [ @@ -59380,7 +77760,10 @@ 0.023, 0.0 ], - "limit": 1000000 + "knowledge": "2024-04", + "limit": 1000000, + "max_output": 32768, + "released": "2024-01-25" }, "bailian/qwen-turbo": { "cost": [ @@ -59389,7 +77772,10 @@ 0.0086, 0.0 ], - "limit": 128000 + "knowledge": "2024-04", + "limit": 128000, + "max_output": 16384, + "released": "2024-11-01" }, "bailian/qwen-vl-max": { "cost": [ @@ -59398,7 +77784,10 @@ 0.046, 0.0 ], - "limit": 131072 + "knowledge": "2024-04", + "limit": 131072, + "max_output": 8192, + "released": "2024-04-08" }, "bailian/qwen3-coder-flash": { "cost": [ @@ -59407,7 +77796,10 @@ 0.06, 0.27 ], - "limit": 1000000 + "knowledge": "2025-04", + "limit": 1000000, + "max_output": 65536, + "released": "2025-07-28" }, "bailian/qwen3-coder-next": { "cost": [ @@ -59416,7 +77808,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-09", + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-03" }, "bailian/qwen3-coder-plus": { "cost": [ @@ -59425,7 +77821,10 @@ 0.2, 1.0 ], - "limit": 1048576 + "knowledge": "2025-04", + "limit": 1048576, + "max_output": 65536, + "released": "2025-07-23" }, "bailian/qwen3-max": { "cost": [ @@ -59434,7 +77833,10 @@ 0.072, 0.0 ], - "limit": 262144 + "knowledge": "2025-04", + "limit": 262144, + "max_output": 65536, + "released": "2025-09-23" }, "bailian/qwen3.5-122b-a10b": { "cost": [ @@ -59443,7 +77845,10 @@ 0.29, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 64000, + "open": true, + "released": "2026-02-23" }, "bailian/qwen3.5-27b": { "cost": [ @@ -59452,7 +77857,10 @@ 0.29, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-23" }, "bailian/qwen3.5-35b-a3b": { "cost": [ @@ -59461,7 +77869,10 @@ 0.29, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-23" }, "bailian/qwen3.5-397b-a17b": { "cost": [ @@ -59470,7 +77881,10 @@ 0.55, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 64000, + "open": true, + "released": "2026-02-15" }, "bailian/qwen3.5-flash": { "cost": [ @@ -59479,7 +77893,9 @@ 0.01, 0.125 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 65536, + "released": "2026-02-23" }, "bailian/qwen3.5-plus": { "cost": [ @@ -59488,7 +77904,10 @@ 0.04, 0.4 ], - "limit": 1000000 + "knowledge": "2025-04", + "limit": 1000000, + "max_output": 65536, + "released": "2026-02-16" }, "bailian/qwen3.6-27b": { "cost": [ @@ -59497,7 +77916,10 @@ 0.0, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 64000, + "open": true, + "released": "2026-04-22" }, "bailian/qwen3.6-flash": { "cost": [ @@ -59506,7 +77928,9 @@ 0.025, 0.31 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 65536, + "released": "2026-04-27" }, "bailian/qwen3.6-max-preview": { "cost": [ @@ -59515,7 +77939,10 @@ 0.2, 1.17 ], - "limit": 262144 + "knowledge": "2025-04", + "limit": 262144, + "max_output": 65536, + "released": "2026-04-20" }, "bailian/qwen3.6-plus": { "cost": [ @@ -59524,7 +77951,10 @@ 0.05, 0.625 ], - "limit": 1000000 + "knowledge": "2025-04", + "limit": 1000000, + "max_output": 65536, + "released": "2026-04-02" }, "bailian/qwen3.7-max": { "cost": [ @@ -59533,7 +77963,9 @@ 0.5, 3.125 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-05-21" }, "bailian/qwen3.7-plus": { "cost": [ @@ -59542,7 +77974,10 @@ 0.08, 0.5 ], - "limit": 1000000 + "knowledge": "2025-04", + "limit": 1000000, + "max_output": 64000, + "released": "2026-06-02" }, "bailian/qwen3.8-27b": { "cost": [ @@ -59551,7 +77986,10 @@ 0.05, 0.5625 ], - "limit": 1131072 + "limit": 1131072, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "bailian/qwen3.8-flash": { "cost": [ @@ -59560,7 +77998,9 @@ 0.016, 0.2 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-08-26" }, "bailian/qwen3.8-max": { "cost": [ @@ -59569,7 +78009,9 @@ 0.25, 2.5 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-08-03" }, "bailian/qwen3.8-max-0902": { "cost": [ @@ -59578,7 +78020,9 @@ 0.25, 2.5 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-09-02" }, "deepseek/deepseek-v3.2": { "cost": [ @@ -59587,7 +78031,11 @@ 0.06, 0.0 ], - "limit": 128000 + "knowledge": "2024-07", + "limit": 128000, + "max_output": 32000, + "open": true, + "released": "2025-12-01" }, "deepseek/deepseek-v4-flash": { "cost": [ @@ -59596,7 +78044,11 @@ 0.014, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "deepseek/deepseek-v4-flash-0423": { "cost": [ @@ -59605,7 +78057,11 @@ 0.028, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-23" }, "deepseek/deepseek-v4-flash-0731": { "cost": [ @@ -59614,7 +78070,11 @@ 0.014, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-07-31" }, "deepseek/deepseek-v4-pro": { "cost": [ @@ -59623,16 +78083,24 @@ 0.044, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "deepseek/deepseek-v4-pro-0423": { "cost": [ - 1.32, - 3.96, - 0.15, + 1.74, + 3.48, + 0.145, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-23" }, "deepseek/deepseek-v4-pro-0813": { "cost": [ @@ -59641,7 +78109,10 @@ 0.044, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-08-13" }, "deepseek/deepseek-v4.1-flash": { "cost": [ @@ -59650,7 +78121,11 @@ 0.006, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-09-10" }, "deepseek/deepseek-v4.1-flash-1017": { "cost": [ @@ -59659,7 +78134,11 @@ 0.006, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-10-17" }, "google/gemini-2.5-flash": { "cost": [ @@ -59668,7 +78147,10 @@ 0.03, 1.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2025-06-17" }, "google/gemini-2.5-flash-lite": { "cost": [ @@ -59677,7 +78159,10 @@ 0.01, 1.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2025-06-17" }, "google/gemini-2.5-pro": { "cost": [ @@ -59686,7 +78171,10 @@ 0.125, 4.5 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2025-06-17" }, "google/gemini-3-flash-preview": { "cost": [ @@ -59695,7 +78183,10 @@ 0.05, 1.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2025-12-17" }, "google/gemini-3.1-flash-lite": { "cost": [ @@ -59704,7 +78195,10 @@ 0.025, 1.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-05-07" }, "google/gemini-3.1-pro-preview": { "cost": [ @@ -59713,7 +78207,10 @@ 0.2, 4.5 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-02-19" }, "google/gemini-3.5-flash": { "cost": [ @@ -59722,7 +78219,10 @@ 0.15, 0.083 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-05-19" }, "google/gemini-3.5-flash-lite": { "cost": [ @@ -59731,7 +78231,10 @@ 0.03, 0.083 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-07-21" }, "google/gemini-3.6-flash": { "cost": [ @@ -59740,7 +78243,10 @@ 0.075, 0.0415 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-07-21" }, "google/gemini-3.7-flash": { "cost": [ @@ -59749,7 +78255,10 @@ 0.075, 0.0415 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-08-13" }, "google/gemini-3.8-flash": { "cost": [ @@ -59758,7 +78267,9 @@ 0.075, 0.0415 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 65536, + "released": "2026-09-02" }, "google/gemini-4-argon": { "cost": [ @@ -59767,7 +78278,10 @@ 0.1, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-10-13" }, "minimax/m2-her": { "cost": [ @@ -59776,7 +78290,9 @@ 0.0, 0.0 ], - "limit": 65536 + "limit": 65536, + "max_output": 2048, + "released": "2026-01-23" }, "minimax/minimax-m2": { "cost": [ @@ -59785,7 +78301,10 @@ 0.03, 0.375 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-10-27" }, "minimax/minimax-m2.1": { "cost": [ @@ -59794,7 +78313,10 @@ 0.03, 0.375 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-12-23" }, "minimax/minimax-m2.1-lightning": { "cost": [ @@ -59803,7 +78325,10 @@ 0.03, 0.375 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-12-23" }, "minimax/minimax-m2.5": { "cost": [ @@ -59812,7 +78337,10 @@ 0.03, 0.375 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-02-12" }, "minimax/minimax-m2.5-lightning": { "cost": [ @@ -59821,7 +78349,10 @@ 0.03, 0.375 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-02-13" }, "minimax/minimax-m2.7": { "cost": [ @@ -59830,7 +78361,10 @@ 0.06, 0.375 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-03-18" }, "minimax/minimax-m2.7-highspeed": { "cost": [ @@ -59839,7 +78373,10 @@ 0.06, 0.375 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-03-18" }, "minimax/minimax-m3": { "cost": [ @@ -59848,7 +78385,10 @@ 0.12, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 512000, + "open": true, + "released": "2026-06-01" }, "moonshotai/kimi-k2.6": { "cost": [ @@ -59857,7 +78397,11 @@ 0.16, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-20" }, "moonshotai/kimi-k2.7-code": { "cost": [ @@ -59866,7 +78410,11 @@ 0.19, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-06-12" }, "moonshotai/kimi-k2.7-code-highspeed": { "cost": [ @@ -59875,7 +78423,11 @@ 0.38, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-06-12" }, "moonshotai/kimi-k3": { "cost": [ @@ -59884,7 +78436,10 @@ 0.3, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-16" }, "openai/gpt-4.1": { "cost": [ @@ -59893,7 +78448,10 @@ 0.5, 0.0 ], - "limit": 1047576 + "knowledge": "2024-04", + "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14" }, "openai/gpt-4.1-mini": { "cost": [ @@ -59902,7 +78460,10 @@ 0.1, 0.0 ], - "limit": 1047576 + "knowledge": "2024-04", + "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14" }, "openai/gpt-4o": { "cost": [ @@ -59911,7 +78472,10 @@ 1.25, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-05-13" }, "openai/gpt-4o-mini": { "cost": [ @@ -59920,7 +78484,10 @@ 0.075, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-07-18" }, "openai/gpt-5": { "cost": [ @@ -59929,7 +78496,10 @@ 0.13, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "openai/gpt-5-mini": { "cost": [ @@ -59938,7 +78508,10 @@ 0.03, 0.0 ], - "limit": 256000 + "knowledge": "2024-05-30", + "limit": 256000, + "max_output": 32768, + "released": "2025-08-07" }, "openai/gpt-5-nano": { "cost": [ @@ -59947,7 +78520,10 @@ 0.01, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "openai/gpt-5.1": { "cost": [ @@ -59956,7 +78532,10 @@ 0.13, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "openai/gpt-5.1-codex-max": { "cost": [ @@ -59965,7 +78544,10 @@ 0.13, 0.0 ], - "limit": 256000 + "knowledge": "2024-09-30", + "limit": 256000, + "max_output": 128000, + "released": "2025-11-13" }, "openai/gpt-5.1-codex-mini": { "cost": [ @@ -59974,7 +78556,10 @@ 0.03, 0.0 ], - "limit": 256000 + "knowledge": "2024-09-30", + "limit": 256000, + "max_output": 65536, + "released": "2025-11-13" }, "openai/gpt-5.2": { "cost": [ @@ -59983,7 +78568,10 @@ 0.18, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "openai/gpt-5.2-codex": { "cost": [ @@ -59992,7 +78580,10 @@ 0.18, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "openai/gpt-5.3-codex": { "cost": [ @@ -60001,7 +78592,10 @@ 0.18, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-02-05" }, "openai/gpt-5.4": { "cost": [ @@ -60010,7 +78604,10 @@ 0.25, 0.0 ], + "knowledge": "2025-08-31", "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05", "tiers": [ { "cost": [ @@ -60033,7 +78630,10 @@ 0.075, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "openai/gpt-5.4-nano": { "cost": [ @@ -60042,7 +78642,10 @@ 0.02, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "openai/gpt-5.4-pro": { "cost": [ @@ -60051,7 +78654,10 @@ 0.0, 0.0 ], + "knowledge": "2025-08-31", "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05", "tiers": [ { "cost": [ @@ -60074,7 +78680,10 @@ 0.5, 0.0 ], + "knowledge": "2025-12-01", "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23", "tiers": [ { "cost": [ @@ -60097,7 +78706,10 @@ 0.02, 0.25 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -60120,7 +78732,10 @@ 0.25, 3.125 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -60143,7 +78758,10 @@ 0.2, 2.5 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -60166,7 +78784,10 @@ 1.0, 12.5 ], + "knowledge": "2026-04-30", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-04", "tiers": [ { "cost": [ @@ -60189,7 +78810,10 @@ 0.01, 0.125 ], + "knowledge": "2026-05-18", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -60212,7 +78836,10 @@ 0.2, 2.5 ], + "knowledge": "2026-04-20", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -60235,7 +78862,10 @@ 0.1, 2.5 ], + "knowledge": "2026-04-30", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-29", "tiers": [ { "cost": [ @@ -60258,7 +78888,10 @@ 0.0043, 0.027 ], - "limit": 1000000 + "knowledge": "2024-04", + "limit": 1000000, + "max_output": 32000, + "released": "2025-07-28" }, "qwen/qwen-max": { "cost": [ @@ -60267,7 +78900,10 @@ 0.069, 0.0 ], - "limit": 32000 + "knowledge": "2024-04", + "limit": 32000, + "max_output": 8000, + "released": "2024-04-03" }, "qwen/qwen-plus": { "cost": [ @@ -60276,7 +78912,10 @@ 0.023, 0.0 ], - "limit": 1000000 + "knowledge": "2024-04", + "limit": 1000000, + "max_output": 32000, + "released": "2024-01-25" }, "qwen/qwen-turbo": { "cost": [ @@ -60285,7 +78924,10 @@ 0.0086, 0.0 ], - "limit": 128000 + "knowledge": "2024-04", + "limit": 128000, + "max_output": 16000, + "released": "2024-11-01" }, "qwen/qwen-vl-max": { "cost": [ @@ -60294,7 +78936,10 @@ 0.023, 0.0 ], - "limit": 128000 + "knowledge": "2024-04", + "limit": 128000, + "max_output": 8000, + "released": "2024-04-08" }, "qwen/qwen3-coder-flash": { "cost": [ @@ -60303,7 +78948,10 @@ 0.06, 0.27 ], - "limit": 1000000 + "knowledge": "2025-04", + "limit": 1000000, + "max_output": 64000, + "released": "2025-07-28" }, "qwen/qwen3-coder-next": { "cost": [ @@ -60312,7 +78960,11 @@ 0.0, 0.0 ], - "limit": 256000 + "knowledge": "2025-09", + "limit": 256000, + "max_output": 64000, + "open": true, + "released": "2026-02-03" }, "qwen/qwen3-coder-plus": { "cost": [ @@ -60321,7 +78973,10 @@ 0.2, 1.0 ], - "limit": 1000000 + "knowledge": "2025-04", + "limit": 1000000, + "max_output": 64000, + "released": "2025-07-23" }, "qwen/qwen3-max": { "cost": [ @@ -60330,7 +78985,10 @@ 0.072, 0.0 ], - "limit": 256000 + "knowledge": "2025-04", + "limit": 256000, + "max_output": 64000, + "released": "2025-09-23" }, "qwen/qwen3.5-122b-a10b": { "cost": [ @@ -60339,7 +78997,10 @@ 0.29, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 64000, + "open": true, + "released": "2026-02-23" }, "qwen/qwen3.5-27b": { "cost": [ @@ -60348,7 +79009,10 @@ 0.29, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 64000, + "open": true, + "released": "2026-02-23" }, "qwen/qwen3.5-35b-a3b": { "cost": [ @@ -60357,7 +79021,10 @@ 0.29, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 64000, + "open": true, + "released": "2026-02-23" }, "qwen/qwen3.5-397b-a17b": { "cost": [ @@ -60366,7 +79033,10 @@ 0.55, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 64000, + "open": true, + "released": "2026-02-15" }, "qwen/qwen3.5-flash": { "cost": [ @@ -60375,7 +79045,9 @@ 0.01, 0.125 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 64000, + "released": "2026-02-23" }, "qwen/qwen3.5-plus": { "cost": [ @@ -60384,7 +79056,10 @@ 0.04, 0.4 ], - "limit": 1000000 + "knowledge": "2025-04", + "limit": 1000000, + "max_output": 64000, + "released": "2026-02-16" }, "qwen/qwen3.6-27b": { "cost": [ @@ -60393,7 +79068,10 @@ 0.0, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 64000, + "open": true, + "released": "2026-04-22" }, "qwen/qwen3.6-flash": { "cost": [ @@ -60402,7 +79080,9 @@ 0.025, 0.31 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 64000, + "released": "2026-04-27" }, "qwen/qwen3.6-max-preview": { "cost": [ @@ -60411,7 +79091,10 @@ 0.2, 1.17 ], - "limit": 256000 + "knowledge": "2025-04", + "limit": 256000, + "max_output": 64000, + "released": "2026-04-20" }, "qwen/qwen3.6-plus": { "cost": [ @@ -60420,7 +79103,10 @@ 0.05, 0.625 ], - "limit": 1000000 + "knowledge": "2025-04", + "limit": 1000000, + "max_output": 64000, + "released": "2026-04-02" }, "qwen/qwen3.7-max": { "cost": [ @@ -60429,7 +79115,9 @@ 0.17, 2.14 ], - "limit": 1064000 + "limit": 1064000, + "max_output": 64000, + "released": "2026-05-21" }, "qwen/qwen3.7-plus": { "cost": [ @@ -60438,7 +79126,10 @@ 0.08, 0.5 ], - "limit": 1064000 + "knowledge": "2025-04", + "limit": 1064000, + "max_output": 64000, + "released": "2026-06-02" }, "qwen/qwen3.8-27b": { "cost": [ @@ -60447,7 +79138,10 @@ 0.043, 0.63 ], - "limit": 1131072 + "limit": 1131072, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "qwen/qwen3.8-flash": { "cost": [ @@ -60456,7 +79150,9 @@ 0.011, 0.14 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-08-26" }, "qwen/qwen3.8-max": { "cost": [ @@ -60465,7 +79161,9 @@ 0.17, 2.14 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-08-03" }, "qwen/qwen3.8-max-0902": { "cost": [ @@ -60474,7 +79172,9 @@ 0.17, 2.14 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-09-02" }, "volcengine/doubao-seed-2.0-code": { "cost": [ @@ -60483,7 +79183,9 @@ 0.14, 0.0024 ], - "limit": 256000 + "limit": 256000, + "max_output": 128000, + "released": "2026-02-14" }, "volcengine/doubao-seed-2.0-lite": { "cost": [ @@ -60492,7 +79194,9 @@ 0.03, 0.0024 ], - "limit": 256000 + "limit": 256000, + "max_output": 32000, + "released": "2026-02-14" }, "volcengine/doubao-seed-2.0-mini": { "cost": [ @@ -60501,7 +79205,9 @@ 0.02, 0.0024 ], - "limit": 256000 + "limit": 256000, + "max_output": 32000, + "released": "2026-02-14" }, "volcengine/doubao-seed-2.0-pro": { "cost": [ @@ -60510,7 +79216,9 @@ 0.14, 0.0024 ], - "limit": 256000 + "limit": 256000, + "max_output": 128000, + "released": "2026-02-14" }, "volcengine/doubao-seed-2.1-pro": { "cost": [ @@ -60519,7 +79227,9 @@ 0.1416, 0.002 ], - "limit": 256000 + "limit": 256000, + "max_output": 256000, + "released": "2026-06-23" }, "volcengine/doubao-seed-2.1-turbo": { "cost": [ @@ -60528,7 +79238,9 @@ 0.068, 0.0019 ], - "limit": 256000 + "limit": 256000, + "max_output": 256000, + "released": "2026-06-23" }, "volcengine/doubao-seed-character": { "cost": [ @@ -60537,7 +79249,9 @@ 0.024, 0.0025 ], - "limit": 256000 + "limit": 256000, + "max_output": 256000, + "released": "2026-06-23" }, "volcengine/doubao-seed-evolving": { "cost": [ @@ -60546,7 +79260,9 @@ 0.177, 0.0025 ], - "limit": 256000 + "limit": 256000, + "max_output": 256000, + "released": "2026-06-23" }, "x-ai/grok-4.1-fast": { "cost": [ @@ -60555,7 +79271,9 @@ 0.05, 0.0 ], - "limit": 2000000 + "limit": 2000000, + "max_output": 30000, + "released": "2025-11-19" }, "x-ai/grok-4.20": { "cost": [ @@ -60564,7 +79282,9 @@ 0.4, 0.0 ], - "limit": 2000000 + "limit": 2000000, + "max_output": 128000, + "released": "2026-03-09" }, "x-ai/grok-4.3": { "cost": [ @@ -60573,7 +79293,9 @@ 0.2, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 30000, + "released": "2026-04-17" }, "x-ai/grok-4.5": { "cost": [ @@ -60582,7 +79304,9 @@ 0.3, 0.0 ], - "limit": 500000 + "limit": 500000, + "max_output": 65536, + "released": "2026-07-08" }, "x-ai/grok-4.6": { "cost": [ @@ -60591,7 +79315,10 @@ 0.5, 0.0 ], - "limit": 500000 + "knowledge": "2026-02-01", + "limit": 500000, + "max_output": 65536, + "released": "2026-08-12" }, "x-ai/grok-4.7": { "cost": [ @@ -60600,7 +79327,10 @@ 0.5, 0.0 ], - "limit": 500000 + "knowledge": "2026-05", + "limit": 500000, + "max_output": 65536, + "released": "2026-09-21" }, "z-ai/glm-4.6": { "cost": [ @@ -60609,7 +79339,11 @@ 0.11, 0.0 ], - "limit": 204800 + "knowledge": "2025-04", + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-09-30" }, "z-ai/glm-4.7": { "cost": [ @@ -60618,7 +79352,11 @@ 0.11, 0.0 ], - "limit": 204800 + "knowledge": "2025-04", + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-12-22" }, "z-ai/glm-4.7-flashx": { "cost": [ @@ -60627,7 +79365,11 @@ 0.01, 0.0 ], - "limit": 200000 + "knowledge": "2025-04", + "limit": 200000, + "max_output": 128000, + "open": true, + "released": "2026-01-19" }, "z-ai/glm-5": { "cost": [ @@ -60636,7 +79378,10 @@ 0.2, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-02-12" }, "z-ai/glm-5-turbo": { "cost": [ @@ -60645,7 +79390,9 @@ 0.24, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 131072, + "released": "2026-03-16" }, "z-ai/glm-5.1": { "cost": [ @@ -60654,7 +79401,10 @@ 0.26, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 131072, + "open": true, + "released": "2026-04-07" }, "z-ai/glm-5.2": { "cost": [ @@ -60663,7 +79413,10 @@ 0.26, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "z-ai/glm-5.3": { "cost": [ @@ -60672,7 +79425,10 @@ 0.26, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "z-ai/glm-5.3-flash": { "cost": [ @@ -60681,7 +79437,10 @@ 0.03, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-26" }, "z-ai/glm-5.3-flashx": { "cost": [ @@ -60690,7 +79449,10 @@ 0.03, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-26" }, "z-ai/glm-5v-turbo": { "cost": [ @@ -60699,7 +79461,9 @@ 0.24, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 131072, + "released": "2026-04-01" } }, "name": "Ofox" @@ -60713,7 +79477,11 @@ 0.022, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-04-24" }, "deepseek-v4-pro:0813": { "cost": [ @@ -60722,7 +79490,10 @@ 0.022, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-08-13" }, "deepseek-v4.1-flash": { "cost": [ @@ -60731,7 +79502,11 @@ 0.003, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-09-10" }, "deepseek-v4.1-flash:1017": { "cost": [ @@ -60740,7 +79515,11 @@ 0.003, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-10-17" }, "gemma4:31b": { "cost": [ @@ -60749,7 +79528,11 @@ 0.05, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-02" }, "glm-5.2": { "cost": [ @@ -60758,7 +79541,10 @@ 0.26, 0.0 ], - "limit": 976000 + "limit": 976000, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "glm-5.3": { "cost": [ @@ -60767,7 +79553,10 @@ 0.26, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "glm-5.3-flash": { "cost": [ @@ -60776,7 +79565,10 @@ 0.03, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-26" }, "gpt-oss:120b": { "cost": [ @@ -60785,7 +79577,11 @@ 0.014, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "gpt-oss:20b": { "cost": [ @@ -60794,7 +79590,11 @@ 0.035, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "kimi-k2.6": { "cost": [ @@ -60803,7 +79603,11 @@ 0.16, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-20" }, "kimi-k2.7-code": { "cost": [ @@ -60812,7 +79616,11 @@ 0.19, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-06-12" }, "kimi-k3": { "cost": [ @@ -60821,7 +79629,10 @@ 0.3, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-16" }, "minimax-m2.7": { "cost": [ @@ -60830,7 +79641,10 @@ 0.06, 0.0 ], - "limit": 196608 + "limit": 196608, + "max_output": 196608, + "open": true, + "released": "2026-03-18" }, "minimax-m3": { "cost": [ @@ -60839,7 +79653,11 @@ 0.12, 0.0 ], - "limit": 512000 + "knowledge": "2025-01", + "limit": 512000, + "max_output": 131072, + "open": true, + "released": "2026-06-01" }, "minimax-m3.1-flash": { "cost": [ @@ -60848,7 +79666,9 @@ 0.015, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 512000, + "released": "2026-10-19" }, "mistral-large-3:675b": { "cost": [ @@ -60857,7 +79677,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2024-11", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2025-12-02" }, "mistral-large-4": { "cost": [ @@ -60866,7 +79690,9 @@ 0.07, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 262144, + "released": "2026-10-06" }, "muse-spark-open": { "cost": [ @@ -60875,7 +79701,11 @@ 0.15, 0.0 ], - "limit": 1048576 + "knowledge": "2026-01-04", + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-10-15" }, "nemotron-3-nano:30b": { "cost": [ @@ -60884,7 +79714,11 @@ 0.0, 0.0 ], - "limit": 1048576 + "knowledge": "2025-06-25", + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2025-12-15" }, "nemotron-3-super": { "cost": [ @@ -60893,7 +79727,11 @@ 0.015, 0.0 ], - "limit": 262144 + "knowledge": "2025-06", + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-03-11" }, "nemotron-3-ultra": { "cost": [ @@ -60902,7 +79740,11 @@ 0.1, 0.0 ], - "limit": 262144 + "knowledge": "2025-09", + "limit": 262144, + "max_output": 128000, + "open": true, + "released": "2026-06-04" } }, "name": "Ollama Cloud" @@ -60916,7 +79758,10 @@ 0.0, 0.0 ], + "knowledge": "2021-09-01", "limit": 16385, + "max_output": 4096, + "released": "2023-03-01", "status": "deprecated" }, "gpt-4": { @@ -60926,7 +79771,10 @@ 0.0, 0.0 ], + "knowledge": "2023-11", "limit": 8192, + "max_output": 8192, + "released": "2023-11-06", "status": "deprecated" }, "gpt-4-turbo": { @@ -60936,7 +79784,10 @@ 0.0, 0.0 ], + "knowledge": "2023-12", "limit": 128000, + "max_output": 4096, + "released": "2023-11-06", "status": "deprecated" }, "gpt-4.1": { @@ -60946,7 +79797,10 @@ 0.5, 0.0 ], - "limit": 1047576 + "knowledge": "2024-04", + "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14" }, "gpt-4.1-fast": { "cost": [ @@ -60955,7 +79809,10 @@ 0.875, 0.0 ], - "limit": 1047576 + "knowledge": "2024-04", + "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14" }, "gpt-4.1-mini": { "cost": [ @@ -60964,7 +79821,10 @@ 0.1, 0.0 ], - "limit": 1047576 + "knowledge": "2024-04", + "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14" }, "gpt-4.1-mini-fast": { "cost": [ @@ -60973,7 +79833,10 @@ 0.175, 0.0 ], - "limit": 1047576 + "knowledge": "2024-04", + "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14" }, "gpt-4.1-nano": { "cost": [ @@ -60982,7 +79845,10 @@ 0.025, 0.0 ], + "knowledge": "2024-04", "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14", "status": "deprecated" }, "gpt-4.1-nano-fast": { @@ -60992,7 +79858,10 @@ 0.05, 0.0 ], + "knowledge": "2024-04", "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14", "status": "deprecated" }, "gpt-4o": { @@ -61002,7 +79871,10 @@ 1.25, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-05-13" }, "gpt-4o-2024-05-13": { "cost": [ @@ -61011,7 +79883,10 @@ 0.0, 0.0 ], + "knowledge": "2023-09", "limit": 128000, + "max_output": 4096, + "released": "2024-05-13", "status": "deprecated" }, "gpt-4o-2024-05-13-fast": { @@ -61021,7 +79896,10 @@ 0.0, 0.0 ], + "knowledge": "2023-09", "limit": 128000, + "max_output": 4096, + "released": "2024-05-13", "status": "deprecated" }, "gpt-4o-2024-08-06": { @@ -61031,7 +79909,10 @@ 1.25, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-08-06" }, "gpt-4o-2024-11-20": { "cost": [ @@ -61040,7 +79921,10 @@ 1.25, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-11-20" }, "gpt-4o-fast": { "cost": [ @@ -61049,7 +79933,10 @@ 2.125, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-05-13" }, "gpt-4o-mini": { "cost": [ @@ -61058,7 +79945,10 @@ 0.075, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-07-18" }, "gpt-4o-mini-fast": { "cost": [ @@ -61067,7 +79957,10 @@ 0.125, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-07-18" }, "gpt-5": { "cost": [ @@ -61076,7 +79969,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "gpt-5-fast": { "cost": [ @@ -61085,7 +79981,10 @@ 0.25, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "gpt-5-flex": { "cost": [ @@ -61094,7 +79993,10 @@ 0.0625, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "gpt-5-mini": { "cost": [ @@ -61103,7 +80005,10 @@ 0.025, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "gpt-5-mini-fast": { "cost": [ @@ -61112,7 +80017,10 @@ 0.045, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "gpt-5-mini-flex": { "cost": [ @@ -61121,7 +80029,10 @@ 0.0125, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "gpt-5-nano": { "cost": [ @@ -61130,7 +80041,10 @@ 0.005, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "gpt-5-nano-flex": { "cost": [ @@ -61139,7 +80053,10 @@ 0.0025, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "gpt-5-pro": { "cost": [ @@ -61148,7 +80065,10 @@ 0.0, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 272000, + "released": "2025-10-06" }, "gpt-5.1": { "cost": [ @@ -61157,7 +80077,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "gpt-5.1-fast": { "cost": [ @@ -61166,7 +80089,10 @@ 0.25, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "gpt-5.1-flex": { "cost": [ @@ -61175,7 +80101,10 @@ 0.0625, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "gpt-5.2": { "cost": [ @@ -61184,7 +80113,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "gpt-5.2-fast": { "cost": [ @@ -61193,7 +80125,10 @@ 0.35, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "gpt-5.2-flex": { "cost": [ @@ -61202,7 +80137,10 @@ 0.0875, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "gpt-5.2-pro": { "cost": [ @@ -61211,7 +80149,10 @@ 0.0, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "gpt-5.3-codex": { "cost": [ @@ -61220,7 +80161,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-02-05" }, "gpt-5.3-codex-fast": { "cost": [ @@ -61229,7 +80173,10 @@ 0.35, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-02-05" }, "gpt-5.3-codex-spark": { "cost": [ @@ -61238,7 +80185,10 @@ 0.175, 0.0 ], - "limit": 128000 + "knowledge": "2025-08-31", + "limit": 128000, + "max_output": 32000, + "released": "2026-02-05" }, "gpt-5.4": { "cost": [ @@ -61247,7 +80197,10 @@ 0.25, 0.0 ], + "knowledge": "2025-08-31", "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05", "tiers": [ { "cost": [ @@ -61270,7 +80223,10 @@ 0.5, 0.0 ], - "limit": 1050000 + "knowledge": "2025-08-31", + "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05" }, "gpt-5.4-mini": { "cost": [ @@ -61279,7 +80235,10 @@ 0.075, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "gpt-5.4-mini-fast": { "cost": [ @@ -61288,7 +80247,10 @@ 0.15, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "gpt-5.4-mini-flex": { "cost": [ @@ -61297,7 +80259,10 @@ 0.0375, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "gpt-5.4-nano": { "cost": [ @@ -61306,7 +80271,10 @@ 0.02, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "gpt-5.4-nano-flex": { "cost": [ @@ -61315,7 +80283,10 @@ 0.01, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "gpt-5.4-pro": { "cost": [ @@ -61324,7 +80295,10 @@ 0.0, 0.0 ], + "knowledge": "2025-08-31", "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05", "tiers": [ { "cost": [ @@ -61347,7 +80321,10 @@ 0.5, 0.0 ], + "knowledge": "2025-12-01", "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23", "tiers": [ { "cost": [ @@ -61370,7 +80347,10 @@ 1.25, 0.0 ], - "limit": 1050000 + "knowledge": "2025-12-01", + "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23" }, "gpt-5.5-pro": { "cost": [ @@ -61379,7 +80359,10 @@ 0.0, 0.0 ], + "knowledge": "2025-12-01", "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23", "tiers": [ { "cost": [ @@ -61402,7 +80385,10 @@ 0.4, 5.0 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -61425,7 +80411,10 @@ 0.8, 10.0 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "gpt-5.6-luna": { "cost": [ @@ -61434,7 +80423,10 @@ 0.02, 0.25 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -61457,7 +80449,10 @@ 0.04, 0.5 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "gpt-5.6-sol": { "cost": [ @@ -61466,7 +80461,10 @@ 0.4, 5.0 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -61489,7 +80487,10 @@ 0.8, 10.0 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "gpt-5.6-terra": { "cost": [ @@ -61498,7 +80499,10 @@ 0.2, 2.5 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -61521,7 +80525,10 @@ 0.4, 5.0 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "gpt-6-astra": { "cost": [ @@ -61530,7 +80537,10 @@ 1.0, 12.5 ], + "knowledge": "2026-04-30", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-04", "tiers": [ { "cost": [ @@ -61553,7 +80563,10 @@ 2.0, 25.0 ], - "limit": 1050000 + "knowledge": "2026-04-30", + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-04" }, "gpt-6-astra-ultrafast": { "cost": [ @@ -61562,7 +80575,10 @@ 6.0, 75.0 ], - "limit": 1050000 + "knowledge": "2026-04-30", + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-04" }, "gpt-6-luna": { "cost": [ @@ -61571,7 +80587,10 @@ 0.01, 0.125 ], + "knowledge": "2026-05-18", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -61594,7 +80613,10 @@ 0.02, 0.25 ], - "limit": 1050000 + "knowledge": "2026-05-18", + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22" }, "gpt-6-sol": { "cost": [ @@ -61603,7 +80625,10 @@ 0.2, 2.5 ], + "knowledge": "2026-04-20", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -61626,7 +80651,10 @@ 0.4, 5.0 ], - "limit": 1050000 + "knowledge": "2026-04-20", + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22" }, "gpt-6.1-sol": { "cost": [ @@ -61635,7 +80663,10 @@ 0.1, 2.5 ], + "knowledge": "2026-04-30", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-29", "tiers": [ { "cost": [ @@ -61658,7 +80689,10 @@ 0.2, 5.0 ], - "limit": 1050000 + "knowledge": "2026-04-30", + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-29" }, "gpt-6.1-sol-ultrafast": { "cost": [ @@ -61667,7 +80701,48 @@ 0.6, 15.0 ], - "limit": 1050000 + "knowledge": "2026-04-30", + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-29" + }, + "gpt-6.1-terra": { + "cost": [ + 1.0, + 5.0, + 0.05, + 1.25 + ], + "knowledge": "2026-06-01", + "limit": 1050000, + "max_output": 128000, + "released": "2026-10-26", + "tiers": [ + { + "cost": [ + 2.0, + 7.5, + 0.1, + 2.5 + ], + "tier": { + "size": 272000, + "type": "context" + } + } + ] + }, + "gpt-6.1-terra-fast": { + "cost": [ + 2.0, + 10.0, + 0.1, + 2.5 + ], + "knowledge": "2026-06-01", + "limit": 1050000, + "max_output": 128000, + "released": "2026-10-26" }, "gpt-daybreak-blue-latest": { "cost": [ @@ -61676,7 +80751,10 @@ 0.4, 5.0 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-08-07", "tiers": [ { "cost": [ @@ -61699,7 +80777,10 @@ 1.25, 15.625 ], - "limit": 400000 + "knowledge": "2026-02-16", + "limit": 400000, + "max_output": 128000, + "released": "2026-08-07" }, "gpt-image-2": { "cost": [ @@ -61707,7 +80788,9 @@ 30.0, 1.25, 0.0 - ] + ], + "released": "2026-04-21", + "type": "image" }, "gpt-realtime-2.1": { "cost": [ @@ -61716,7 +80799,11 @@ 0.4, 0.0 ], - "limit": 128000 + "knowledge": "2024-09-30", + "limit": 128000, + "max_output": 32000, + "released": "2026-07-06", + "type": "realtime" }, "o1": { "cost": [ @@ -61725,7 +80812,10 @@ 7.5, 0.0 ], + "knowledge": "2023-09", "limit": 200000, + "max_output": 100000, + "released": "2024-12-05", "status": "deprecated" }, "o1-pro": { @@ -61735,7 +80825,10 @@ 0.0, 0.0 ], + "knowledge": "2023-09", "limit": 200000, + "max_output": 100000, + "released": "2025-03-19", "status": "deprecated" }, "o3": { @@ -61745,7 +80838,10 @@ 0.5, 0.0 ], - "limit": 200000 + "knowledge": "2024-05", + "limit": 200000, + "max_output": 100000, + "released": "2025-04-16" }, "o3-fast": { "cost": [ @@ -61754,7 +80850,10 @@ 0.875, 0.0 ], - "limit": 200000 + "knowledge": "2024-05", + "limit": 200000, + "max_output": 100000, + "released": "2025-04-16" }, "o3-flex": { "cost": [ @@ -61763,7 +80862,10 @@ 0.25, 0.0 ], - "limit": 200000 + "knowledge": "2024-05", + "limit": 200000, + "max_output": 100000, + "released": "2025-04-16" }, "o3-mini": { "cost": [ @@ -61772,7 +80874,10 @@ 0.55, 0.0 ], + "knowledge": "2024-05", "limit": 200000, + "max_output": 100000, + "released": "2024-12-20", "status": "deprecated" }, "o3-pro": { @@ -61782,7 +80887,10 @@ 0.0, 0.0 ], - "limit": 200000 + "knowledge": "2024-05", + "limit": 200000, + "max_output": 100000, + "released": "2025-06-10" }, "o4-mini": { "cost": [ @@ -61791,7 +80899,10 @@ 0.275, 0.0 ], + "knowledge": "2024-05", "limit": 200000, + "max_output": 100000, + "released": "2025-04-16", "status": "deprecated" }, "o4-mini-fast": { @@ -61801,7 +80912,10 @@ 0.5, 0.0 ], + "knowledge": "2024-05", "limit": 200000, + "max_output": 100000, + "released": "2025-04-16", "status": "deprecated" }, "o4-mini-flex": { @@ -61811,7 +80925,10 @@ 0.1375, 0.0 ], + "knowledge": "2024-05", "limit": 200000, + "max_output": 100000, + "released": "2025-04-16", "status": "deprecated" }, "text-embedding-3-large": { @@ -61821,7 +80938,11 @@ 0.0, 0.0 ], - "limit": 8191 + "knowledge": "2024-01", + "limit": 8191, + "max_output": 3072, + "released": "2024-01-25", + "type": "embedding" }, "text-embedding-3-small": { "cost": [ @@ -61830,7 +80951,11 @@ 0.0, 0.0 ], - "limit": 8191 + "knowledge": "2024-01", + "limit": 8191, + "max_output": 1536, + "released": "2024-01-25", + "type": "embedding" }, "text-embedding-ada-002": { "cost": [ @@ -61839,7 +80964,11 @@ 0.0, 0.0 ], - "limit": 8192 + "knowledge": "2022-12", + "limit": 8192, + "max_output": 1536, + "released": "2022-12-15", + "type": "embedding" } }, "name": "OpenAI" @@ -61853,7 +80982,11 @@ 0.0, 0.0 ], - "limit": 1048576 + "knowledge": "2026-06-30", + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-10-05" }, "big-pickle": { "cost": [ @@ -61862,7 +80995,10 @@ 0.0, 0.0 ], - "limit": 200000 + "knowledge": "2025-01", + "limit": 200000, + "max_output": 32000, + "released": "2025-10-17" }, "cat-jam-free": { "cost": [ @@ -61872,6 +81008,8 @@ 0.0 ], "limit": 1048576, + "max_output": 131072, + "released": "2026-10-12", "status": "deprecated" }, "claude-3-5-haiku": { @@ -61881,7 +81019,10 @@ 0.08, 1.0 ], + "knowledge": "2024-07-31", "limit": 200000, + "max_output": 8192, + "released": "2024-10-22", "status": "deprecated" }, "claude-fable-5": { @@ -61891,7 +81032,10 @@ 1.0, 12.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-09" }, "claude-fable-5-1": { "cost": [ @@ -61900,7 +81044,10 @@ 0.25, 12.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-01" }, "claude-haiku-4-5": { "cost": [ @@ -61909,7 +81056,10 @@ 0.1, 1.25 ], - "limit": 200000 + "knowledge": "2025-02-28", + "limit": 200000, + "max_output": 64000, + "released": "2025-10-15" }, "claude-haiku-5-5": { "cost": [ @@ -61918,7 +81068,10 @@ 0.01, 0.125 ], + "knowledge": "2026-06", "limit": 1000000, + "max_output": 128000, + "released": "2026-10-07", "tiers": [ { "cost": [ @@ -61941,7 +81094,10 @@ 1.5, 18.75 ], + "knowledge": "2025-03-31", "limit": 200000, + "max_output": 32000, + "released": "2025-08-05", "status": "deprecated" }, "claude-opus-4-5": { @@ -61951,7 +81107,10 @@ 0.5, 6.25 ], - "limit": 200000 + "knowledge": "2025-05", + "limit": 200000, + "max_output": 64000, + "released": "2025-11-24" }, "claude-opus-4-6": { "cost": [ @@ -61960,7 +81119,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2025-05-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-05" }, "claude-opus-4-7": { "cost": [ @@ -61969,7 +81131,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-16" }, "claude-opus-4-8": { "cost": [ @@ -61978,7 +81143,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-28" }, "claude-opus-5": { "cost": [ @@ -61987,7 +81155,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-05", + "limit": 1000000, + "max_output": 128000, + "released": "2026-07-24" }, "claude-opus-5-5": { "cost": [ @@ -61996,7 +81167,10 @@ 0.2, 5.0 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-22" }, "claude-sonnet-4": { "cost": [ @@ -62005,7 +81179,10 @@ 0.3, 3.75 ], + "knowledge": "2025-03-31", "limit": 1000000, + "max_output": 64000, + "released": "2025-05-22", "status": "deprecated", "tiers": [ { @@ -62029,7 +81206,10 @@ 0.3, 3.75 ], + "knowledge": "2025-07-31", "limit": 1000000, + "max_output": 64000, + "released": "2025-09-29", "tiers": [ { "cost": [ @@ -62052,7 +81232,10 @@ 0.3, 3.75 ], - "limit": 1000000 + "knowledge": "2025-08-31", + "limit": 1000000, + "max_output": 64000, + "released": "2026-02-17" }, "claude-sonnet-5": { "cost": [ @@ -62061,7 +81244,10 @@ 0.2, 2.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-30" }, "claude-sonnet-5-5": { "cost": [ @@ -62070,7 +81256,10 @@ 0.2, 2.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-28" }, "deepseek-v4-flash": { "cost": [ @@ -62079,7 +81268,12 @@ 0.028, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-07-31", + "status": "deprecated" }, "deepseek-v4-flash-free": { "cost": [ @@ -62088,7 +81282,11 @@ 0.0, 0.0 ], + "knowledge": "2025-05", "limit": 200000, + "max_output": 128000, + "open": true, + "released": "2026-07-31", "status": "deprecated" }, "deepseek-v4-flash-vision-exp": { @@ -62099,6 +81297,9 @@ 0.0 ], "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-08-21", "status": "deprecated" }, "deepseek-v4-pro": { @@ -62108,7 +81309,11 @@ 0.145, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "deepseek-v4.1-flash": { "cost": [ @@ -62117,7 +81322,11 @@ 0.006, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-09-10" }, "deepseek-v4.1-flash-free": { "cost": [ @@ -62126,7 +81335,11 @@ 0.0, 0.0 ], - "limit": 200000 + "knowledge": "2025-05", + "limit": 200000, + "max_output": 32000, + "open": true, + "released": "2026-09-10" }, "exo-free": { "cost": [ @@ -62136,6 +81349,8 @@ 0.0 ], "limit": 1048576, + "max_output": 131072, + "released": "2026-10-06", "status": "deprecated" }, "fledge-alpha-free": { @@ -62146,6 +81361,8 @@ 0.0 ], "limit": 1048576, + "max_output": 131072, + "released": "2026-10-01", "status": "deprecated" }, "flint-40b-free": { @@ -62155,7 +81372,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2026-06", + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-10-21" }, "gemini-3-flash": { "cost": [ @@ -62164,7 +81385,10 @@ 0.05, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2025-12-17" }, "gemini-3-pro": { "cost": [ @@ -62173,7 +81397,10 @@ 0.2, 0.0 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2025-11-18", "status": "deprecated", "tiers": [ { @@ -62197,7 +81424,10 @@ 0.2, 0.0 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2026-02-19", "tiers": [ { "cost": [ @@ -62220,7 +81450,10 @@ 0.15, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-05-19" }, "gemini-3.5-flash-lite": { "cost": [ @@ -62229,7 +81462,10 @@ 0.03, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-07-21" }, "gemini-3.6-flash": { "cost": [ @@ -62238,7 +81474,10 @@ 0.15, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-07-21" }, "gemini-3.7-flash": { "cost": [ @@ -62247,7 +81486,10 @@ 0.15, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-08-13" }, "gemini-3.8-flash": { "cost": [ @@ -62256,7 +81498,9 @@ 0.15, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65536, + "released": "2026-09-02" }, "gemini-4-argon": { "cost": [ @@ -62265,7 +81509,10 @@ 0.1, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-10-13" }, "glm-4.6": { "cost": [ @@ -62274,7 +81521,11 @@ 0.1, 0.0 ], + "knowledge": "2025-04", "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-09-30", "status": "deprecated" }, "glm-4.7": { @@ -62284,7 +81535,11 @@ 0.1, 0.0 ], + "knowledge": "2025-04", "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-12-22", "status": "deprecated" }, "glm-4.7-free": { @@ -62294,7 +81549,11 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-12-22", "status": "deprecated" }, "glm-5": { @@ -62304,7 +81563,11 @@ 0.2, 0.0 ], - "limit": 204800 + "knowledge": "2025-04", + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-02-12" }, "glm-5-free": { "cost": [ @@ -62313,7 +81576,11 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-02-12", "status": "deprecated" }, "glm-5.1": { @@ -62323,7 +81590,11 @@ 0.26, 0.0 ], - "limit": 204800 + "knowledge": "2025-04", + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-04-07" }, "glm-5.2": { "cost": [ @@ -62332,7 +81603,10 @@ 0.26, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "glm-5.3": { "cost": [ @@ -62341,7 +81615,10 @@ 0.26, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "glm-5.3-flash": { "cost": [ @@ -62350,7 +81627,10 @@ 0.03, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-26" }, "glm-5.3-flash-free": { "cost": [ @@ -62359,7 +81639,10 @@ 0.0, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 32000, + "open": true, + "released": "2026-08-26" }, "gpt-5": { "cost": [ @@ -62368,7 +81651,10 @@ 0.107, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "gpt-5-codex": { "cost": [ @@ -62377,7 +81663,10 @@ 0.107, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-09-15" }, "gpt-5-nano": { "cost": [ @@ -62386,7 +81675,10 @@ 0.005, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "gpt-5.1": { "cost": [ @@ -62395,7 +81687,10 @@ 0.107, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "gpt-5.1-codex": { "cost": [ @@ -62404,7 +81699,10 @@ 0.107, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "gpt-5.1-codex-max": { "cost": [ @@ -62413,7 +81711,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "gpt-5.1-codex-mini": { "cost": [ @@ -62422,7 +81723,10 @@ 0.025, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "gpt-5.2": { "cost": [ @@ -62431,7 +81735,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "gpt-5.2-codex": { "cost": [ @@ -62440,7 +81747,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "gpt-5.3-codex": { "cost": [ @@ -62449,7 +81759,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-02-05" }, "gpt-5.3-codex-spark": { "cost": [ @@ -62458,7 +81771,10 @@ 0.175, 0.0 ], - "limit": 128000 + "knowledge": "2025-08-31", + "limit": 128000, + "max_output": 128000, + "released": "2026-02-05" }, "gpt-5.4": { "cost": [ @@ -62467,7 +81783,10 @@ 0.25, 0.0 ], + "knowledge": "2025-08-31", "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05", "tiers": [ { "cost": [ @@ -62490,7 +81809,10 @@ 0.075, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "gpt-5.4-nano": { "cost": [ @@ -62499,7 +81821,10 @@ 0.02, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "gpt-5.4-pro": { "cost": [ @@ -62508,7 +81833,10 @@ 30.0, 0.0 ], - "limit": 1050000 + "knowledge": "2025-08-31", + "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05" }, "gpt-5.5": { "cost": [ @@ -62517,7 +81845,10 @@ 0.5, 0.0 ], + "knowledge": "2025-12-01", "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23", "tiers": [ { "cost": [ @@ -62540,7 +81871,10 @@ 30.0, 0.0 ], - "limit": 1050000 + "knowledge": "2025-12-01", + "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23" }, "gpt-5.6-luna": { "cost": [ @@ -62549,7 +81883,10 @@ 0.02, 0.25 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -62572,7 +81909,10 @@ 0.4, 5.0 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -62595,7 +81935,10 @@ 0.2, 2.5 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -62618,7 +81961,10 @@ 1.0, 12.5 ], + "knowledge": "2026-04-30", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-04", "tiers": [ { "cost": [ @@ -62641,7 +81987,10 @@ 0.01, 0.125 ], + "knowledge": "2026-05-18", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -62664,7 +82013,10 @@ 0.2, 2.5 ], + "knowledge": "2026-04-20", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -62687,7 +82039,10 @@ 0.1, 2.5 ], + "knowledge": "2026-04-30", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-29", "tiers": [ { "cost": [ @@ -62711,6 +82066,8 @@ 0.0 ], "limit": 500000, + "max_output": 500000, + "released": "2026-07-08", "tiers": [ { "cost": [ @@ -62733,7 +82090,10 @@ 0.5, 0.0 ], + "knowledge": "2026-02-01", "limit": 500000, + "max_output": 500000, + "released": "2026-08-12", "tiers": [ { "cost": [ @@ -62756,7 +82116,10 @@ 0.5, 0.0 ], + "knowledge": "2026-05", "limit": 500000, + "max_output": 500000, + "released": "2026-09-21", "tiers": [ { "cost": [ @@ -62779,7 +82142,9 @@ 0.2, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 256000, + "released": "2026-04-16" }, "grok-code": { "cost": [ @@ -62789,6 +82154,8 @@ 0.0 ], "limit": 256000, + "max_output": 256000, + "released": "2025-09-02", "status": "deprecated" }, "hy3-free": { @@ -62799,6 +82166,9 @@ 0.0 ], "limit": 190000, + "max_output": 64000, + "open": true, + "released": "2026-07-06", "status": "deprecated" }, "hy3-preview-free": { @@ -62808,7 +82178,11 @@ 0.0, 0.0 ], + "knowledge": "2025-06", "limit": 256000, + "max_output": 64000, + "open": true, + "released": "2026-04-20", "status": "deprecated" }, "kimi-k2": { @@ -62818,7 +82192,11 @@ 0.4, 0.0 ], + "knowledge": "2024-10", "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2025-09-05", "status": "deprecated" }, "kimi-k2-thinking": { @@ -62828,7 +82206,11 @@ 0.4, 0.0 ], + "knowledge": "2024-08", "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2025-11-06", "status": "deprecated" }, "kimi-k2.5": { @@ -62838,7 +82220,11 @@ 0.1, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-01-27" }, "kimi-k2.5-free": { "cost": [ @@ -62847,7 +82233,11 @@ 0.0, 0.0 ], + "knowledge": "2025-01", "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-01-27", "status": "deprecated" }, "kimi-k2.6": { @@ -62857,7 +82247,11 @@ 0.16, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-04-20" }, "kimi-k2.7-code": { "cost": [ @@ -62866,16 +82260,23 @@ 0.19, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-06-12" }, "kimi-k3": { "cost": [ 3.0, 15.0, 0.3, - 0.0 + 3.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-16" }, "laguna-s-2.1-free": { "cost": [ @@ -62885,6 +82286,9 @@ 0.0 ], "limit": 256000, + "max_output": 32000, + "open": true, + "released": "2026-07-21", "status": "deprecated" }, "ling-2.6-flash-free": { @@ -62894,7 +82298,11 @@ 0.0, 0.0 ], + "knowledge": "2025-06", "limit": 262100, + "max_output": 32800, + "open": true, + "released": "2026-04-21", "status": "deprecated" }, "ling-3.0-flash-fin-free": { @@ -62905,6 +82313,9 @@ 0.0 ], "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-08-27", "status": "deprecated" }, "ling-3.0-flash-free": { @@ -62915,6 +82326,9 @@ 0.0 ], "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-07-23", "status": "deprecated" }, "ling-3.0-tiny-free": { @@ -62925,6 +82339,8 @@ 0.0 ], "limit": 262144, + "max_output": 32768, + "released": "2026-08-06", "status": "deprecated" }, "ling-3.1-flash-free": { @@ -62935,6 +82351,9 @@ 0.0 ], "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-09-29", "status": "deprecated" }, "ll-alpha-free": { @@ -62944,7 +82363,11 @@ 0.0, 0.0 ], + "knowledge": "2026-06", "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-10-15", "status": "deprecated" }, "longcat-2.0-free": { @@ -62955,6 +82378,9 @@ 0.0 ], "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-30", "status": "deprecated" }, "longcat-2.5-preview-free": { @@ -62965,6 +82391,8 @@ 0.0 ], "limit": 1000000, + "max_output": 131072, + "released": "2026-09-25", "status": "deprecated" }, "mimo-v2-flash-free": { @@ -62974,7 +82402,11 @@ 0.0, 0.0 ], + "knowledge": "2024-12-01", "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2025-12-16", "status": "deprecated" }, "mimo-v2-omni-free": { @@ -62984,7 +82416,10 @@ 0.0, 0.0 ], + "knowledge": "2024-12", "limit": 262144, + "max_output": 64000, + "released": "2026-03-18", "status": "deprecated" }, "mimo-v2-pro-free": { @@ -62994,7 +82429,10 @@ 0.0, 0.0 ], + "knowledge": "2024-12", "limit": 1048576, + "max_output": 64000, + "released": "2026-03-18", "status": "deprecated" }, "mimo-v2.5-free": { @@ -63004,7 +82442,11 @@ 0.0, 0.0 ], + "knowledge": "2024-12", "limit": 200000, + "max_output": 32000, + "open": true, + "released": "2026-04-22", "status": "deprecated" }, "mimo-v2.6-flash-free": { @@ -63014,7 +82456,10 @@ 0.0, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 32000, + "open": true, + "released": "2026-09-22" }, "minimax-m2.1": { "cost": [ @@ -63023,7 +82468,11 @@ 0.1, 0.0 ], + "knowledge": "2025-01", "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-12-23", "status": "deprecated" }, "minimax-m2.1-free": { @@ -63033,7 +82482,11 @@ 0.0, 0.0 ], + "knowledge": "2025-01", "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-12-23", "status": "deprecated" }, "minimax-m2.5": { @@ -63043,7 +82496,11 @@ 0.06, 0.0 ], - "limit": 204800 + "knowledge": "2025-01", + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-02-12" }, "minimax-m2.5-free": { "cost": [ @@ -63052,7 +82509,11 @@ 0.0, 0.0 ], + "knowledge": "2025-01", "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-02-12", "status": "deprecated" }, "minimax-m2.7": { @@ -63062,7 +82523,11 @@ 0.06, 0.0 ], - "limit": 204800 + "knowledge": "2025-01", + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-03-18" }, "minimax-m3": { "cost": [ @@ -63071,7 +82536,10 @@ 0.06, 0.0 ], - "limit": 512000 + "limit": 512000, + "max_output": 128000, + "open": true, + "released": "2026-06-01" }, "minimax-m3-free": { "cost": [ @@ -63080,7 +82548,11 @@ 0.0, 0.0 ], + "knowledge": "2025-01", "limit": 200000, + "max_output": 32000, + "open": true, + "released": "2026-06-01", "status": "deprecated" }, "minimax-m3.1-flash-free": { @@ -63091,6 +82563,8 @@ 0.0 ], "limit": 1000000, + "max_output": 512000, + "released": "2026-10-19", "status": "deprecated" }, "mistral-large-4": { @@ -63100,7 +82574,9 @@ 0.07, 0.0 ], - "limit": 524288 + "limit": 524288, + "max_output": 262144, + "released": "2026-10-06" }, "muse-spark-1.2": { "cost": [ @@ -63109,7 +82585,9 @@ 0.15, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-08-05" }, "muse-spark-1.2-contributor-free": { "cost": [ @@ -63119,6 +82597,8 @@ 0.0 ], "limit": 1048576, + "max_output": 131072, + "released": "2026-08-05", "status": "deprecated" }, "muse-spark-1.3": { @@ -63128,7 +82608,9 @@ 0.15, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-09-02" }, "muse-spark-1.3-contributor-free": { "cost": [ @@ -63138,6 +82620,8 @@ 0.0 ], "limit": 1048576, + "max_output": 131072, + "released": "2026-09-02", "status": "deprecated" }, "muse-wonder-1.0": { @@ -63147,7 +82631,9 @@ 0.2, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-10-12" }, "nemotron-3-super-free": { "cost": [ @@ -63156,7 +82642,11 @@ 0.0, 0.0 ], + "knowledge": "2025-06", "limit": 204800, + "max_output": 128000, + "open": true, + "released": "2026-03-11", "status": "deprecated" }, "nemotron-3-ultra-free": { @@ -63166,7 +82656,12 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-09", + "limit": 1000000, + "max_output": 128000, + "open": true, + "released": "2026-06-04", + "status": "deprecated" }, "nemotron-3.5-lightning-free": { "cost": [ @@ -63175,7 +82670,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-09", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-08-11" }, "nemotron-3.5-super-vl-free": { "cost": [ @@ -63184,7 +82683,10 @@ 0.0, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-10-15" }, "north-mini-code-free": { "cost": [ @@ -63193,7 +82695,11 @@ 0.0, 0.0 ], + "knowledge": "2025-09-23", "limit": 256000, + "max_output": 64000, + "open": true, + "released": "2026-06-09", "status": "deprecated" }, "qwen3-coder": { @@ -63203,7 +82709,11 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2025-07-22", "status": "deprecated" }, "qwen3.5-plus": { @@ -63213,7 +82723,10 @@ 0.02, 0.25 ], - "limit": 262144 + "knowledge": "2025-04", + "limit": 262144, + "max_output": 65536, + "released": "2026-02-16" }, "qwen3.6-plus": { "cost": [ @@ -63222,7 +82735,10 @@ 0.05, 0.625 ], - "limit": 262144 + "knowledge": "2025-04", + "limit": 262144, + "max_output": 65536, + "released": "2026-04-02" }, "qwen3.6-plus-free": { "cost": [ @@ -63231,7 +82747,10 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 262144, + "max_output": 65536, + "released": "2026-04-02", "status": "deprecated" }, "qwen3.8-flash": { @@ -63241,7 +82760,9 @@ 0.016, 0.2 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-08-26" }, "qwen3.8-max": { "cost": [ @@ -63250,7 +82771,9 @@ 0.25, 2.5 ], - "limit": 262144 + "limit": 262144, + "max_output": 131072, + "released": "2026-08-03" }, "ring-2.6-1t-free": { "cost": [ @@ -63259,7 +82782,11 @@ 0.0, 0.0 ], + "knowledge": "2025-06", "limit": 262000, + "max_output": 66000, + "open": true, + "released": "2026-05-08", "status": "deprecated" }, "space-bunny-free": { @@ -63270,6 +82797,8 @@ 0.0 ], "limit": 1048576, + "max_output": 524288, + "released": "2026-09-23", "status": "deprecated" }, "step-5-preview-free": { @@ -63280,6 +82809,9 @@ 0.0 ], "limit": 1000000, + "max_output": 65536, + "open": true, + "released": "2026-09-16", "status": "deprecated" }, "trinity-large-preview-free": { @@ -63289,7 +82821,11 @@ 0.0, 0.0 ], + "knowledge": "2025-06", "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2026-01-27", "status": "deprecated" }, "x-preview-f-free": { @@ -63300,6 +82836,8 @@ 0.0 ], "limit": 1000000, + "max_output": 131072, + "released": "2026-08-21", "status": "deprecated" } }, @@ -63314,7 +82852,11 @@ 0.0, 0.0 ], - "limit": 1048576 + "knowledge": "2026-06-30", + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-10-05" }, "cat-jam-free": { "cost": [ @@ -63324,6 +82866,8 @@ 0.0 ], "limit": 1048576, + "max_output": 131072, + "released": "2026-10-12", "status": "deprecated" }, "claude-haiku-5-5": { @@ -63333,7 +82877,10 @@ 0.01, 0.125 ], + "knowledge": "2026-06", "limit": 1000000, + "max_output": 128000, + "released": "2026-10-07", "tiers": [ { "cost": [ @@ -63356,7 +82903,11 @@ 0.022, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "deepseek-v4.1-flash": { "cost": [ @@ -63365,7 +82916,23 @@ 0.003, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-09-10" + }, + "gemini-4-argon": { + "cost": [ + 2.0, + 10.0, + 0.1, + 0.0 + ], + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-10-13" }, "gemini-4-argon-contributor": { "cost": [ @@ -63374,7 +82941,11 @@ 0.2, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-10-13", + "status": "deprecated" }, "glm-5.2": { "cost": [ @@ -63383,7 +82954,10 @@ 0.26, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "glm-5.3": { "cost": [ @@ -63392,7 +82966,10 @@ 0.26, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "glm-5.3-flash": { "cost": [ @@ -63401,7 +82978,10 @@ 0.03, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-26" }, "gpt-5.6-luna": { "cost": [ @@ -63410,7 +82990,10 @@ 0.02, 0.25 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -63433,7 +83016,10 @@ 0.01, 0.125 ], + "knowledge": "2026-05-18", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -63456,7 +83042,10 @@ 0.5, 0.0 ], + "knowledge": "2026-05", "limit": 500000, + "max_output": 500000, + "released": "2026-09-21", "tiers": [ { "cost": [ @@ -63479,7 +83068,10 @@ 0.035, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 128000, + "open": true, + "released": "2026-07-06" }, "hy4-preview": { "cost": [ @@ -63488,7 +83080,21 @@ 0.042, 0.0 ], - "limit": 1024000 + "limit": 1024000, + "max_output": 64000, + "open": true, + "released": "2026-08-28" + }, + "iceman-contributor-free": { + "cost": [ + 0.0, + 0.0, + 0.0, + 0.0 + ], + "limit": 262144, + "max_output": 131072, + "released": "2026-10-24" }, "kimi-k2.7-code": { "cost": [ @@ -63497,16 +83103,34 @@ 0.19, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-06-12" }, "kimi-k3": { "cost": [ 3.0, 15.0, 0.3, - 0.0 + 3.0 + ], + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-16" + }, + "kimi-k3.1-pro": { + "cost": [ + 2.0, + 10.0, + 0.2, + 2.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-10-23" }, "longcat-2.0": { "cost": [ @@ -63515,7 +83139,10 @@ 0.006, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-30" }, "longcat-2.5-preview-free": { "cost": [ @@ -63525,6 +83152,8 @@ 0.0 ], "limit": 1000000, + "max_output": 131072, + "released": "2026-09-25", "status": "deprecated" }, "mimo-v2.5": { @@ -63534,7 +83163,11 @@ 0.0028, 0.0 ], - "limit": 1000000 + "knowledge": "2024-12", + "limit": 1000000, + "max_output": 128000, + "open": true, + "released": "2026-04-22" }, "mimo-v2.5-pro": { "cost": [ @@ -63543,7 +83176,11 @@ 0.003625, 0.0 ], - "limit": 1048576 + "knowledge": "2024-12", + "limit": 1048576, + "max_output": 128000, + "open": true, + "released": "2026-04-22" }, "mimo-v2.6-flash": { "cost": [ @@ -63552,7 +83189,10 @@ 0.0028, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-09-22" }, "mimo-v2.6-pro": { "cost": [ @@ -63561,7 +83201,10 @@ 0.003625, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-09-22" }, "minimax-m2.7": { "cost": [ @@ -63570,7 +83213,11 @@ 0.06, 0.375 ], + "knowledge": "2025-01", "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-03-18", "status": "deprecated" }, "minimax-m3": { @@ -63580,7 +83227,11 @@ 0.06, 0.0 ], + "knowledge": "2025-01", "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-01", "tiers": [ { "cost": [ @@ -63603,7 +83254,9 @@ 0.015, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 512000, + "released": "2026-10-19" }, "minimax-m3.1-flash-free": { "cost": [ @@ -63613,6 +83266,8 @@ 0.0 ], "limit": 1000000, + "max_output": 512000, + "released": "2026-10-19", "status": "deprecated" }, "muse-spark-1.2-contributor": { @@ -63622,7 +83277,9 @@ 0.002, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-08-05" }, "muse-spark-1.3-contributor": { "cost": [ @@ -63631,7 +83288,9 @@ 0.002, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-09-02" }, "qwen3.7-plus": { "cost": [ @@ -63640,7 +83299,10 @@ 0.04, 0.5 ], + "knowledge": "2025-04", "limit": 1000000, + "max_output": 65536, + "released": "2026-06-02", "tiers": [ { "cost": [ @@ -63663,7 +83325,9 @@ 0.016, 0.2 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-08-26" }, "qwen3.8-max": { "cost": [ @@ -63672,7 +83336,9 @@ 0.25, 2.5 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-08-03" }, "space-bunny": { "cost": [ @@ -63682,6 +83348,8 @@ 0.0 ], "limit": 1048576, + "max_output": 524288, + "released": "2026-09-23", "status": "deprecated" }, "step-5-preview": { @@ -63691,7 +83359,10 @@ 0.1, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 65536, + "open": true, + "released": "2026-09-16" }, "step-5-preview-free": { "cost": [ @@ -63701,6 +83372,9 @@ 0.0 ], "limit": 1000000, + "max_output": 65536, + "open": true, + "released": "2026-09-16", "status": "deprecated" } }, @@ -63715,7 +83389,11 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-07-31" }, "moonshotai/kimi-k2.7-code": { "cost": [ @@ -63724,7 +83402,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-06-12" }, "openai/gpt-oss-120b": { "cost": [ @@ -63733,7 +83415,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05" } }, "name": "OpenReason" @@ -63747,7 +83433,9 @@ 0.2, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 32768, + "released": "2025-12-21" }, "aion-labs/aion-3.0": { "cost": [ @@ -63756,7 +83444,9 @@ 0.75, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 32768, + "released": "2026-05-05" }, "aion-labs/aion-3.0-mini": { "cost": [ @@ -63765,7 +83455,9 @@ 0.18, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 32768, + "released": "2026-05-14" }, "aion-labs/aion-3.5": { "cost": [ @@ -63774,7 +83466,9 @@ 0.75, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "released": "2026-09-23" }, "aion-labs/aion-3.5-mini": { "cost": [ @@ -63783,7 +83477,9 @@ 0.18, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "released": "2026-09-23" }, "aion-labs/aion-rp-llama-3.1-8b": { "cost": [ @@ -63792,7 +83488,11 @@ 0.0, 0.0 ], - "limit": 32768 + "knowledge": "2023-12-31", + "limit": 32768, + "max_output": 29491, + "open": true, + "released": "2025-02-04" }, "amazon/nova-2-lite-v1": { "cost": [ @@ -63801,7 +83501,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-10", + "limit": 1000000, + "max_output": 65535, + "released": "2025-12-02" }, "amazon/nova-lite-v1": { "cost": [ @@ -63810,7 +83513,10 @@ 0.0, 0.0 ], - "limit": 300000 + "knowledge": "2024-10-31", + "limit": 300000, + "max_output": 5120, + "released": "2024-12-05" }, "amazon/nova-micro-v1": { "cost": [ @@ -63819,7 +83525,10 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-10-31", + "limit": 128000, + "max_output": 5120, + "released": "2024-12-05" }, "amazon/nova-premier-v1": { "cost": [ @@ -63828,7 +83537,10 @@ 0.625, 0.0 ], + "knowledge": "2024-10", "limit": 1000000, + "max_output": 32000, + "released": "2025-04-30", "status": "deprecated" }, "amazon/nova-pro-v1": { @@ -63838,7 +83550,10 @@ 0.0, 0.0 ], - "limit": 300000 + "knowledge": "2024-10-31", + "limit": 300000, + "max_output": 5120, + "released": "2024-12-05" }, "anthracite-org/magnum-v4-72b": { "cost": [ @@ -63847,7 +83562,11 @@ 0.0, 0.0 ], - "limit": 32768 + "knowledge": "2024-06-30", + "limit": 32768, + "max_output": 4096, + "open": true, + "released": "2024-10-22" }, "anthropic/claude-fable-5": { "cost": [ @@ -63856,7 +83575,10 @@ 1.0, 12.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-09" }, "anthropic/claude-fable-5.1": { "cost": [ @@ -63865,7 +83587,10 @@ 0.25, 12.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-01" }, "anthropic/claude-haiku-4.5": { "cost": [ @@ -63874,7 +83599,10 @@ 0.1, 1.25 ], - "limit": 200000 + "knowledge": "2025-02-28", + "limit": 200000, + "max_output": 64000, + "released": "2025-10-15" }, "anthropic/claude-haiku-5.5": { "cost": [ @@ -63883,7 +83611,10 @@ 0.01, 0.125 ], + "knowledge": "2026-06", "limit": 1000000, + "max_output": 128000, + "released": "2026-10-07", "tiers": [ { "cost": [ @@ -63906,7 +83637,10 @@ 1.5, 18.75 ], - "limit": 200000 + "knowledge": "2025-03-31", + "limit": 200000, + "max_output": 32000, + "released": "2025-08-05" }, "anthropic/claude-opus-4.5": { "cost": [ @@ -63915,7 +83649,10 @@ 0.5, 6.25 ], - "limit": 200000 + "knowledge": "2025-05", + "limit": 200000, + "max_output": 64000, + "released": "2025-11-24" }, "anthropic/claude-opus-4.6": { "cost": [ @@ -63924,7 +83661,10 @@ 0.5, 6.25 ], + "knowledge": "2025-05-31", "limit": 1000000, + "max_output": 128000, + "released": "2026-02-05", "tiers": [ { "cost": [ @@ -63947,7 +83687,10 @@ 0.5, 6.25 ], + "knowledge": "2026-01-31", "limit": 1000000, + "max_output": 128000, + "released": "2026-04-16", "tiers": [ { "cost": [ @@ -63970,7 +83713,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-28" }, "anthropic/claude-opus-5": { "cost": [ @@ -63979,7 +83725,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-05", + "limit": 1000000, + "max_output": 128000, + "released": "2026-07-24" }, "anthropic/claude-opus-5.5": { "cost": [ @@ -63988,7 +83737,10 @@ 0.2, 5.0 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-22" }, "anthropic/claude-sonnet-4.5": { "cost": [ @@ -63997,7 +83749,10 @@ 0.3, 3.75 ], + "knowledge": "2025-07-31", "limit": 1000000, + "max_output": 64000, + "released": "2025-09-29", "tiers": [ { "cost": [ @@ -64020,7 +83775,10 @@ 0.3, 3.75 ], + "knowledge": "2025-08-31", "limit": 1000000, + "max_output": 128000, + "released": "2026-02-17", "tiers": [ { "cost": [ @@ -64043,7 +83801,10 @@ 0.2, 2.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-30" }, "anthropic/claude-sonnet-5.5": { "cost": [ @@ -64052,16 +83813,10 @@ 0.1, 2.5 ], - "limit": 1000000 - }, - "arcee-ai/trinity-large-thinking": { - "cost": [ - 0.25, - 0.8, - 0.06, - 0.0 - ], - "limit": 262144 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-28" }, "bytedance-seed/seed-1.6": { "cost": [ @@ -64071,6 +83826,8 @@ 0.0 ], "limit": 262144, + "max_output": 32768, + "released": "2025-10-15", "status": "deprecated", "tiers": [ { @@ -64095,6 +83852,8 @@ 0.0 ], "limit": 262144, + "max_output": 32768, + "released": "2025-08-28", "status": "deprecated", "tiers": [ { @@ -64118,7 +83877,9 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 235929, + "released": "2026-06-23" }, "bytedance-seed/seed-2.0-code": { "cost": [ @@ -64128,6 +83889,8 @@ 0.0 ], "limit": 262144, + "max_output": 131072, + "released": "2026-02-14", "status": "deprecated", "tiers": [ { @@ -64152,6 +83915,8 @@ 0.0 ], "limit": 262144, + "max_output": 131072, + "released": "2026-02-14", "tiers": [ { "cost": [ @@ -64175,6 +83940,8 @@ 0.0 ], "limit": 262144, + "max_output": 131072, + "released": "2026-02-14", "tiers": [ { "cost": [ @@ -64197,7 +83964,11 @@ 0.1, 0.0 ], - "limit": 128000 + "knowledge": "2025-01-31", + "limit": 128000, + "max_output": 2048, + "open": true, + "released": "2025-07-22" }, "cognitivecomputations/dolphin-mistral-24b-venice-edition": { "cost": [ @@ -64206,7 +83977,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-04-30", + "limit": 128000, + "max_output": 8192, + "open": true, + "released": "2025-07-09" }, "cohere/command-a": { "cost": [ @@ -64215,7 +83990,11 @@ 0.0, 0.0 ], - "limit": 256000 + "knowledge": "2024-08-31", + "limit": 256000, + "max_output": 8192, + "open": true, + "released": "2025-03-13" }, "cohere/command-a-plus": { "cost": [ @@ -64224,7 +84003,11 @@ 0.15, 0.0 ], - "limit": 192000 + "knowledge": "2025-04-01", + "limit": 192000, + "max_output": 64000, + "open": true, + "released": "2026-05-20" }, "cohere/command-r-08-2024": { "cost": [ @@ -64233,7 +84016,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-06-01", + "limit": 128000, + "max_output": 4000, + "open": true, + "released": "2024-08-30" }, "cohere/command-r-plus-08-2024": { "cost": [ @@ -64242,7 +84029,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-06-01", + "limit": 128000, + "max_output": 4000, + "open": true, + "released": "2024-08-30" }, "cohere/command-r7b-12-2024": { "cost": [ @@ -64251,7 +84042,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-06-01", + "limit": 128000, + "max_output": 4000, + "open": true, + "released": "2024-12-13" }, "cohere/north-mini-code:free": { "cost": [ @@ -64260,7 +84055,11 @@ 0.0, 0.0 ], - "limit": 256000 + "knowledge": "2025-09-23", + "limit": 256000, + "max_output": 64000, + "open": true, + "released": "2026-06-09" }, "deepseek/deepseek-chat": { "cost": [ @@ -64269,7 +84068,11 @@ 0.0, 0.0 ], - "limit": 163840 + "knowledge": "2025-09", + "limit": 163840, + "max_output": 16000, + "open": true, + "released": "2025-12-01" }, "deepseek/deepseek-chat-v3-0324": { "cost": [ @@ -64278,7 +84081,11 @@ 0.11, 0.0 ], - "limit": 163840 + "knowledge": "2024-07-31", + "limit": 163840, + "max_output": 115200, + "open": true, + "released": "2025-03-24" }, "deepseek/deepseek-chat-v3.1": { "cost": [ @@ -64287,7 +84094,11 @@ 0.13, 0.0 ], - "limit": 163840 + "knowledge": "2025-03-31", + "limit": 163840, + "max_output": 32768, + "open": true, + "released": "2025-08-21" }, "deepseek/deepseek-r1-0528": { "cost": [ @@ -64296,7 +84107,10 @@ 0.35, 0.0 ], - "limit": 163840 + "limit": 163840, + "max_output": 32768, + "open": true, + "released": "2025-05-28" }, "deepseek/deepseek-v3.1-terminus": { "cost": [ @@ -64305,7 +84119,11 @@ 0.0, 0.0 ], - "limit": 163840 + "knowledge": "2025-03-31", + "limit": 163840, + "max_output": 147456, + "open": true, + "released": "2025-09-22" }, "deepseek/deepseek-v3.2": { "cost": [ @@ -64314,7 +84132,11 @@ 0.028, 0.0 ], - "limit": 163840 + "knowledge": "2024-07", + "limit": 163840, + "max_output": 65536, + "open": true, + "released": "2025-12-01" }, "deepseek/deepseek-v3.2-exp": { "cost": [ @@ -64323,7 +84145,11 @@ 0.0, 0.0 ], - "limit": 163840 + "knowledge": "2025-07-31", + "limit": 163840, + "max_output": 147456, + "open": true, + "released": "2025-09-29" }, "deepseek/deepseek-v4-flash": { "cost": [ @@ -64332,16 +84158,24 @@ 0.0182, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 943717, + "open": true, + "released": "2026-04-24" }, "deepseek/deepseek-v4-flash-0731": { "cost": [ - 0.04708, - 0.14124, - 0.001498, + 0.119, + 0.238, + 0.0238, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 943718, + "open": true, + "released": "2026-07-31" }, "deepseek/deepseek-v4-flash-vision-exp": { "cost": [ @@ -64350,16 +84184,23 @@ 0.00686, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 262144, + "open": true, + "released": "2026-08-21" }, "deepseek/deepseek-v4-pro": { "cost": [ - 0.892272, - 1.784544, - 0.074356, + 0.888966, + 1.777932, + 0.074081, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "deepseek/deepseek-v4-pro-0813": { "cost": [ @@ -64368,16 +84209,23 @@ 0.022, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 393216, + "open": true, + "released": "2026-08-13" }, "deepseek/deepseek-v4.1-flash": { "cost": [ - 0.3, - 1.2, - 0.006, + 0.14, + 0.42, + 0.0042, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-09-10" }, "deepseek/deepseek-v4.1-flash-1017": { "cost": [ @@ -64386,7 +84234,11 @@ 0.003, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 393216, + "open": true, + "released": "2026-10-17" }, "dots-studio/dots-3-note-preview:free": { "cost": [ @@ -64396,6 +84248,8 @@ 0.0 ], "limit": 512000, + "max_output": 460800, + "released": "2026-08-14", "status": "deprecated" }, "elorian/glimpse": { @@ -64405,7 +84259,9 @@ 0.06, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 256000, + "released": "2026-10-17" }, "fireworks/ember-1": { "cost": [ @@ -64414,7 +84270,9 @@ 0.3, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 943718, + "released": "2026-09-22" }, "google/gemini-2.5-flash": { "cost": [ @@ -64423,7 +84281,10 @@ 0.03, 0.083333 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65535, + "released": "2025-06-17", "status": "deprecated" }, "google/gemini-2.5-flash-image": { @@ -64433,7 +84294,11 @@ 0.03, 0.083333 ], - "limit": 32768 + "knowledge": "2024-06", + "limit": 32768, + "max_output": 8192, + "released": "2025-08-26", + "type": "image" }, "google/gemini-2.5-flash-lite": { "cost": [ @@ -64442,7 +84307,10 @@ 0.01, 0.083333 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65535, + "released": "2025-06-17", "status": "deprecated" }, "google/gemini-2.5-pro": { @@ -64452,7 +84320,10 @@ 0.125, 0.375 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2025-06-17", "status": "deprecated", "tiers": [ { @@ -64476,7 +84347,10 @@ 0.125, 0.375 ], + "knowledge": "2025-01-31", "limit": 1048576, + "max_output": 65536, + "released": "2025-06-05", "tiers": [ { "cost": [ @@ -64499,7 +84373,10 @@ 0.05, 0.083333 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2025-12-17" }, "google/gemini-3-pro-image": { "cost": [ @@ -64508,7 +84385,11 @@ 0.2, 0.375 ], - "limit": 131072 + "knowledge": "2025-01", + "limit": 131072, + "max_output": 32768, + "released": "2026-05-28", + "type": "image" }, "google/gemini-3-pro-image-preview": { "cost": [ @@ -64517,7 +84398,11 @@ 0.2, 0.375 ], - "limit": 65536 + "knowledge": "2025-01", + "limit": 65536, + "max_output": 32768, + "released": "2025-11-20", + "type": "image" }, "google/gemini-3.1-flash-image": { "cost": [ @@ -64526,7 +84411,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2025-01", + "limit": 131072, + "max_output": 32768, + "released": "2026-05-28", + "type": "image" }, "google/gemini-3.1-flash-image-preview": { "cost": [ @@ -64535,7 +84424,11 @@ 0.0, 0.0 ], - "limit": 65536 + "knowledge": "2025-01", + "limit": 65536, + "max_output": 58982, + "released": "2026-02-26", + "type": "image" }, "google/gemini-3.1-flash-lite": { "cost": [ @@ -64544,7 +84437,10 @@ 0.025, 0.083333 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-05-07" }, "google/gemini-3.1-flash-lite-image": { "cost": [ @@ -64553,7 +84449,11 @@ 0.0, 0.0 ], - "limit": 65536 + "knowledge": "2025-01", + "limit": 65536, + "max_output": 58982, + "released": "2026-06-30", + "type": "image" }, "google/gemini-3.1-flash-lite-preview": { "cost": [ @@ -64562,7 +84462,10 @@ 0.025, 0.083333 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-03-03" }, "google/gemini-3.1-pro-preview": { "cost": [ @@ -64571,7 +84474,10 @@ 0.2, 0.375 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2026-02-19", "tiers": [ { "cost": [ @@ -64594,7 +84500,10 @@ 0.2, 0.375 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2026-02-19", "tiers": [ { "cost": [ @@ -64617,7 +84526,10 @@ 0.15, 0.083333 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-05-19" }, "google/gemini-3.5-flash-lite": { "cost": [ @@ -64626,7 +84538,10 @@ 0.03, 0.083333 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-07-21" }, "google/gemini-3.6-flash": { "cost": [ @@ -64635,7 +84550,10 @@ 0.075, 0.041667 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-07-21" }, "google/gemini-3.7-flash": { "cost": [ @@ -64644,7 +84562,10 @@ 0.075, 0.041667 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-08-13" }, "google/gemini-3.8-flash": { "cost": [ @@ -64653,7 +84574,9 @@ 0.0825, 0.041667 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65536, + "released": "2026-09-02" }, "google/gemini-4-argon": { "cost": [ @@ -64662,7 +84585,10 @@ 0.1, 0.1875 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 943718, + "released": "2026-10-13" }, "google/gemini-nano-banana-2.1": { "cost": [ @@ -64671,7 +84597,10 @@ 0.0, 0.0 ], - "limit": 65536 + "limit": 65536, + "max_output": 58982, + "released": "2026-10-06", + "type": "image" }, "google/gemma-2-27b-it": { "cost": [ @@ -64680,7 +84609,11 @@ 0.0, 0.0 ], - "limit": 8192 + "knowledge": "2024-06-30", + "limit": 8192, + "max_output": 2048, + "open": true, + "released": "2024-07-13" }, "google/gemma-3-12b-it": { "cost": [ @@ -64689,7 +84622,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-08", + "limit": 131072, + "max_output": 16384, + "open": true, + "released": "2025-03-12" }, "google/gemma-3-27b-it": { "cost": [ @@ -64698,16 +84635,24 @@ 0.04, 0.0 ], - "limit": 131072 + "knowledge": "2024-08", + "limit": 131072, + "max_output": 117964, + "open": true, + "released": "2025-03-12" }, "google/gemma-3-4b-it": { "cost": [ - 0.04, 0.05, - 0.02, + 0.1, + 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-08", + "limit": 131072, + "max_output": 16384, + "open": true, + "released": "2025-03-12" }, "google/gemma-4-26b-a4b-it": { "cost": [ @@ -64716,7 +84661,10 @@ 0.05, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 235929, + "open": true, + "released": "2026-04-02" }, "google/gemma-4-26b-a4b-it:free": { "cost": [ @@ -64725,7 +84673,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-04-02" }, "google/gemma-4-31b-it": { "cost": [ @@ -64734,7 +84685,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 16384, + "open": true, + "released": "2026-04-02" }, "google/gemma-4-31b-it:free": { "cost": [ @@ -64743,7 +84698,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-04-02" }, "google/lyria-3-clip-preview": { "cost": [ @@ -64752,7 +84711,9 @@ 0.0, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65536, + "released": "2026-03-25" }, "google/lyria-3-pro-preview": { "cost": [ @@ -64761,7 +84722,9 @@ 0.0, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65536, + "released": "2026-03-25" }, "gryphe/mythomax-l2-13b": { "cost": [ @@ -64770,16 +84733,10 @@ 0.0, 0.0 ], - "limit": 8192 - }, - "ibm-granite/granite-4.0-h-micro": { - "cost": [ - 0.017, - 0.112, - 0.0, - 0.0 - ], - "limit": 131000 + "limit": 8192, + "max_output": 3686, + "open": true, + "released": "2023-08-10" }, "ibm-granite/granite-4.2-8b": { "cost": [ @@ -64788,7 +84745,10 @@ 0.015, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 117964, + "open": true, + "released": "2026-08-25" }, "inception/mercury-2": { "cost": [ @@ -64797,7 +84757,9 @@ 0.025, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 50000, + "released": "2026-02-24" }, "inception/mercury-2.5": { "cost": [ @@ -64806,7 +84768,9 @@ 0.004, 0.0 ], - "limit": 260000 + "limit": 260000, + "max_output": 65536, + "released": "2026-09-08" }, "inception/mercury-3": { "cost": [ @@ -64815,7 +84779,9 @@ 0.01, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-10-16" }, "inclusionai/ling-3.0-flash": { "cost": [ @@ -64824,7 +84790,10 @@ 0.0042, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-07-23" }, "inclusionai/ling-3.0-flash-vl": { "cost": [ @@ -64833,7 +84802,10 @@ 0.012, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2026-09-10" }, "inclusionai/ling-3.1-flash": { "cost": [ @@ -64842,7 +84814,10 @@ 0.015, 0.0 ], - "limit": 262144 + "limit": 1000000, + "max_output": 262144, + "open": true, + "released": "2026-09-29" }, "inference-net/schematron-v2-small": { "cost": [ @@ -64851,7 +84826,9 @@ 0.05, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 4096, + "released": "2026-04-16" }, "inference-net/schematron-v2-turbo": { "cost": [ @@ -64860,7 +84837,21 @@ 0.03, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 8192, + "released": "2026-04-16" + }, + "liquid/lfm-2.5-2.6b": { + "cost": [ + 0.35, + 0.5, + 0.04, + 0.0 + ], + "limit": 128000, + "max_output": 8192, + "open": true, + "released": "2026-08-11" }, "liquid/lfm-2.5-2.6b:free": { "cost": [ @@ -64869,7 +84860,10 @@ 0.0, 0.0 ], - "limit": 65536 + "limit": 65536, + "max_output": 8192, + "open": true, + "released": "2026-08-11" }, "liquid/lfm-2.5-24b-a2b": { "cost": [ @@ -64878,7 +84872,10 @@ 0.025, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 8192, + "open": true, + "released": "2026-10-13" }, "mancer/weaver": { "cost": [ @@ -64887,7 +84884,10 @@ 0.0, 0.0 ], - "limit": 8000 + "knowledge": "2023-06-30", + "limit": 8000, + "max_output": 6000, + "released": "2023-08-02" }, "meituan/longcat-2.0": { "cost": [ @@ -64896,7 +84896,10 @@ 0.006, 0.0 ], - "limit": 1048756 + "limit": 1048756, + "max_output": 262144, + "open": true, + "released": "2026-06-30" }, "meta-llama/llama-3.1-70b-instruct": { "cost": [ @@ -64905,16 +84908,24 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2023-12", + "limit": 131072, + "max_output": 16384, + "open": true, + "released": "2024-07-23" }, "meta-llama/llama-3.1-8b-instruct": { "cost": [ - 0.05, - 0.08, - 0.025, + 0.02, + 0.04, + 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2023-12", + "limit": 131072, + "max_output": 16384, + "open": true, + "released": "2024-07-23" }, "meta-llama/llama-3.2-1b-instruct": { "cost": [ @@ -64923,16 +84934,24 @@ 0.0, 0.0 ], - "limit": 60000 + "knowledge": "2023-12", + "limit": 60000, + "max_output": 54000, + "open": true, + "released": "2024-09-25" }, "meta-llama/llama-3.2-3b-instruct": { "cost": [ - 0.0509, - 0.335, + 0.05, + 0.33, 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2023-12", + "limit": 131072, + "max_output": 117964, + "open": true, + "released": "2024-09-25" }, "meta-llama/llama-3.3-70b-instruct": { "cost": [ @@ -64941,7 +84960,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2023-12", + "limit": 131072, + "max_output": 16384, + "open": true, + "released": "2024-12-06" }, "meta-llama/llama-4-maverick": { "cost": [ @@ -64950,7 +84973,11 @@ 0.05, 0.0 ], - "limit": 524288 + "knowledge": "2024-08", + "limit": 524288, + "max_output": 16384, + "open": true, + "released": "2025-04-05" }, "meta-llama/llama-4-scout": { "cost": [ @@ -64959,7 +84986,11 @@ 0.0, 0.0 ], - "limit": 1310720 + "knowledge": "2024-08", + "limit": 1310720, + "max_output": 16384, + "open": true, + "released": "2025-04-05" }, "meta-llama/llama-guard-4-12b": { "cost": [ @@ -64968,7 +84999,10 @@ 0.0, 0.0 ], - "limit": 163840 + "limit": 163840, + "max_output": 16384, + "open": true, + "released": "2025-04-29" }, "meta/muse-glimmer-30b": { "cost": [ @@ -64977,7 +85011,11 @@ 0.04, 0.0 ], - "limit": 131072 + "knowledge": "2026-01-04", + "limit": 131072, + "max_output": 16384, + "open": true, + "released": "2026-08-10" }, "meta/muse-spark-1.1": { "cost": [ @@ -64986,7 +85024,9 @@ 0.15, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 943718, + "released": "2026-04-08" }, "meta/muse-spark-1.2": { "cost": [ @@ -64995,7 +85035,9 @@ 0.15, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 943718, + "released": "2026-08-05" }, "meta/muse-spark-1.2-contributor": { "cost": [ @@ -65004,7 +85046,9 @@ 0.002, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 943718, + "released": "2026-08-21" }, "meta/muse-spark-1.3": { "cost": [ @@ -65013,7 +85057,9 @@ 0.15, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 943718, + "released": "2026-09-02" }, "meta/muse-spark-1.3-contributor": { "cost": [ @@ -65022,7 +85068,9 @@ 0.002, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 943718, + "released": "2026-09-02" }, "meta/muse-spark-open": { "cost": [ @@ -65031,7 +85079,11 @@ 0.15, 0.0 ], - "limit": 1048576 + "knowledge": "2026-01-04", + "limit": 1048576, + "max_output": 943718, + "open": true, + "released": "2026-10-15" }, "meta/muse-wonder": { "cost": [ @@ -65040,7 +85092,9 @@ 0.2, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 943718, + "released": "2026-10-12" }, "microsoft/phi-4": { "cost": [ @@ -65049,7 +85103,11 @@ 0.0, 0.0 ], - "limit": 16384 + "knowledge": "2024-06-30", + "limit": 16384, + "max_output": 14745, + "open": true, + "released": "2025-01-10" }, "minimax/minimax-01": { "cost": [ @@ -65058,7 +85116,11 @@ 0.0, 0.0 ], - "limit": 1000192 + "knowledge": "2024-03-31", + "limit": 1000192, + "max_output": 40000, + "open": true, + "released": "2025-01-15" }, "minimax/minimax-m1": { "cost": [ @@ -65067,7 +85129,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2024-06-30", + "limit": 1000000, + "max_output": 40000, + "released": "2025-06-17" }, "minimax/minimax-m2": { "cost": [ @@ -65076,7 +85141,10 @@ 0.0, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-10-27" }, "minimax/minimax-m2-her": { "cost": [ @@ -65085,7 +85153,9 @@ 0.03, 0.0 ], - "limit": 65536 + "limit": 65536, + "max_output": 2048, + "released": "2026-01-23" }, "minimax/minimax-m2.1": { "cost": [ @@ -65094,16 +85164,22 @@ 0.03, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-12-23" }, "minimax/minimax-m2.5": { "cost": [ - 0.27, - 0.95, + 0.3, + 1.2, 0.03, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-02-12" }, "minimax/minimax-m2.7": { "cost": [ @@ -65112,7 +85188,10 @@ 0.06, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-03-18" }, "minimax/minimax-m3": { "cost": [ @@ -65121,7 +85200,10 @@ 0.06, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 512000, + "open": true, + "released": "2026-06-01" }, "minimax/minimax-m3.1-flash": { "cost": [ @@ -65130,7 +85212,9 @@ 0.015, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 524288, + "released": "2026-10-19" }, "mistralai/codestral-2508": { "cost": [ @@ -65139,7 +85223,9 @@ 0.03, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 204800, + "released": "2025-07-30" }, "mistralai/devstral-2512": { "cost": [ @@ -65148,7 +85234,11 @@ 0.04, 0.0 ], - "limit": 262144 + "knowledge": "2025-12", + "limit": 262144, + "max_output": 209715, + "open": true, + "released": "2025-12-09" }, "mistralai/ministral-14b-2512": { "cost": [ @@ -65157,7 +85247,10 @@ 0.02, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 209715, + "open": true, + "released": "2025-12-02" }, "mistralai/ministral-3b-2512": { "cost": [ @@ -65166,7 +85259,10 @@ 0.01, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 104857, + "open": true, + "released": "2025-12-02" }, "mistralai/ministral-8b-2512": { "cost": [ @@ -65175,7 +85271,10 @@ 0.015, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 209715, + "open": true, + "released": "2025-12-02" }, "mistralai/mistral-large": { "cost": [ @@ -65184,7 +85283,10 @@ 0.2, 0.0 ], - "limit": 128000 + "knowledge": "2024-11-30", + "limit": 128000, + "max_output": 102400, + "released": "2024-02-26" }, "mistralai/mistral-large-2407": { "cost": [ @@ -65193,7 +85295,11 @@ 0.2, 0.0 ], - "limit": 131072 + "knowledge": "2024-03-31", + "limit": 131072, + "max_output": 104857, + "open": true, + "released": "2024-07-24" }, "mistralai/mistral-large-2512": { "cost": [ @@ -65202,7 +85308,11 @@ 0.05, 0.0 ], - "limit": 262144 + "knowledge": "2024-11", + "limit": 262144, + "max_output": 209715, + "open": true, + "released": "2025-12-02" }, "mistralai/mistral-large-4-0": { "cost": [ @@ -65211,7 +85321,9 @@ 0.14, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 262144, + "released": "2026-10-06" }, "mistralai/mistral-medium-3": { "cost": [ @@ -65220,7 +85332,10 @@ 0.04, 0.0 ], - "limit": 131072 + "knowledge": "2025-03-31", + "limit": 131072, + "max_output": 104857, + "released": "2025-05-07" }, "mistralai/mistral-medium-3-5": { "cost": [ @@ -65229,7 +85344,9 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 209715, + "released": "2026-04-30" }, "mistralai/mistral-medium-3.1": { "cost": [ @@ -65238,7 +85355,10 @@ 0.04, 0.0 ], - "limit": 131072 + "knowledge": "2025-06-30", + "limit": 131072, + "max_output": 104857, + "released": "2025-08-12" }, "mistralai/mistral-nemo": { "cost": [ @@ -65247,7 +85367,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-07", + "limit": 131072, + "max_output": 16384, + "open": true, + "released": "2024-07-18" }, "mistralai/mistral-saba": { "cost": [ @@ -65256,7 +85380,10 @@ 0.02, 0.0 ], - "limit": 32768 + "knowledge": "2024-09-30", + "limit": 32768, + "max_output": 26214, + "released": "2025-02-17" }, "mistralai/mistral-small-24b-instruct-2501": { "cost": [ @@ -65265,7 +85392,11 @@ 0.0, 0.0 ], - "limit": 32768 + "knowledge": "2023-10-31", + "limit": 32768, + "max_output": 16384, + "open": true, + "released": "2025-01-30" }, "mistralai/mistral-small-2603": { "cost": [ @@ -65274,7 +85405,11 @@ 0.015, 0.0 ], - "limit": 262144 + "knowledge": "2025-06", + "limit": 262144, + "max_output": 209715, + "open": true, + "released": "2026-03-16" }, "mistralai/mistral-small-3.1-24b-instruct": { "cost": [ @@ -65283,7 +85418,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2023-10-31", + "limit": 128000, + "max_output": 102400, + "open": true, + "released": "2025-03-17" }, "mistralai/mistral-small-3.2-24b-instruct": { "cost": [ @@ -65292,7 +85431,11 @@ 0.0, 0.0 ], - "limit": 256000 + "knowledge": "2023-10-31", + "limit": 256000, + "max_output": 16384, + "open": true, + "released": "2025-06-20" }, "mistralai/mixtral-8x22b-instruct": { "cost": [ @@ -65301,7 +85444,11 @@ 0.2, 0.0 ], - "limit": 65536 + "knowledge": "2024-01-31", + "limit": 65536, + "max_output": 52428, + "open": true, + "released": "2024-04-17" }, "mistralai/voxtral-small-24b-2507": { "cost": [ @@ -65310,7 +85457,10 @@ 0.01, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 26214, + "open": true, + "released": "2025-07-15" }, "moondream/moondream3-preview": { "cost": [ @@ -65319,7 +85469,10 @@ 0.0, 0.0 ], - "limit": 32000 + "limit": 32000, + "max_output": 4096, + "open": true, + "released": "2026-10-15" }, "moondream/moondream3.1-9b-a2b": { "cost": [ @@ -65328,7 +85481,10 @@ 0.0, 0.0 ], - "limit": 32000 + "limit": 32000, + "max_output": 4096, + "open": true, + "released": "2026-10-15" }, "moonshotai/kimi-k2": { "cost": [ @@ -65337,7 +85493,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-12-31", + "limit": 131072, + "max_output": 98304, + "open": true, + "released": "2025-07-11" }, "moonshotai/kimi-k2-0905": { "cost": [ @@ -65346,7 +85506,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 98304, + "open": true, + "released": "2025-09-05" }, "moonshotai/kimi-k2-thinking": { "cost": [ @@ -65355,7 +85518,11 @@ 0.15, 0.0 ], - "limit": 262144 + "knowledge": "2024-08", + "limit": 262144, + "max_output": 98304, + "open": true, + "released": "2025-11-06" }, "moonshotai/kimi-k2.5": { "cost": [ @@ -65364,7 +85531,11 @@ 0.15, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 235929, + "open": true, + "released": "2026-01-27" }, "moonshotai/kimi-k2.6": { "cost": [ @@ -65373,25 +85544,47 @@ 0.15, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 235929, + "open": true, + "released": "2026-04-20" }, "moonshotai/kimi-k2.7-code": { "cost": [ - 0.6712, - 3.35, + 0.56, + 3.1, 0.15, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 235929, + "open": true, + "released": "2026-06-12" }, "moonshotai/kimi-k3": { "cost": [ - 0.239, - 11.936, - 0.21, + 0.191, + 20.0, + 0.181, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 943718, + "open": true, + "released": "2026-07-16" + }, + "moonshotai/kimi-k3.1-pro": { + "cost": [ + 2.0, + 10.0, + 0.2, + 0.0 + ], + "limit": 1048576, + "max_output": 943718, + "released": "2026-10-23" }, "morph/morph-v3-fast": { "cost": [ @@ -65400,7 +85593,9 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 131072, + "released": "2025-07-07" }, "morph/morph-v3-large": { "cost": [ @@ -65409,7 +85604,9 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 131072, + "released": "2025-07-07" }, "nex-agi/nex-n2.5-mini": { "cost": [ @@ -65418,7 +85615,10 @@ 0.0025, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 235929, + "open": true, + "released": "2026-09-08" }, "nex-agi/nex-n2.5-pro": { "cost": [ @@ -65427,7 +85627,10 @@ 0.015, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 235929, + "open": true, + "released": "2026-09-08" }, "nousresearch/hermes-3-llama-3.1-405b": { "cost": [ @@ -65436,7 +85639,11 @@ 0.0, 0.0 ], + "knowledge": "2023-12-31", "limit": 131072, + "max_output": 16384, + "open": true, + "released": "2024-08-16", "status": "deprecated" }, "nousresearch/hermes-3-llama-3.1-70b": { @@ -65446,26 +85653,38 @@ 0.0, 0.0 ], + "knowledge": "2023-12-31", "limit": 131072, + "max_output": 16384, + "open": true, + "released": "2024-08-18", "status": "deprecated" }, "nousresearch/hermes-4-405b": { "cost": [ 1.0, 3.0, - 0.0, + 0.2, 0.0 ], - "limit": 131072 + "knowledge": "2024-08-31", + "limit": 131072, + "max_output": 117964, + "open": true, + "released": "2025-08-26" }, "nvidia/nemotron-3-nano-30b-a3b": { "cost": [ 0.06, 0.24, - 0.0, + 0.012, 0.0 ], - "limit": 262144 + "knowledge": "2025-06-25", + "limit": 262144, + "max_output": 235929, + "open": true, + "released": "2025-12-15" }, "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free": { "cost": [ @@ -65474,7 +85693,10 @@ 0.0, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 65536, + "open": true, + "released": "2026-04-28" }, "nvidia/nemotron-3-super-120b-a12b": { "cost": [ @@ -65483,16 +85705,11 @@ 0.15, 0.0 ], - "limit": 262144 - }, - "nvidia/nemotron-3-super-120b-a12b:free": { - "cost": [ - 0.0, - 0.0, - 0.0, - 0.0 - ], - "limit": 262144 + "knowledge": "2025-06", + "limit": 262144, + "max_output": 235929, + "open": true, + "released": "2026-03-11" }, "nvidia/nemotron-3-ultra-550b-a55b": { "cost": [ @@ -65501,7 +85718,11 @@ 0.12, 0.0 ], - "limit": 262144 + "knowledge": "2025-09", + "limit": 262144, + "max_output": 182520, + "open": true, + "released": "2026-06-04" }, "nvidia/nemotron-3-ultra-550b-a55b:free": { "cost": [ @@ -65510,7 +85731,11 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-09", + "limit": 1000000, + "max_output": 65536, + "open": true, + "released": "2026-06-04" }, "nvidia/nemotron-3.5-content-safety": { "cost": [ @@ -65519,7 +85744,10 @@ 0.0, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 117964, + "open": true, + "released": "2026-06-02" }, "nvidia/nemotron-3.5-content-safety:free": { "cost": [ @@ -65528,7 +85756,10 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 8192, + "open": true, + "released": "2026-06-02" }, "nvidia/nemotron-3.5-lightning": { "cost": [ @@ -65537,7 +85768,11 @@ 0.04, 0.0 ], - "limit": 262144 + "knowledge": "2025-09", + "limit": 262144, + "max_output": 235929, + "open": true, + "released": "2026-08-11" }, "nvidia/nemotron-3.5-lightning:free": { "cost": [ @@ -65546,7 +85781,11 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-09", + "limit": 1000000, + "max_output": 65536, + "open": true, + "released": "2026-08-11" }, "nvidia/nemotron-3.5-super-vl": { "cost": [ @@ -65555,7 +85794,10 @@ 0.02, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 235929, + "open": true, + "released": "2026-10-15" }, "nvidia/nemotron-3.5-super-vl:free": { "cost": [ @@ -65564,16 +85806,10 @@ 0.0, 0.0 ], - "limit": 1000000 - }, - "openai/gpt-3.5-turbo": { - "cost": [ - 0.5, - 1.5, - 0.0, - 0.0 - ], - "limit": 16385 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-10-15" }, "openai/gpt-3.5-turbo-0613": { "cost": [ @@ -65582,7 +85818,10 @@ 0.0, 0.0 ], - "limit": 4095 + "knowledge": "2021-09-30", + "limit": 4095, + "max_output": 3685, + "released": "2024-01-25" }, "openai/gpt-3.5-turbo-16k": { "cost": [ @@ -65591,16 +85830,10 @@ 0.0, 0.0 ], - "limit": 16385 - }, - "openai/gpt-3.5-turbo-instruct": { - "cost": [ - 1.5, - 2.0, - 0.0, - 0.0 - ], - "limit": 4095 + "knowledge": "2021-09-30", + "limit": 16385, + "max_output": 4096, + "released": "2023-08-28" }, "openai/gpt-4": { "cost": [ @@ -65609,16 +85842,10 @@ 0.0, 0.0 ], - "limit": 8191 - }, - "openai/gpt-4-turbo": { - "cost": [ - 10.0, - 30.0, - 0.0, - 0.0 - ], - "limit": 128000 + "knowledge": "2023-11", + "limit": 8191, + "max_output": 4096, + "released": "2023-11-06" }, "openai/gpt-4.1": { "cost": [ @@ -65627,7 +85854,10 @@ 0.5, 0.0 ], - "limit": 1047576 + "knowledge": "2024-04", + "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14" }, "openai/gpt-4.1-mini": { "cost": [ @@ -65636,16 +85866,22 @@ 0.1, 0.0 ], - "limit": 1047576 + "knowledge": "2024-04", + "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14" }, "openai/gpt-4.1-nano": { "cost": [ 0.1, 0.4, - 0.025, + 0.03, 0.0 ], - "limit": 1047576 + "knowledge": "2024-04", + "limit": 1047576, + "max_output": 942818, + "released": "2025-04-14" }, "openai/gpt-4o": { "cost": [ @@ -65654,7 +85890,10 @@ 1.25, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-05-13" }, "openai/gpt-4o-2024-05-13": { "cost": [ @@ -65663,7 +85902,10 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 4096, + "released": "2024-05-13" }, "openai/gpt-4o-2024-08-06": { "cost": [ @@ -65672,7 +85914,10 @@ 1.25, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-08-06" }, "openai/gpt-4o-2024-11-20": { "cost": [ @@ -65681,7 +85926,10 @@ 1.25, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-11-20" }, "openai/gpt-4o-mini": { "cost": [ @@ -65690,7 +85938,10 @@ 0.075, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-07-18" }, "openai/gpt-4o-mini-2024-07-18": { "cost": [ @@ -65699,7 +85950,10 @@ 0.075, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-07-18" }, "openai/gpt-5": { "cost": [ @@ -65708,7 +85962,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "openai/gpt-5-image": { "cost": [ @@ -65717,7 +85974,11 @@ 1.25, 0.0 ], - "limit": 400000 + "knowledge": "2024-10-01", + "limit": 400000, + "max_output": 128000, + "released": "2025-10-14", + "type": "image" }, "openai/gpt-5-image-mini": { "cost": [ @@ -65726,7 +85987,10 @@ 0.25, 0.0 ], - "limit": 400000 + "limit": 400000, + "max_output": 128000, + "released": "2025-10-16", + "type": "image" }, "openai/gpt-5-mini": { "cost": [ @@ -65735,7 +85999,10 @@ 0.025, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "openai/gpt-5-nano": { "cost": [ @@ -65744,7 +86011,10 @@ 0.005, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "openai/gpt-5-pro": { "cost": [ @@ -65753,7 +86023,10 @@ 0.0, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-10-06" }, "openai/gpt-5.1": { "cost": [ @@ -65762,7 +86035,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "openai/gpt-5.1-codex": { "cost": [ @@ -65771,7 +86047,10 @@ 0.13, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "openai/gpt-5.1-codex-max": { "cost": [ @@ -65780,7 +86059,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "openai/gpt-5.1-codex-mini": { "cost": [ @@ -65789,7 +86071,10 @@ 0.03, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "openai/gpt-5.2": { "cost": [ @@ -65798,7 +86083,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "openai/gpt-5.2-chat": { "cost": [ @@ -65807,7 +86095,10 @@ 0.175, 0.0 ], - "limit": 128000 + "knowledge": "2025-08-31", + "limit": 128000, + "max_output": 32000, + "released": "2025-12-11" }, "openai/gpt-5.2-codex": { "cost": [ @@ -65816,7 +86107,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "openai/gpt-5.2-pro": { "cost": [ @@ -65825,7 +86119,10 @@ 0.0, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "openai/gpt-5.3-codex": { "cost": [ @@ -65834,7 +86131,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-02-05" }, "openai/gpt-5.4": { "cost": [ @@ -65843,7 +86143,10 @@ 0.25, 0.0 ], + "knowledge": "2025-08-31", "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05", "tiers": [ { "cost": [ @@ -65866,7 +86169,10 @@ 2.0, 0.0 ], - "limit": 272000 + "limit": 272000, + "max_output": 128000, + "released": "2026-04-21", + "type": "image" }, "openai/gpt-5.4-mini": { "cost": [ @@ -65875,7 +86181,10 @@ 0.075, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "openai/gpt-5.4-nano": { "cost": [ @@ -65884,7 +86193,10 @@ 0.02, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "openai/gpt-5.4-pro": { "cost": [ @@ -65893,7 +86205,10 @@ 0.0, 0.0 ], + "knowledge": "2025-08-31", "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05", "tiers": [ { "cost": [ @@ -65916,7 +86231,10 @@ 0.5, 0.0 ], + "knowledge": "2025-12-01", "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23", "tiers": [ { "cost": [ @@ -65939,7 +86257,10 @@ 0.0, 0.0 ], + "knowledge": "2025-12-01", "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23", "tiers": [ { "cost": [ @@ -65962,7 +86283,10 @@ 0.02, 0.25 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -65985,7 +86309,10 @@ 0.02, 0.25 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -66008,7 +86335,10 @@ 0.4, 5.0 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -66031,7 +86361,10 @@ 0.4, 5.0 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -66054,7 +86387,10 @@ 0.2, 2.5 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -66077,7 +86413,10 @@ 0.2, 2.5 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -66100,7 +86439,10 @@ 1.0, 12.5 ], + "knowledge": "2026-04-30", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-04", "tiers": [ { "cost": [ @@ -66124,6 +86466,8 @@ 12.5 ], "limit": 1050000, + "max_output": 128000, + "released": "2026-09-04", "tiers": [ { "cost": [ @@ -66146,7 +86490,10 @@ 0.01, 0.125 ], + "knowledge": "2026-05-18", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -66170,6 +86517,8 @@ 0.125 ], "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -66192,7 +86541,10 @@ 0.2, 2.5 ], + "knowledge": "2026-04-20", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -66216,6 +86568,8 @@ 2.5 ], "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -66238,7 +86592,10 @@ 0.1, 2.5 ], + "knowledge": "2026-04-30", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-29", "tiers": [ { "cost": [ @@ -66262,6 +86619,8 @@ 2.5 ], "limit": 1050000, + "max_output": 128000, + "released": "2026-09-29", "tiers": [ { "cost": [ @@ -66277,6 +86636,57 @@ } ] }, + "openai/gpt-6.1-terra": { + "cost": [ + 1.0, + 5.0, + 0.05, + 1.25 + ], + "knowledge": "2026-06-01", + "limit": 1050000, + "max_output": 128000, + "released": "2026-10-26", + "tiers": [ + { + "cost": [ + 2.0, + 7.5, + 0.1, + 2.5 + ], + "tier": { + "size": 272000, + "type": "context" + } + } + ] + }, + "openai/gpt-6.1-terra-pro": { + "cost": [ + 1.0, + 5.0, + 0.05, + 1.25 + ], + "limit": 1050000, + "max_output": 128000, + "released": "2026-10-26", + "tiers": [ + { + "cost": [ + 2.0, + 7.5, + 0.1, + 2.5 + ], + "tier": { + "size": 272000, + "type": "context" + } + } + ] + }, "openai/gpt-audio": { "cost": [ 2.5, @@ -66284,7 +86694,10 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2023-10-01", + "limit": 128000, + "max_output": 16384, + "released": "2025-08-28" }, "openai/gpt-audio-mini": { "cost": [ @@ -66293,7 +86706,10 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2023-10-01", + "limit": 128000, + "max_output": 16384, + "released": "2025-10-06" }, "openai/gpt-chat-latest": { "cost": [ @@ -66302,7 +86718,9 @@ 0.5, 0.0 ], - "limit": 400000 + "limit": 400000, + "max_output": 128000, + "released": "2026-05-05" }, "openai/gpt-oss-120b": { "cost": [ @@ -66311,7 +86729,11 @@ 0.075, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 65536, + "open": true, + "released": "2025-08-05" }, "openai/gpt-oss-20b": { "cost": [ @@ -66320,7 +86742,11 @@ 0.009, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "openai/gpt-oss-safeguard-20b": { "cost": [ @@ -66329,25 +86755,10 @@ 0.0375, 0.0 ], - "limit": 131072 - }, - "openai/o1": { - "cost": [ - 15.0, - 60.0, - 7.5, - 0.0 - ], - "limit": 200000 - }, - "openai/o1-pro": { - "cost": [ - 150.0, - 600.0, - 0.0, - 0.0 - ], - "limit": 200000 + "limit": 131072, + "max_output": 65536, + "open": true, + "released": "2025-10-29" }, "openai/o3": { "cost": [ @@ -66356,25 +86767,10 @@ 0.5, 0.0 ], - "limit": 200000 - }, - "openai/o3-mini": { - "cost": [ - 1.1, - 4.4, - 0.55, - 0.0 - ], - "limit": 200000 - }, - "openai/o3-mini-high": { - "cost": [ - 1.1, - 4.4, - 0.55, - 0.0 - ], - "limit": 200000 + "knowledge": "2024-05", + "limit": 200000, + "max_output": 100000, + "released": "2025-04-16" }, "openai/o3-pro": { "cost": [ @@ -66383,25 +86779,10 @@ 0.0, 0.0 ], - "limit": 200000 - }, - "openai/o4-mini": { - "cost": [ - 1.1, - 4.4, - 0.275, - 0.0 - ], - "limit": 200000 - }, - "openai/o4-mini-high": { - "cost": [ - 1.1, - 4.4, - 0.275, - 0.0 - ], - "limit": 200000 + "knowledge": "2024-05", + "limit": 200000, + "max_output": 100000, + "released": "2025-06-10" }, "openrouter/free": { "cost": [ @@ -66410,7 +86791,9 @@ 0.0, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 8000, + "released": "2026-02-01" }, "perceptron/perceptron-mk1": { "cost": [ @@ -66419,7 +86802,9 @@ 0.0, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 8192, + "released": "2026-05-12" }, "perceptron/perceptron-mk1.5": { "cost": [ @@ -66428,7 +86813,9 @@ 0.0, 0.0 ], - "limit": 36864 + "limit": 36864, + "max_output": 8192, + "released": "2026-09-25" }, "perplexity/sonar": { "cost": [ @@ -66437,7 +86824,9 @@ 0.0, 0.0 ], - "limit": 127072 + "limit": 127072, + "max_output": 114364, + "released": "2025-01-27" }, "perplexity/sonar-deep-research": { "cost": [ @@ -66446,7 +86835,10 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 115200, + "reasoning": 3.0, + "released": "2025-03-07" }, "perplexity/sonar-pro": { "cost": [ @@ -66455,7 +86847,9 @@ 0.0, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 8000, + "released": "2025-03-07" }, "perplexity/sonar-pro-search": { "cost": [ @@ -66464,7 +86858,9 @@ 0.0, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 8000, + "released": "2025-10-30" }, "perplexity/sonar-reasoning-pro": { "cost": [ @@ -66473,7 +86869,9 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 115200, + "released": "2025-03-07" }, "poolside/laguna-s-2.1": { "cost": [ @@ -66483,6 +86881,9 @@ 0.0 ], "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-21", "status": "deprecated" }, "poolside/laguna-s-2.1:free": { @@ -66493,6 +86894,9 @@ 0.0 ], "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-07-21", "status": "deprecated" }, "poolside/laguna-xs-2.1": { @@ -66503,6 +86907,9 @@ 0.0 ], "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-07-02", "status": "deprecated" }, "poolside/laguna-xs-2.1:free": { @@ -66513,6 +86920,9 @@ 0.0 ], "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-07-02", "status": "deprecated" }, "prism-ml/ternary-bonsai-2-27b": { @@ -66522,7 +86932,22 @@ 0.0375, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-09-18" + }, + "prism-ml/ternary-bonsai-2-9b": { + "cost": [ + 0.08, + 0.13, + 0.04, + 0.0 + ], + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-10-16" }, "qwen/qwen-2.5-72b-instruct": { "cost": [ @@ -66531,7 +86956,11 @@ 0.0, 0.0 ], - "limit": 32768 + "knowledge": "2024-06-30", + "limit": 32768, + "max_output": 16384, + "open": true, + "released": "2024-09-19" }, "qwen/qwen-2.5-7b-instruct": { "cost": [ @@ -66540,7 +86969,11 @@ 0.0, 0.0 ], - "limit": 32768 + "knowledge": "2024-06-30", + "limit": 32768, + "max_output": 29491, + "open": true, + "released": "2024-10-16" }, "qwen/qwen-2.5-coder-32b-instruct": { "cost": [ @@ -66549,7 +86982,10 @@ 0.0, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 29491, + "open": true, + "released": "2024-11-12" }, "qwen/qwen-plus": { "cost": [ @@ -66558,7 +86994,10 @@ 0.052, 0.325 ], + "knowledge": "2024-04", "limit": 1000000, + "max_output": 32768, + "released": "2024-01-25", "tiers": [ { "cost": [ @@ -66581,7 +87020,11 @@ 0.4, 0.0 ], - "limit": 128000 + "knowledge": "2024-04", + "limit": 128000, + "max_output": 115200, + "open": true, + "released": "2025-01-26" }, "qwen/qwen3-14b": { "cost": [ @@ -66590,7 +87033,11 @@ 0.0, 0.0 ], - "limit": 40960 + "knowledge": "2025-03-31", + "limit": 40960, + "max_output": 16384, + "open": true, + "released": "2025-04-28" }, "qwen/qwen3-235b-a22b-2507": { "cost": [ @@ -66599,7 +87046,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 16384, + "open": true, + "released": "2025-07-21" }, "qwen/qwen3-235b-a22b-thinking-2507": { "cost": [ @@ -66608,7 +87058,10 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 16384, + "open": true, + "released": "2025-07-25" }, "qwen/qwen3-30b-a3b": { "cost": [ @@ -66617,16 +87070,22 @@ 0.0, 0.0 ], - "limit": 40960 + "limit": 40960, + "max_output": 16384, + "open": true, + "released": "2025-04-28" }, "qwen/qwen3-30b-a3b-instruct-2507": { "cost": [ - 0.09, + 0.1, 0.3, - 0.0, + 0.1, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 235929, + "open": true, + "released": "2025-07-28" }, "qwen/qwen3-32b": { "cost": [ @@ -66635,7 +87094,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2025-04", + "limit": 131072, + "max_output": 16384, + "open": true, + "released": "2025-04-28" }, "qwen/qwen3-coder": { "cost": [ @@ -66644,7 +87107,11 @@ 0.1, 0.0 ], - "limit": 262144 + "knowledge": "2025-04", + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2025-07-22" }, "qwen/qwen3-coder-30b-a3b-instruct": { "cost": [ @@ -66653,7 +87120,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-04", + "limit": 262144, + "max_output": 235929, + "open": true, + "released": "2025-07-31" }, "qwen/qwen3-coder-flash": { "cost": [ @@ -66662,7 +87133,10 @@ 0.039, 0.24375 ], + "knowledge": "2025-04", "limit": 1000000, + "max_output": 65536, + "released": "2025-07-28", "tiers": [ { "cost": [ @@ -66697,7 +87171,11 @@ 0.07, 0.0 ], - "limit": 262144 + "knowledge": "2025-09", + "limit": 262144, + "max_output": 235929, + "open": true, + "released": "2026-02-03" }, "qwen/qwen3-next-80b-a3b-instruct": { "cost": [ @@ -66706,16 +87184,11 @@ 0.0, 0.0 ], - "limit": 262144 - }, - "qwen/qwen3-next-80b-a3b-thinking": { - "cost": [ - 0.15, - 1.2, - 0.0, - 0.0 - ], - "limit": 262144 + "knowledge": "2025-04", + "limit": 262144, + "max_output": 16384, + "open": true, + "released": "2025-09" }, "qwen/qwen3-vl-235b-a22b-instruct": { "cost": [ @@ -66724,7 +87197,11 @@ 0.1, 0.0 ], - "limit": 262144 + "knowledge": "2025-03-31", + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2025-09-23" }, "qwen/qwen3-vl-30b-a3b-instruct": { "cost": [ @@ -66733,7 +87210,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 16384, + "open": true, + "released": "2025-10-04" }, "qwen/qwen3-vl-30b-a3b-thinking": { "cost": [ @@ -66742,7 +87222,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-03-31", + "limit": 262144, + "max_output": 235929, + "open": true, + "released": "2025-10-06" }, "qwen/qwen3-vl-8b-instruct": { "cost": [ @@ -66751,25 +87235,34 @@ 0.12, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 235929, + "open": true, + "released": "2025-10-14" }, "qwen/qwen3.5-122b-a10b": { "cost": [ - 0.4, - 3.2, + 0.26, + 2.08, 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-23" }, "qwen/qwen3.5-27b": { "cost": [ - 0.27, - 2.16, - 0.27, + 0.26, + 2.6, + 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 81920, + "open": true, + "released": "2026-02-23" }, "qwen/qwen3.5-35b-a3b": { "cost": [ @@ -66778,7 +87271,10 @@ 0.05, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 81920, + "open": true, + "released": "2026-02-23" }, "qwen/qwen3.5-397b-a17b": { "cost": [ @@ -66787,7 +87283,10 @@ 0.3, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 235929, + "open": true, + "released": "2026-02-15" }, "qwen/qwen3.5-9b": { "cost": [ @@ -66797,6 +87296,9 @@ 0.0 ], "limit": 262144, + "max_output": 235929, + "open": true, + "released": "2026-02-23", "status": "deprecated" }, "qwen/qwen3.5-flash-02-23": { @@ -66806,7 +87308,9 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 65536, + "released": "2026-02-25" }, "qwen/qwen3.5-plus-02-15": { "cost": [ @@ -66815,7 +87319,10 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 1000000, + "max_output": 65536, + "released": "2026-02-16", "tiers": [ { "cost": [ @@ -66839,6 +87346,8 @@ 0.375 ], "limit": 1000000, + "max_output": 65536, + "released": "2026-04-27", "tiers": [ { "cost": [ @@ -66856,21 +87365,27 @@ }, "qwen/qwen3.6-27b": { "cost": [ - 0.25, - 2.0, - 0.025, + 0.45, + 2.7, + 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-04-22" }, "qwen/qwen3.6-35b-a3b": { "cost": [ 0.1, - 0.95, - 0.05, + 0.9, + 0.025, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 235929, + "open": true, + "released": "2026-04-17" }, "qwen/qwen3.6-flash": { "cost": [ @@ -66880,6 +87395,8 @@ 0.234375 ], "limit": 1000000, + "max_output": 65536, + "released": "2026-04-27", "tiers": [ { "cost": [ @@ -66902,7 +87419,10 @@ 0.0, 0.40625 ], + "knowledge": "2025-04", "limit": 1000000, + "max_output": 65536, + "released": "2026-04-02", "tiers": [ { "cost": [ @@ -66926,6 +87446,8 @@ 0.038 ], "limit": 1000000, + "max_output": 65536, + "released": "2026-07-15", "tiers": [ { "cost": [ @@ -66960,7 +87482,9 @@ 0.295, 1.84375 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-05-21" }, "qwen/qwen3.7-plus": { "cost": [ @@ -66969,7 +87493,10 @@ 0.064, 0.4 ], + "knowledge": "2025-04", "limit": 1000000, + "max_output": 131072, + "released": "2026-06-02", "tiers": [ { "cost": [ @@ -66992,16 +87519,22 @@ 0.25, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 909000, + "open": true, + "released": "2026-08-12" }, "qwen/qwen3.8-27b": { "cost": [ - 0.2, - 2.5, - 0.09, + 0.039, + 1.25, + 0.0039, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 65536, + "open": true, + "released": "2026-08-14" }, "qwen/qwen3.8-flash": { "cost": [ @@ -67010,7 +87543,9 @@ 0.016, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-08-26" }, "qwen/qwen3.8-max-0902": { "cost": [ @@ -67019,7 +87554,9 @@ 0.25, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-09-02" }, "qwen/qwen3.8-max-prime": { "cost": [ @@ -67028,7 +87565,9 @@ 0.5, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-09-23" }, "qwen/qwen3.8-omni-flash": { "cost": [ @@ -67037,7 +87576,9 @@ 0.016, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-09-17" }, "recursive/flint-v1.0:free": { "cost": [ @@ -67046,7 +87587,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 235929, + "open": true, + "released": "2026-10-21" }, "reflection/beam-1.0-501b-a23b": { "cost": [ @@ -67055,7 +87599,11 @@ 0.05, 0.0 ], - "limit": 1048576 + "knowledge": "2026-06-30", + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-10-05" }, "rekaai/reka-edge": { "cost": [ @@ -67064,7 +87612,10 @@ 0.0, 0.0 ], - "limit": 16384 + "limit": 16384, + "max_output": 14745, + "open": true, + "released": "2026-03-11" }, "rekaai/reka-flash-3": { "cost": [ @@ -67073,7 +87624,11 @@ 0.0, 0.0 ], - "limit": 65536 + "knowledge": "2025-01-31", + "limit": 65536, + "max_output": 58982, + "open": true, + "released": "2025-03-10" }, "relace/relace-apply-3": { "cost": [ @@ -67082,7 +87637,9 @@ 0.0, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 128000, + "released": "2025-09-26" }, "relace/relace-search": { "cost": [ @@ -67091,7 +87648,9 @@ 0.0, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 128000, + "released": "2025-12-08" }, "sakana/fugu-max": { "cost": [ @@ -67100,7 +87659,9 @@ 0.25, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-11" }, "sakana/fugu-ultra": { "cost": [ @@ -67110,6 +87671,8 @@ 0.0 ], "limit": 1000000, + "max_output": 128000, + "released": "2026-06-15", "tiers": [ { "cost": [ @@ -67132,7 +87695,10 @@ 0.5, 0.0 ], + "knowledge": "2026-08-28", "limit": 1000000, + "max_output": 128000, + "released": "2026-09-11", "tiers": [ { "cost": [ @@ -67155,7 +87721,9 @@ 0.15, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "released": "2026-08-03" }, "sao10k/l3-lunaris-8b": { "cost": [ @@ -67164,7 +87732,11 @@ 0.0, 0.0 ], - "limit": 8192 + "knowledge": "2023-12-31", + "limit": 8192, + "max_output": 7372, + "open": true, + "released": "2024-08-13" }, "sao10k/l3.1-euryale-70b": { "cost": [ @@ -67173,7 +87745,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2023-12-31", + "limit": 131072, + "max_output": 16384, + "open": true, + "released": "2024-08-28" }, "scaledown/extract": { "cost": [ @@ -67182,7 +87758,9 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 900000, + "released": "2026-10-13" }, "scaledown/summarize": { "cost": [ @@ -67191,7 +87769,9 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 4000, + "released": "2026-10-13" }, "stepfun/step-3.5-flash": { "cost": [ @@ -67200,7 +87780,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-01-29" }, "stepfun/step-3.7-flash": { "cost": [ @@ -67209,7 +87793,11 @@ 0.04, 0.0 ], - "limit": 262144 + "knowledge": "2026-03-01", + "limit": 262144, + "max_output": 230400, + "open": true, + "released": "2026-05-29" }, "stepfun/step-5-preview": { "cost": [ @@ -67218,7 +87806,10 @@ 0.1, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 64000, + "open": true, + "released": "2026-09-16" }, "tencent/hunyuan-a13b-instruct": { "cost": [ @@ -67227,7 +87818,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2025-03-31", + "limit": 131072, + "max_output": 117964, + "open": true, + "released": "2025-07-08" }, "tencent/hy-mt2-1.8b": { "cost": [ @@ -67236,7 +87831,10 @@ 0.0, 0.0 ], - "limit": 8192 + "limit": 8192, + "max_output": 4096, + "open": true, + "released": "2026-05-21" }, "tencent/hy-mt2-30b-a3b": { "cost": [ @@ -67245,7 +87843,10 @@ 0.0, 0.0 ], - "limit": 8192 + "limit": 8192, + "max_output": 4096, + "open": true, + "released": "2026-05-21" }, "tencent/hy-mt2-7b": { "cost": [ @@ -67254,7 +87855,10 @@ 0.0, 0.0 ], - "limit": 8192 + "limit": 8192, + "max_output": 4096, + "open": true, + "released": "2026-05-21" }, "tencent/hy3": { "cost": [ @@ -67263,7 +87867,10 @@ 0.033, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 128000, + "open": true, + "released": "2026-07-06" }, "tencent/hy3-preview": { "cost": [ @@ -67272,7 +87879,10 @@ 0.06, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 235929, + "open": true, + "released": "2026-04-20" }, "tencent/hy4-preview": { "cost": [ @@ -67281,7 +87891,10 @@ 0.042, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 64000, + "open": true, + "released": "2026-08-28" }, "thedrummer/cydonia-24b-v4.1": { "cost": [ @@ -67290,7 +87903,11 @@ 0.15, 0.0 ], - "limit": 131072 + "knowledge": "2024-04-30", + "limit": 131072, + "max_output": 117964, + "open": true, + "released": "2025-09-27" }, "thedrummer/skyfall-36b-v2": { "cost": [ @@ -67299,7 +87916,11 @@ 0.25, 0.0 ], - "limit": 32768 + "knowledge": "2024-06-30", + "limit": 32768, + "max_output": 29491, + "open": true, + "released": "2025-03-10" }, "thedrummer/unslopnemo-12b": { "cost": [ @@ -67308,7 +87929,11 @@ 0.0, 0.0 ], - "limit": 1024000 + "knowledge": "2024-04-30", + "limit": 1024000, + "max_output": 819200, + "open": true, + "released": "2024-11-08" }, "thinkingmachines/inkling": { "cost": [ @@ -67317,7 +87942,10 @@ 0.17, 0.0 ], - "limit": 524288 + "limit": 524288, + "max_output": 471859, + "open": true, + "released": "2026-07-15" }, "thinkingmachines/inkling-small": { "cost": [ @@ -67326,7 +87954,10 @@ 0.1, 0.0 ], - "limit": 524288 + "limit": 524288, + "max_output": 262144, + "open": true, + "released": "2026-07-30" }, "thinkingmachines/inkling-small:free": { "cost": [ @@ -67335,7 +87966,10 @@ 0.0, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 262144, + "open": true, + "released": "2026-07-30" }, "thinkingmachines/inkling:free": { "cost": [ @@ -67344,7 +87978,10 @@ 0.0, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 262144, + "open": true, + "released": "2026-07-15" }, "unbiased/pareto-26.10": { "cost": [ @@ -67353,7 +87990,9 @@ 0.03, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-10-15" }, "unbiased/pareto-26.9": { "cost": [ @@ -67362,7 +88001,9 @@ 0.25, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 131072, + "released": "2026-10-13" }, "undi95/remm-slerp-l2-13b": { "cost": [ @@ -67371,7 +88012,11 @@ 0.0, 0.0 ], - "limit": 6144 + "knowledge": "2023-06-30", + "limit": 6144, + "max_output": 5529, + "open": true, + "released": "2023-07-22" }, "upstage/solar-mini4": { "cost": [ @@ -67380,7 +88025,10 @@ 0.005, 0.0 ], - "limit": 524288 + "knowledge": "2026-02", + "limit": 524288, + "max_output": 131072, + "released": "2026-09-22" }, "upstage/solar-pro-3": { "cost": [ @@ -67389,7 +88037,10 @@ 0.015, 0.0 ], - "limit": 131072 + "knowledge": "2025-07", + "limit": 131072, + "max_output": 117964, + "released": "2026-01-26" }, "upstage/solar-pro4": { "cost": [ @@ -67398,7 +88049,10 @@ 0.03, 0.0 ], - "limit": 524288 + "knowledge": "2026-02", + "limit": 524288, + "max_output": 131072, + "released": "2026-08-06" }, "writer/palmyra-x5": { "cost": [ @@ -67407,7 +88061,9 @@ 0.0, 0.0 ], - "limit": 1040000 + "limit": 1040000, + "max_output": 8192, + "released": "2025-04-28" }, "x-ai/grok-4.20": { "cost": [ @@ -67416,7 +88072,10 @@ 0.2, 0.0 ], + "knowledge": "2025-09-01", "limit": 2000000, + "max_output": 1800000, + "released": "2026-03-31", "tiers": [ { "cost": [ @@ -67439,7 +88098,10 @@ 0.2, 0.0 ], + "knowledge": "2025-09-01", "limit": 2000000, + "max_output": 1800000, + "released": "2026-03-31", "tiers": [ { "cost": [ @@ -67463,6 +88125,8 @@ 0.0 ], "limit": 1000000, + "max_output": 900000, + "released": "2026-04-17", "tiers": [ { "cost": [ @@ -67486,6 +88150,8 @@ 0.0 ], "limit": 500000, + "max_output": 450000, + "released": "2026-07-08", "tiers": [ { "cost": [ @@ -67508,7 +88174,10 @@ 0.5, 0.0 ], + "knowledge": "2026-02-01", "limit": 500000, + "max_output": 450000, + "released": "2026-08-12", "tiers": [ { "cost": [ @@ -67531,7 +88200,10 @@ 0.5, 0.0 ], + "knowledge": "2026-05", "limit": 500000, + "max_output": 450000, + "released": "2026-09-21", "tiers": [ { "cost": [ @@ -67555,6 +88227,8 @@ 0.0 ], "limit": 256000, + "max_output": 230400, + "released": "2026-04-16", "tiers": [ { "cost": [ @@ -67572,22 +88246,30 @@ }, "xiaomi/mimo-v2.5": { "cost": [ - 0.119, - 0.238, - 0.00255, + 0.4, + 2.0, + 0.08, 0.0 ], + "knowledge": "2024-12", "limit": 1050000, + "max_output": 65536, + "open": true, + "released": "2026-04-22", "status": "deprecated" }, "xiaomi/mimo-v2.5-pro": { "cost": [ - 0.3045, - 0.609, - 0.0028, + 0.48, + 1.8, + 0.096, 0.0 ], + "knowledge": "2024-12", "limit": 1050000, + "max_output": 235929, + "open": true, + "released": "2026-04-22", "status": "deprecated" }, "xiaomi/mimo-v2.6-flash": { @@ -67597,7 +88279,10 @@ 0.0028, 0.0 ], - "limit": 1050000 + "limit": 1050000, + "max_output": 131072, + "open": true, + "released": "2026-09-22" }, "xiaomi/mimo-v2.6-pro": { "cost": [ @@ -67606,7 +88291,10 @@ 0.0036, 0.0 ], - "limit": 1050000 + "limit": 1050000, + "max_output": 131072, + "open": true, + "released": "2026-09-22" }, "xiaomi/mimo-v2.6-pro-ultraspeed": { "cost": [ @@ -67615,7 +88303,10 @@ 0.036, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-09-21" }, "xingchen-agi/xing4.0-29b-a4b:free": { "cost": [ @@ -67624,7 +88315,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 235929, + "open": true, + "released": "2026-10-16" }, "z-ai/glm-4.5": { "cost": [ @@ -67633,7 +88327,11 @@ 0.11, 0.0 ], + "knowledge": "2025-04", "limit": 131072, + "max_output": 98304, + "open": true, + "released": "2025-07-28", "status": "deprecated" }, "z-ai/glm-4.5-air": { @@ -67643,7 +88341,11 @@ 0.025, 0.0 ], - "limit": 131072 + "knowledge": "2025-04", + "limit": 131072, + "max_output": 98304, + "open": true, + "released": "2025-07-28" }, "z-ai/glm-4.5v": { "cost": [ @@ -67652,7 +88354,11 @@ 0.11, 0.0 ], - "limit": 65536 + "knowledge": "2025-04", + "limit": 65536, + "max_output": 16384, + "open": true, + "released": "2025-08-11" }, "z-ai/glm-4.6": { "cost": [ @@ -67661,16 +88367,24 @@ 0.11, 0.0 ], - "limit": 204800 + "knowledge": "2025-04", + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-09-30" }, "z-ai/glm-4.6v": { "cost": [ 0.3, 0.9, - 0.055, + 0.05, 0.0 ], - "limit": 131072 + "knowledge": "2025-04", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-12-08" }, "z-ai/glm-4.7": { "cost": [ @@ -67679,7 +88393,11 @@ 0.099, 0.0 ], - "limit": 204800 + "knowledge": "2025-04", + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-12-22" }, "z-ai/glm-4.7-flash": { "cost": [ @@ -67688,7 +88406,11 @@ 0.0, 0.0 ], - "limit": 200000 + "knowledge": "2025-04", + "limit": 200000, + "max_output": 117964, + "open": true, + "released": "2026-01-19" }, "z-ai/glm-5": { "cost": [ @@ -67697,7 +88419,10 @@ 0.2, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-02-12" }, "z-ai/glm-5-turbo": { "cost": [ @@ -67706,7 +88431,9 @@ 0.24, 0.0 ], - "limit": 202752 + "limit": 202752, + "max_output": 131072, + "released": "2026-03-16" }, "z-ai/glm-5.1": { "cost": [ @@ -67715,34 +88442,46 @@ 0.26, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-04-07" }, "z-ai/glm-5.2": { "cost": [ - 0.0341, + 0.014, 7.0, - 0.033, + 0.013, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 943718, + "open": true, + "released": "2026-06-13" }, "z-ai/glm-5.3": { "cost": [ - 0.079, + 0.0699, 1.4, - 0.078, + 0.0689, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 943718, + "open": true, + "released": "2026-08-14" }, "z-ai/glm-5.3-flash": { "cost": [ - 0.0052, - 0.1985, - 0.0052, + 0.15, + 0.5, + 0.03, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 943717, + "open": true, + "released": "2026-08-26" }, "z-ai/glm-5.3-flashx": { "cost": [ @@ -67751,7 +88490,9 @@ 0.09, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-09-18" }, "z-ai/glm-5.3-prime": { "cost": [ @@ -67760,7 +88501,9 @@ 0.56, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-09-23" }, "z-ai/glm-5v-turbo": { "cost": [ @@ -67769,7 +88512,9 @@ 0.24, 0.0 ], - "limit": 202752 + "limit": 202752, + "max_output": 131072, + "released": "2026-04-01" }, "~anthropic/claude-fable-latest": { "cost": [ @@ -67778,7 +88523,9 @@ 0.25, 12.5 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-09" }, "~anthropic/claude-haiku-latest": { "cost": [ @@ -67788,6 +88535,8 @@ 0.125 ], "limit": 1000000, + "max_output": 128000, + "released": "2026-04-27", "tiers": [ { "cost": [ @@ -67810,7 +88559,9 @@ 0.2, 5.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-21" }, "~anthropic/claude-sonnet-latest": { "cost": [ @@ -67819,34 +88570,43 @@ 0.1, 2.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-27" }, "~deepseek/deepseek-flash-latest": { "cost": [ - 0.045, - 0.6, - 0.006, + 0.0115, + 1.8, + 0.0114, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 943718, + "released": "2026-09-14" }, "~deepseek/deepseek-pro-latest": { "cost": [ - 0.20592, - 0.61776, - 0.006552, + 0.2043, + 8.0, + 0.2, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 393216, + "released": "2026-09-14" }, "~deepseek/deepseek-v4-flash-latest": { "cost": [ - 0.04708, - 0.14124, - 0.001498, + 0.0422, + 0.1637, + 0.028, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 943718, + "released": "2026-08-01" }, "~google/gemini-flash-latest": { "cost": [ @@ -67855,7 +88615,10 @@ 0.075, 0.041667 ], - "limit": 1048576 + "knowledge": "2025-01-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-04-27" }, "~google/gemini-pro-latest": { "cost": [ @@ -67864,7 +88627,10 @@ 0.1, 0.1875 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 943718, + "released": "2026-04-27", "tiers": [ { "cost": [ @@ -67882,12 +88648,14 @@ }, "~moonshotai/kimi-latest": { "cost": [ - 0.238, - 16.0, - 0.228, + 0.19, + 10.5634, + 0.19, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 943718, + "released": "2026-04-27" }, "~openai/gpt-astra-latest": { "cost": [ @@ -67897,6 +88665,8 @@ 12.5 ], "limit": 1050000, + "max_output": 128000, + "released": "2026-09-11", "tiers": [ { "cost": [ @@ -67919,7 +88689,10 @@ 0.01, 0.125 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-11", "tiers": [ { "cost": [ @@ -67942,7 +88715,10 @@ 0.075, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-04-27" }, "~openai/gpt-sol-latest": { "cost": [ @@ -67951,7 +88727,10 @@ 0.1, 2.5 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-11", "tiers": [ { "cost": [ @@ -67969,19 +88748,22 @@ }, "~openai/gpt-terra-latest": { "cost": [ - 2.0, - 12.0, - 0.2, - 2.5 + 1.0, + 5.0, + 0.05, + 1.25 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-11", "tiers": [ { "cost": [ - 4.0, - 18.0, - 0.4, - 5.0 + 2.0, + 7.5, + 0.1, + 2.5 ], "tier": { "size": 272000, @@ -67997,7 +88779,9 @@ 0.03, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-10-13" }, "~x-ai/grok-latest": { "cost": [ @@ -68007,6 +88791,8 @@ 0.0 ], "limit": 500000, + "max_output": 450000, + "released": "2026-07-08", "tiers": [ { "cost": [ @@ -68024,21 +88810,25 @@ }, "~z-ai/glm-flash-latest": { "cost": [ - 0.0052, - 0.1985, - 0.0052, + 0.0237, + 0.1142, + 0.0237, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-08-27" }, "~z-ai/glm-latest": { "cost": [ - 0.079, + 0.0699, 1.4, - 0.078, + 0.0689, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 943718, + "released": "2026-08-19" } }, "name": "OpenRouter" @@ -68052,7 +88842,10 @@ 1.0, 12.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-09" }, "claude-fable-5-1": { "cost": [ @@ -68061,7 +88854,10 @@ 0.25, 12.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-01" }, "claude-haiku-4-5": { "cost": [ @@ -68070,7 +88866,10 @@ 0.11, 1.375 ], - "limit": 200000 + "knowledge": "2025-02-28", + "limit": 200000, + "max_output": 64000, + "released": "2025-10-15" }, "claude-opus-4-5": { "cost": [ @@ -68079,7 +88878,10 @@ 0.5, 6.25 ], - "limit": 200000 + "knowledge": "2025-05", + "limit": 200000, + "max_output": 64000, + "released": "2025-11-24" }, "claude-opus-4-6": { "cost": [ @@ -68088,7 +88890,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2025-05-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-05" }, "claude-opus-4-7": { "cost": [ @@ -68097,7 +88902,10 @@ 0.55, 6.875 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 64000, + "released": "2026-04-16" }, "claude-opus-4-8": { "cost": [ @@ -68106,7 +88914,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-28" }, "claude-opus-5": { "cost": [ @@ -68115,7 +88926,10 @@ 0.55, 6.875 ], - "limit": 1000000 + "knowledge": "2026-05", + "limit": 1000000, + "max_output": 128000, + "released": "2026-07-24" }, "claude-sonnet-4-5": { "cost": [ @@ -68124,7 +88938,10 @@ 0.33, 4.125 ], + "knowledge": "2025-07-31", "limit": 200000, + "max_output": 64000, + "released": "2025-09-29", "tiers": [ { "cost": [ @@ -68147,7 +88964,10 @@ 0.33, 4.125 ], - "limit": 1000000 + "knowledge": "2025-08-31", + "limit": 1000000, + "max_output": 64000, + "released": "2026-02-17" }, "claude-sonnet-5": { "cost": [ @@ -68156,7 +88976,10 @@ 0.22, 2.75 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 64000, + "released": "2026-06-30" }, "deepseek-v4-flash": { "cost": [ @@ -68165,7 +88988,11 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "deepseek-v4-pro": { "cost": [ @@ -68174,7 +89001,11 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 65536, + "open": true, + "released": "2026-04-24" }, "gemini-3-flash-preview": { "cost": [ @@ -68183,7 +89014,10 @@ 0.05, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2025-12-17" }, "gemini-3.1-pro-preview": { "cost": [ @@ -68192,7 +89026,10 @@ 0.2, 0.0 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2026-02-19", "tiers": [ { "cost": [ @@ -68215,7 +89052,10 @@ 0.15, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-05-19" }, "gemini-3.5-flash-lite": { "cost": [ @@ -68224,7 +89064,10 @@ 0.03, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-07-21" }, "gemini-3.7-flash": { "cost": [ @@ -68233,7 +89076,10 @@ 0.075, 0.0 ], + "knowledge": "2026-03", "limit": 1048576, + "max_output": 65536, + "released": "2026-08-13", "status": "deprecated" }, "gemini-3.8-flash": { @@ -68243,7 +89089,9 @@ 0.0825, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65536, + "released": "2026-09-02" }, "gemma-4-31b-it": { "cost": [ @@ -68252,7 +89100,11 @@ 0.0, 0.0 ], - "limit": 256000 + "knowledge": "2025-01", + "limit": 256000, + "max_output": 8192, + "open": true, + "released": "2026-04-02" }, "glm-5.2": { "cost": [ @@ -68261,7 +89113,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "glm-5.3": { "cost": [ @@ -68270,7 +89125,10 @@ 0.44, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "glm-5.3-flash": { "cost": [ @@ -68279,7 +89137,10 @@ 0.07, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 128000, + "open": true, + "released": "2026-08-26" }, "gpt-5.3-codex": { "cost": [ @@ -68288,7 +89149,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-02-05" }, "gpt-5.4": { "cost": [ @@ -68297,7 +89161,10 @@ 0.25, 0.0 ], + "knowledge": "2025-08-31", "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05", "tiers": [ { "cost": [ @@ -68320,7 +89187,10 @@ 0.075, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "gpt-5.4-nano": { "cost": [ @@ -68329,7 +89199,10 @@ 0.02, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "gpt-5.4-pro": { "cost": [ @@ -68338,7 +89211,10 @@ 0.0, 0.0 ], + "knowledge": "2025-08-31", "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05", "tiers": [ { "cost": [ @@ -68361,7 +89237,10 @@ 0.5, 0.0 ], + "knowledge": "2025-12-01", "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23", "tiers": [ { "cost": [ @@ -68384,7 +89263,10 @@ 0.0, 0.0 ], - "limit": 1050000 + "knowledge": "2025-12-01", + "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23" }, "gpt-5.6-luna": { "cost": [ @@ -68393,7 +89275,10 @@ 0.02, 0.25 ], + "knowledge": "2026-02-16", "limit": 1000000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -68416,7 +89301,10 @@ 0.5, 6.25 ], + "knowledge": "2026-02-16", "limit": 1000000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -68439,7 +89327,10 @@ 0.2, 2.5 ], + "knowledge": "2026-02-16", "limit": 1000000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -68462,7 +89353,10 @@ 1.0, 12.5 ], + "knowledge": "2026-04-30", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-04", "tiers": [ { "cost": [ @@ -68485,7 +89379,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-06", + "limit": 128000, + "max_output": 8192, + "open": true, + "released": "2025-08-05" }, "gpt-oss-20b": { "cost": [ @@ -68494,7 +89392,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-06", + "limit": 128000, + "max_output": 8192, + "open": true, + "released": "2025-08-05" }, "grok-4.3": { "cost": [ @@ -68503,7 +89405,9 @@ 0.2, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 30000, + "released": "2026-04-17" }, "grok-4.5": { "cost": [ @@ -68512,7 +89416,9 @@ 0.5, 0.0 ], - "limit": 500000 + "limit": 500000, + "max_output": 500000, + "released": "2026-07-08" }, "grok-4.6": { "cost": [ @@ -68521,7 +89427,10 @@ 0.5, 0.0 ], + "knowledge": "2026-02-01", "limit": 500000, + "max_output": 500000, + "released": "2026-08-12", "tiers": [ { "cost": [ @@ -68544,7 +89453,9 @@ 0.2, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 256000, + "released": "2026-04-16" }, "kimi-k3": { "cost": [ @@ -68553,7 +89464,10 @@ 0.0, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-16" }, "minimax-m2.7": { "cost": [ @@ -68562,7 +89476,10 @@ 0.0, 0.0 ], - "limit": 196608 + "limit": 196608, + "max_output": 131072, + "open": true, + "released": "2026-03-18" }, "minimax-m3": { "cost": [ @@ -68572,6 +89489,9 @@ 0.0 ], "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-01", "tiers": [ { "cost": [ @@ -68594,7 +89514,11 @@ 0.0, 0.0 ], - "limit": 256000 + "knowledge": "2024-11", + "limit": 256000, + "max_output": 8192, + "open": true, + "released": "2025-12-02" }, "mistral-small-2603": { "cost": [ @@ -68603,7 +89527,11 @@ 0.0, 0.0 ], - "limit": 256000 + "knowledge": "2025-06", + "limit": 256000, + "max_output": 8192, + "open": true, + "released": "2026-03-16" }, "muse-spark-1.2": { "cost": [ @@ -68612,7 +89540,9 @@ 0.15, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-08-05" }, "muse-spark-1.3": { "cost": [ @@ -68621,7 +89551,9 @@ 0.15, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-09-02" }, "qwen3-coder-next": { "cost": [ @@ -68630,7 +89562,11 @@ 0.0, 0.0 ], + "knowledge": "2025-09", "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-03", "status": "deprecated" }, "qwen3.6-35b-a3b": { @@ -68640,7 +89576,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-04-17" }, "qwen3.8-2.4t-a95b": { "cost": [ @@ -68649,7 +89588,10 @@ 0.63, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 131072, + "open": true, + "released": "2026-08-12" }, "qwen3.8-27b": { "cost": [ @@ -68658,7 +89600,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-08-14" }, "qwen3.8-max": { "cost": [ @@ -68667,7 +89612,9 @@ 0.25, 0.0 ], - "limit": 983616 + "limit": 983616, + "max_output": 131072, + "released": "2026-08-03" }, "sonar": { "cost": [ @@ -68676,7 +89623,10 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2025-09-01", + "limit": 128000, + "max_output": 4096, + "released": "2024-01-01" }, "sonar-pro": { "cost": [ @@ -68685,7 +89635,10 @@ 0.0, 0.0 ], - "limit": 200000 + "knowledge": "2025-09-01", + "limit": 200000, + "max_output": 8000, + "released": "2024-01-01" }, "sonar-reasoning-pro": { "cost": [ @@ -68694,7 +89647,10 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2025-09-01", + "limit": 128000, + "max_output": 4096, + "released": "2024-01-01" } }, "name": "Opper" @@ -68708,7 +89664,10 @@ 1.0, 12.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-09" }, "anthropic/claude-haiku-4.5": { "cost": [ @@ -68717,7 +89676,10 @@ 0.1, 1.25 ], - "limit": 200000 + "knowledge": "2025-02-28", + "limit": 200000, + "max_output": 64000, + "released": "2025-10-15" }, "anthropic/claude-opus-4.5": { "cost": [ @@ -68726,7 +89688,10 @@ 0.5, 6.25 ], - "limit": 200000 + "knowledge": "2025-05", + "limit": 200000, + "max_output": 64000, + "released": "2025-11-24" }, "anthropic/claude-opus-4.6": { "cost": [ @@ -68735,7 +89700,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2025-05-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-05" }, "anthropic/claude-opus-4.6-fast": { "cost": [ @@ -68744,7 +89712,10 @@ 3.0, 37.5 ], - "limit": 1000000 + "knowledge": "2025-05-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-05" }, "anthropic/claude-opus-4.7": { "cost": [ @@ -68753,7 +89724,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-16" }, "anthropic/claude-opus-4.7-fast": { "cost": [ @@ -68762,7 +89736,10 @@ 3.0, 37.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-16" }, "anthropic/claude-opus-4.8": { "cost": [ @@ -68771,7 +89748,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-28" }, "anthropic/claude-opus-5": { "cost": [ @@ -68780,7 +89760,10 @@ 0.5, 10.0 ], - "limit": 1000000 + "knowledge": "2026-05", + "limit": 1000000, + "max_output": 128000, + "released": "2026-07-24" }, "anthropic/claude-sonnet-4.5": { "cost": [ @@ -68789,7 +89772,10 @@ 0.3, 3.75 ], + "knowledge": "2025-07-31", "limit": 1000000, + "max_output": 64000, + "released": "2025-09-29", "status": "deprecated" }, "anthropic/claude-sonnet-4.6": { @@ -68799,7 +89785,10 @@ 0.3, 3.75 ], - "limit": 1000000 + "knowledge": "2025-08-31", + "limit": 1000000, + "max_output": 64000, + "released": "2026-02-17" }, "anthropic/claude-sonnet-5": { "cost": [ @@ -68808,7 +89797,10 @@ 0.2, 2.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-30" }, "deepseek/deepseek-chat": { "cost": [ @@ -68817,7 +89809,11 @@ 0.007, 0.0 ], - "limit": 1000000 + "knowledge": "2025-09", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2025-12-01" }, "deepseek/deepseek-reasoner": { "cost": [ @@ -68826,7 +89822,11 @@ 0.0077, 0.0 ], - "limit": 1000000 + "knowledge": "2025-09", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2025-12-01" }, "deepseek/deepseek-v4-flash": { "cost": [ @@ -68835,7 +89835,11 @@ 0.007, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "deepseek/deepseek-v4-flash-0731": { "cost": [ @@ -68844,7 +89848,11 @@ 0.007, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-07-31" }, "deepseek/deepseek-v4-flash-free": { "cost": [ @@ -68853,7 +89861,11 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "deepseek/deepseek-v4-flash-vision-exp": { "cost": [ @@ -68862,7 +89874,10 @@ 0.007, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-08-21" }, "deepseek/deepseek-v4-pro": { "cost": [ @@ -68871,7 +89886,11 @@ 0.022, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "deepseek/deepseek-v4-pro-0813": { "cost": [ @@ -68880,7 +89899,10 @@ 0.022, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-08-13" }, "google/gemini-2.5-flash": { "cost": [ @@ -68889,7 +89911,10 @@ 0.03, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2025-06-17" }, "google/gemini-2.5-flash-lite": { "cost": [ @@ -68898,7 +89923,10 @@ 0.01, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2025-06-17" }, "google/gemini-2.5-pro": { "cost": [ @@ -68907,7 +89935,10 @@ 0.25, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2025-06-17" }, "google/gemini-3-flash-preview": { "cost": [ @@ -68916,7 +89947,10 @@ 0.05, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2025-12-17" }, "google/gemini-3.1-flash-lite": { "cost": [ @@ -68925,7 +89959,10 @@ 0.025, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-05-07" }, "google/gemini-3.1-flash-lite-preview": { "cost": [ @@ -68934,7 +89971,10 @@ 0.025, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-03-03" }, "google/gemini-3.1-pro-preview": { "cost": [ @@ -68943,7 +89983,10 @@ 0.2, 0.0 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2026-02-19", "tiers": [ { "cost": [ @@ -68966,7 +90009,10 @@ 0.4, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-02-19" }, "google/gemini-3.5-flash": { "cost": [ @@ -68975,7 +90021,10 @@ 0.15, 0.08333 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-05-19" }, "google/gemini-3.5-flash-lite": { "cost": [ @@ -68984,7 +90033,10 @@ 0.03, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-07-21" }, "google/gemini-3.6-flash": { "cost": [ @@ -68993,7 +90045,10 @@ 0.075, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-07-21" }, "google/gemini-flash-latest": { "cost": [ @@ -69002,7 +90057,10 @@ 0.1, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-08-13" }, "google/gemini-flash-lite-latest": { "cost": [ @@ -69011,7 +90069,10 @@ 0.025, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-07-21" }, "google/gemini-robotics-er-1.6-preview": { "cost": [ @@ -69020,7 +90081,10 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2025-01", + "limit": 131072, + "max_output": 65536, + "released": "2026-04-14" }, "google/gemma-4-26b-a4b-it": { "cost": [ @@ -69029,7 +90093,10 @@ 0.0075, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-04-02" }, "google/gemma-4-31b-it": { "cost": [ @@ -69038,7 +90105,11 @@ 0.02, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-04-02" }, "grok/grok-4.3": { "cost": [ @@ -69048,6 +90119,8 @@ 0.0 ], "limit": 1000000, + "max_output": 30000, + "released": "2026-04-17", "tiers": [ { "cost": [ @@ -69071,6 +90144,8 @@ 0.0 ], "limit": 500000, + "max_output": 500000, + "released": "2026-07-08", "tiers": [ { "cost": [ @@ -69093,7 +90168,10 @@ 0.5, 0.0 ], + "knowledge": "2026-02-01", "limit": 500000, + "max_output": 500000, + "released": "2026-08-12", "tiers": [ { "cost": [ @@ -69116,7 +90194,11 @@ 0.1, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-01-27" }, "kimi/kimi-k2.6": { "cost": [ @@ -69125,7 +90207,11 @@ 0.16, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-04-20" }, "kimi/kimi-k2.7-code": { "cost": [ @@ -69134,7 +90220,11 @@ 0.19, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-06-12" }, "kimi/kimi-k3": { "cost": [ @@ -69143,7 +90233,10 @@ 0.3, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-16" }, "meta/muse-spark-1.1": { "cost": [ @@ -69152,7 +90245,9 @@ 0.15, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-04-08" }, "meta/muse-spark-1.2": { "cost": [ @@ -69161,7 +90256,9 @@ 0.15, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-08-05" }, "minimax/minimax-m2.5": { "cost": [ @@ -69170,7 +90267,10 @@ 0.03, 0.375 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-02-12" }, "minimax/minimax-m2.5-highspeed": { "cost": [ @@ -69179,7 +90279,10 @@ 0.03, 0.375 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-02-13" }, "minimax/minimax-m2.7": { "cost": [ @@ -69188,7 +90291,10 @@ 0.06, 0.375 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-03-18" }, "minimax/minimax-m2.7-highspeed": { "cost": [ @@ -69197,7 +90303,10 @@ 0.06, 0.375 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-03-18" }, "minimax/minimax-m3": { "cost": [ @@ -69206,7 +90315,10 @@ 0.06, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 512000, + "open": true, + "released": "2026-06-01" }, "openai/gpt-3.5-turbo": { "cost": [ @@ -69215,7 +90327,10 @@ 0.0, 0.0 ], - "limit": 16385 + "knowledge": "2021-09-01", + "limit": 16385, + "max_output": 4096, + "released": "2023-03-01" }, "openai/gpt-4": { "cost": [ @@ -69224,7 +90339,10 @@ 0.0, 0.0 ], - "limit": 8192 + "knowledge": "2023-11", + "limit": 8192, + "max_output": 8192, + "released": "2023-11-06" }, "openai/gpt-4-turbo": { "cost": [ @@ -69233,7 +90351,10 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2023-12", + "limit": 128000, + "max_output": 4096, + "released": "2023-11-06" }, "openai/gpt-4.1": { "cost": [ @@ -69242,7 +90363,10 @@ 0.5, 0.0 ], - "limit": 1047576 + "knowledge": "2024-04", + "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14" }, "openai/gpt-4.1-mini": { "cost": [ @@ -69251,7 +90375,10 @@ 0.1, 0.0 ], - "limit": 1047576 + "knowledge": "2024-04", + "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14" }, "openai/gpt-4.1-nano": { "cost": [ @@ -69260,7 +90387,10 @@ 0.025, 0.0 ], - "limit": 1047576 + "knowledge": "2024-04", + "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14" }, "openai/gpt-4o": { "cost": [ @@ -69269,7 +90399,10 @@ 1.25, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-05-13" }, "openai/gpt-4o-2024-05-13": { "cost": [ @@ -69278,7 +90411,10 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 4096, + "released": "2024-05-13" }, "openai/gpt-4o-2024-08-06": { "cost": [ @@ -69287,7 +90423,10 @@ 1.25, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-08-06" }, "openai/gpt-4o-2024-11-20": { "cost": [ @@ -69296,7 +90435,10 @@ 1.25, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-11-20" }, "openai/gpt-4o-mini": { "cost": [ @@ -69305,7 +90447,10 @@ 0.075, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-07-18" }, "openai/gpt-5": { "cost": [ @@ -69314,7 +90459,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "openai/gpt-5-chat-latest": { "cost": [ @@ -69323,7 +90471,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 100000, + "released": "2025-08-07" }, "openai/gpt-5-mini": { "cost": [ @@ -69332,7 +90483,10 @@ 0.025, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "openai/gpt-5-nano": { "cost": [ @@ -69341,7 +90495,10 @@ 0.005, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "openai/gpt-5-pro": { "cost": [ @@ -69350,7 +90507,10 @@ 0.0, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 272000, + "released": "2025-10-06" }, "openai/gpt-5.1": { "cost": [ @@ -69359,7 +90519,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "openai/gpt-5.1-chat-latest": { "cost": [ @@ -69368,7 +90531,10 @@ 0.125, 0.0 ], - "limit": 128000 + "knowledge": "2024-09-30", + "limit": 128000, + "max_output": 16384, + "released": "2025-11-13" }, "openai/gpt-5.1-codex": { "cost": [ @@ -69377,7 +90543,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "openai/gpt-5.1-codex-mini": { "cost": [ @@ -69386,7 +90555,10 @@ 0.025, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "openai/gpt-5.2": { "cost": [ @@ -69395,7 +90567,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "openai/gpt-5.2-chat-latest": { "cost": [ @@ -69404,7 +90579,10 @@ 0.175, 0.0 ], - "limit": 128000 + "knowledge": "2025-08-31", + "limit": 128000, + "max_output": 16384, + "released": "2025-12-11" }, "openai/gpt-5.2-codex": { "cost": [ @@ -69413,7 +90591,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "openai/gpt-5.2-pro": { "cost": [ @@ -69422,7 +90603,10 @@ 0.0, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "openai/gpt-5.3-codex": { "cost": [ @@ -69431,7 +90615,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-02-05" }, "openai/gpt-5.4": { "cost": [ @@ -69440,7 +90627,10 @@ 0.25, 0.0 ], + "knowledge": "2025-08-31", "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05", "tiers": [ { "cost": [ @@ -69463,7 +90653,10 @@ 0.5, 0.0 ], - "limit": 1050000 + "knowledge": "2025-08-31", + "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05" }, "openai/gpt-5.4-mini": { "cost": [ @@ -69472,7 +90665,10 @@ 0.075, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "openai/gpt-5.4-mini-fast": { "cost": [ @@ -69481,7 +90677,10 @@ 0.15, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "openai/gpt-5.4-nano": { "cost": [ @@ -69490,7 +90689,10 @@ 0.02, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "openai/gpt-5.4-pro": { "cost": [ @@ -69499,7 +90701,10 @@ 0.0, 0.0 ], + "knowledge": "2025-08-31", "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05", "tiers": [ { "cost": [ @@ -69522,7 +90727,10 @@ 0.5, 0.0 ], + "knowledge": "2025-12-01", "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23", "tiers": [ { "cost": [ @@ -69545,7 +90753,10 @@ 1.25, 0.0 ], - "limit": 1050000 + "knowledge": "2025-12-01", + "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23" }, "openai/gpt-5.5-pro": { "cost": [ @@ -69554,7 +90765,10 @@ 0.0, 0.0 ], + "knowledge": "2025-12-01", "limit": 1050000, + "max_output": 100000, + "released": "2026-04-23", "tiers": [ { "cost": [ @@ -69577,7 +90791,10 @@ 0.02, 0.25 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -69600,7 +90817,10 @@ 0.4, 5.0 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -69623,7 +90843,10 @@ 0.2, 2.5 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -69646,7 +90869,11 @@ 0.0, 0.0 ], + "knowledge": "2024-06", "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05", "status": "deprecated" }, "orcarouter/auto": { @@ -69656,7 +90883,9 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 16384, + "released": "2025-01-01" }, "orcarouter/free": { "cost": [ @@ -69665,7 +90894,9 @@ 0.0, 0.0 ], - "limit": 65536 + "limit": 65536, + "max_output": 32768, + "released": "2026-08-27" }, "qwen/qwen3-max": { "cost": [ @@ -69674,7 +90905,10 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 262144, + "max_output": 65536, + "released": "2025-09-23", "tiers": [ { "cost": [ @@ -69709,7 +90943,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2025-03-31", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-09-23" }, "qwen/qwen3-vl-235b-a22b-thinking": { "cost": [ @@ -69718,7 +90956,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2025-03-31", + "limit": 131072, + "max_output": 40960, + "open": true, + "released": "2025-09-23" }, "qwen/qwen3.5-122b-a10b": { "cost": [ @@ -69728,6 +90970,9 @@ 0.0 ], "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-23", "tiers": [ { "cost": [ @@ -69751,6 +90996,9 @@ 0.0 ], "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-23", "tiers": [ { "cost": [ @@ -69774,6 +91022,9 @@ 0.0 ], "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-23", "tiers": [ { "cost": [ @@ -69797,6 +91048,9 @@ 0.0 ], "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-15", "tiers": [ { "cost": [ @@ -69819,7 +91073,9 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 65536, + "released": "2026-02-23" }, "qwen/qwen3.5-plus": { "cost": [ @@ -69828,7 +91084,10 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 1000000, + "max_output": 65536, + "released": "2026-02-16", "tiers": [ { "cost": [ @@ -69851,7 +91110,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-04-17" }, "qwen/qwen3.6-flash": { "cost": [ @@ -69861,6 +91123,8 @@ 0.0 ], "limit": 1000000, + "max_output": 65536, + "released": "2026-04-27", "tiers": [ { "cost": [ @@ -69883,7 +91147,10 @@ 0.0276, 0.345 ], + "knowledge": "2025-04", "limit": 1000000, + "max_output": 65536, + "released": "2026-04-02", "tiers": [ { "cost": [ @@ -69907,6 +91174,8 @@ 0.038 ], "limit": 1000000, + "max_output": 131072, + "released": "2026-07-15", "tiers": [ { "cost": [ @@ -69941,7 +91210,9 @@ 0.25, 1.563 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-05-21" }, "qwen/qwen3.7-plus": { "cost": [ @@ -69950,7 +91221,10 @@ 0.071, 0.0 ], + "knowledge": "2025-04", "limit": 1000000, + "max_output": 64000, + "released": "2026-06-02", "tiers": [ { "cost": [ @@ -69973,7 +91247,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-08-14" }, "qwen/qwen3.8-max": { "cost": [ @@ -69982,7 +91259,9 @@ 0.25, 2.5 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-08-03" }, "tencent/hy3": { "cost": [ @@ -69991,7 +91270,10 @@ 0.059, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 128000, + "open": true, + "released": "2026-07-06" }, "tencent/hy3-free": { "cost": [ @@ -70000,7 +91282,10 @@ 0.0, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 128000, + "open": true, + "released": "2026-07-06" }, "z-ai/glm-4.5": { "cost": [ @@ -70009,7 +91294,11 @@ 0.11, 0.0 ], - "limit": 131072 + "knowledge": "2025-04", + "limit": 131072, + "max_output": 98304, + "open": true, + "released": "2025-07-28" }, "z-ai/glm-4.5-air": { "cost": [ @@ -70018,7 +91307,11 @@ 0.03, 0.0 ], - "limit": 131072 + "knowledge": "2025-04", + "limit": 131072, + "max_output": 98304, + "open": true, + "released": "2025-07-28" }, "z-ai/glm-4.6": { "cost": [ @@ -70027,7 +91320,11 @@ 0.11, 0.0 ], - "limit": 204800 + "knowledge": "2025-04", + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-09-30" }, "z-ai/glm-4.7": { "cost": [ @@ -70036,7 +91333,11 @@ 0.11, 0.0 ], - "limit": 204800 + "knowledge": "2025-04", + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-12-22" }, "z-ai/glm-5": { "cost": [ @@ -70045,7 +91346,10 @@ 0.26, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-02-12" }, "z-ai/glm-5.1": { "cost": [ @@ -70054,7 +91358,10 @@ 0.26, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 131072, + "open": true, + "released": "2026-04-07" }, "z-ai/glm-5.2": { "cost": [ @@ -70063,7 +91370,10 @@ 0.26, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "z-ai/glm-5.3": { "cost": [ @@ -70072,7 +91382,10 @@ 0.234, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "z-ai/glm-5.3-flash": { "cost": [ @@ -70081,7 +91394,10 @@ 0.03, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 128000, + "open": true, + "released": "2026-08-26" }, "z-ai/glm-5.3-flash-free": { "cost": [ @@ -70090,7 +91406,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 128000, + "open": true, + "released": "2026-08-26" } }, "name": "OrcaRouter" @@ -70104,7 +91423,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2025-08-05" }, "gpt-oss-20b": { "cost": [ @@ -70113,7 +91436,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2025-08-05" }, "meta-llama-3_3-70b-instruct": { "cost": [ @@ -70122,7 +91449,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2023-12", + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2024-12-06" }, "mistral-nemo-instruct-2407": { "cost": [ @@ -70131,7 +91462,11 @@ 0.0, 0.0 ], - "limit": 65536 + "knowledge": "2024-07", + "limit": 65536, + "max_output": 65536, + "open": true, + "released": "2024-07-18" }, "mistral-small-3.2-24b-instruct-2506": { "cost": [ @@ -70140,7 +91475,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2023-10-31", + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2025-06-20" }, "qwen2.5-vl-72b-instruct": { "cost": [ @@ -70149,7 +91488,11 @@ 0.0, 0.0 ], - "limit": 32768 + "knowledge": "2024-04", + "limit": 32768, + "max_output": 32768, + "open": true, + "released": "2025-01-26" }, "qwen3.5-397b-a17b": { "cost": [ @@ -70158,7 +91501,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-02-15" }, "qwen3.5-9b": { "cost": [ @@ -70167,7 +91513,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-02-23" }, "qwen3.6-27b": { "cost": [ @@ -70176,7 +91525,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-22" }, "qwen3.8-27b": { "cost": [ @@ -70185,7 +91537,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-08-14" }, "qwen3guard-gen-0.6b": { "cost": [ @@ -70194,7 +91549,10 @@ 0.0, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 16384, + "open": true, + "released": "2026-01-22" }, "qwen3guard-gen-8b": { "cost": [ @@ -70203,7 +91561,10 @@ 0.0, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 16384, + "open": true, + "released": "2026-01-22" } }, "name": "OVHcloud AI Endpoints" @@ -70217,7 +91578,10 @@ 0.012, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-26" } }, "name": "Pareto Inference" @@ -70231,7 +91595,11 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "glm-4.7-flash": { "cost": [ @@ -70240,7 +91608,11 @@ 0.0, 0.0 ], - "limit": 200000 + "knowledge": "2025-04", + "limit": 200000, + "max_output": 131072, + "open": true, + "released": "2026-01-19" }, "gpt-oss:120b": { "cost": [ @@ -70249,7 +91621,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "llama3.3:70b": { "cost": [ @@ -70258,7 +91634,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2023-12", + "limit": 128000, + "max_output": 4096, + "open": true, + "released": "2024-12-06" }, "qwen3-coder:30b": { "cost": [ @@ -70267,7 +91647,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-04", + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2025-07-31" }, "qwen3.6:27b": { "cost": [ @@ -70276,7 +91660,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-04-22" } }, "name": "Pendra" @@ -70290,7 +91677,10 @@ 0.0, 0.0 ], + "knowledge": "2025-09-01", "limit": 128000, + "max_output": 4096, + "released": "2024-01-01", "status": "deprecated" }, "sonar-deep-research": { @@ -70300,7 +91690,11 @@ 0.0, 0.0 ], + "knowledge": "2025-01", "limit": 128000, + "max_output": 32768, + "reasoning": 3.0, + "released": "2025-02-01", "status": "deprecated" }, "sonar-pro": { @@ -70310,7 +91704,10 @@ 0.0, 0.0 ], + "knowledge": "2025-09-01", "limit": 200000, + "max_output": 8192, + "released": "2024-01-01", "status": "deprecated" }, "sonar-reasoning-pro": { @@ -70320,7 +91717,10 @@ 0.0, 0.0 ], + "knowledge": "2025-09-01", "limit": 128000, + "max_output": 4096, + "released": "2024-01-01", "status": "deprecated" } }, @@ -70335,7 +91735,10 @@ 1.0, 12.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-09" }, "anthropic/claude-fable-5-1": { "cost": [ @@ -70344,7 +91747,10 @@ 0.25, 12.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-01" }, "anthropic/claude-haiku-4-5": { "cost": [ @@ -70353,7 +91759,10 @@ 0.1, 1.25 ], - "limit": 200000 + "knowledge": "2025-02-28", + "limit": 200000, + "max_output": 64000, + "released": "2025-10-15" }, "anthropic/claude-haiku-5-5": { "cost": [ @@ -70362,7 +91771,10 @@ 0.01, 0.125 ], + "knowledge": "2026-06", "limit": 1000000, + "max_output": 128000, + "released": "2026-10-07", "tiers": [ { "cost": [ @@ -70385,7 +91797,10 @@ 0.5, 6.25 ], - "limit": 200000 + "knowledge": "2025-03-31", + "limit": 200000, + "max_output": 64000, + "released": "2025-11-24" }, "anthropic/claude-opus-4-6": { "cost": [ @@ -70394,7 +91809,10 @@ 0.5, 6.25 ], - "limit": 200000 + "knowledge": "2025-05-31", + "limit": 200000, + "max_output": 128000, + "released": "2026-02-05" }, "anthropic/claude-opus-4-7": { "cost": [ @@ -70403,7 +91821,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-16" }, "anthropic/claude-opus-5": { "cost": [ @@ -70412,7 +91833,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-05", + "limit": 1000000, + "max_output": 128000, + "released": "2026-07-24" }, "anthropic/claude-opus-5-5": { "cost": [ @@ -70421,7 +91845,10 @@ 0.2, 5.0 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-22" }, "anthropic/claude-sonnet-4-5": { "cost": [ @@ -70430,7 +91857,10 @@ 0.3, 3.75 ], - "limit": 200000 + "knowledge": "2025-07-31", + "limit": 200000, + "max_output": 64000, + "released": "2025-09-29" }, "anthropic/claude-sonnet-4-6": { "cost": [ @@ -70439,7 +91869,10 @@ 0.3, 3.75 ], - "limit": 200000 + "knowledge": "2025-08-31", + "limit": 200000, + "max_output": 64000, + "released": "2026-02-17" }, "anthropic/claude-sonnet-5": { "cost": [ @@ -70448,7 +91881,10 @@ 0.2, 2.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-30" }, "anthropic/claude-sonnet-5-5": { "cost": [ @@ -70457,7 +91893,10 @@ 0.1, 2.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-28" }, "deepseek/deepseek-v4-flash-0731": { "cost": [ @@ -70466,7 +91905,11 @@ 0.028, 0.0 ], + "knowledge": "2025-05", "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-07-31", "status": "deprecated" }, "google/gemini-3-flash-preview": { @@ -70476,7 +91919,10 @@ 0.05, 0.0 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2025-12-17", "tiers": [ { "cost": [ @@ -70499,7 +91945,10 @@ 0.2, 0.0 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2026-02-19", "tiers": [ { "cost": [ @@ -70522,7 +91971,10 @@ 0.15, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-07-21" }, "google/gemini-3.7-flash": { "cost": [ @@ -70531,7 +91983,10 @@ 0.075, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-08-13" }, "google/gemini-3.8-flash": { "cost": [ @@ -70540,7 +91995,9 @@ 0.075, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65536, + "released": "2026-09-02" }, "google/gemini-4-argon": { "cost": [ @@ -70549,7 +92006,10 @@ 0.1, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-10-13" }, "moonshot-ai/kimi-k2.7-code": { "cost": [ @@ -70558,7 +92018,11 @@ 0.19, 0.0 ], + "knowledge": "2025-01", "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-06-12", "status": "deprecated" }, "moonshot-ai/kimi-k3": { @@ -70569,6 +92033,9 @@ 0.0 ], "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-16", "status": "deprecated" }, "nvidia/nemotron-3-super-120b-a12b": { @@ -70578,7 +92045,11 @@ 0.0, 0.0 ], + "knowledge": "2026-02", "limit": 1000000, + "max_output": 32000, + "open": true, + "released": "2026-03-11", "status": "deprecated" }, "openai/gpt-5-mini": { @@ -70588,7 +92059,10 @@ 0.025, 0.0 ], + "knowledge": "2024-05-30", "limit": 400000, + "max_output": 128000, + "released": "2025-08-07", "status": "deprecated" }, "openai/gpt-5.1": { @@ -70598,7 +92072,10 @@ 0.125, 0.0 ], + "knowledge": "2024-09-30", "limit": 400000, + "max_output": 128000, + "released": "2025-11-13", "status": "deprecated" }, "openai/gpt-5.2": { @@ -70608,7 +92085,10 @@ 0.175, 0.0 ], + "knowledge": "2025-08-31", "limit": 400000, + "max_output": 128000, + "released": "2025-12-11", "status": "deprecated" }, "openai/gpt-5.4": { @@ -70618,7 +92098,10 @@ 0.25, 0.0 ], + "knowledge": "2025-08-31", "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05", "status": "deprecated" }, "openai/gpt-5.5": { @@ -70628,7 +92111,10 @@ 0.5, 0.0 ], - "limit": 1050000 + "knowledge": "2025-12-01", + "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23" }, "openai/gpt-5.6-luna": { "cost": [ @@ -70637,7 +92123,10 @@ 0.02, 0.25 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -70660,7 +92149,10 @@ 0.4, 5.0 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -70683,7 +92175,10 @@ 0.2, 2.5 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -70706,7 +92201,10 @@ 1.0, 12.5 ], + "knowledge": "2026-04-30", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-04", "tiers": [ { "cost": [ @@ -70729,7 +92227,10 @@ 0.01, 0.125 ], + "knowledge": "2026-05-18", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -70752,7 +92253,10 @@ 0.2, 2.5 ], + "knowledge": "2026-04-20", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -70775,7 +92279,10 @@ 0.1, 2.5 ], + "knowledge": "2026-04-30", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-29", "tiers": [ { "cost": [ @@ -70798,7 +92305,10 @@ 0.044, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-08-13" }, "perplexity/glm-5.3": { "cost": [ @@ -70807,7 +92317,10 @@ 0.26, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "perplexity/glm-5.3-flash": { "cost": [ @@ -70816,7 +92329,10 @@ 0.03, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-26" }, "perplexity/kimi-k3": { "cost": [ @@ -70825,7 +92341,10 @@ 0.3, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-16" }, "perplexity/nemotron-3.5-super-120b-a12b": { "cost": [ @@ -70834,7 +92353,10 @@ 0.04, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-10-15" }, "perplexity/sonar": { "cost": [ @@ -70843,7 +92365,10 @@ 0.0625, 0.0 ], - "limit": 128000 + "knowledge": "2025-09-01", + "limit": 128000, + "max_output": 8192, + "released": "2024-01-01" }, "xai/grok-4-1-fast-non-reasoning": { "cost": [ @@ -70852,7 +92377,10 @@ 0.05, 0.0 ], + "knowledge": "2025-07", "limit": 2000000, + "max_output": 30000, + "released": "2025-11-19", "status": "deprecated" }, "xai/grok-4.5": { @@ -70863,6 +92391,8 @@ 0.0 ], "limit": 500000, + "max_output": 500000, + "released": "2026-07-08", "tiers": [ { "cost": [ @@ -70885,7 +92415,10 @@ 0.5, 0.0 ], + "knowledge": "2026-02-01", "limit": 500000, + "max_output": 500000, + "released": "2026-08-12", "tiers": [ { "cost": [ @@ -70908,7 +92441,10 @@ 0.5, 2.0 ], + "knowledge": "2026-05", "limit": 500000, + "max_output": 500000, + "released": "2026-09-21", "tiers": [ { "cost": [ @@ -70936,7 +92472,10 @@ 1.1, 13.75 ], + "knowledge": "2026-01-31", "limit": 1000000, + "max_output": 128000, + "released": "2026-06-09", "status": "deprecated" }, "claude-haiku-4-5": { @@ -70946,7 +92485,10 @@ 0.1, 1.25 ], + "knowledge": "2025-02-28", "limit": 200000, + "max_output": 64000, + "released": "2025-10-15", "status": "deprecated" }, "claude-opus-5": { @@ -70956,7 +92498,10 @@ 0.5, 6.25 ], + "knowledge": "2026-05", "limit": 1000000, + "max_output": 128000, + "released": "2026-07-24", "status": "deprecated" }, "claude-opus-5-fast": { @@ -70966,7 +92511,10 @@ 1.0, 12.5 ], + "knowledge": "2026-05", "limit": 1000000, + "max_output": 128000, + "released": "2026-07-24", "status": "deprecated" }, "claude-sonnet-5": { @@ -70976,7 +92524,10 @@ 0.2, 2.5 ], + "knowledge": "2026-01-31", "limit": 1000000, + "max_output": 128000, + "released": "2026-06-30", "status": "deprecated" }, "deepseek-ai/DeepSeek-V4-Flash": { @@ -70986,7 +92537,11 @@ 0.0197, 0.1 ], + "knowledge": "2025-05", "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-04-24", "status": "deprecated" }, "fastino/GLiNER-2.5-Decide": { @@ -70996,7 +92551,10 @@ 0.03, 0.03 ], - "limit": 8192 + "limit": 8192, + "max_output": 8192, + "open": true, + "released": "2026-09-24" }, "fastino/gliguard-LLMGuardrails-300M": { "cost": [ @@ -71005,7 +92563,10 @@ 0.15, 0.15 ], - "limit": 8192 + "limit": 8192, + "max_output": 8192, + "open": true, + "released": "2026-04-30" }, "fastino/gliguard-PII-multi": { "cost": [ @@ -71014,7 +92575,10 @@ 0.15, 0.15 ], - "limit": 8192 + "limit": 8192, + "max_output": 8192, + "open": true, + "released": "2026-07-08" }, "fastino/gliner2-base-v1": { "cost": [ @@ -71023,7 +92587,10 @@ 0.03, 0.03 ], - "limit": 2048 + "limit": 2048, + "max_output": 2048, + "open": true, + "released": "2025-06-30" }, "fastino/gliner2-large-v1": { "cost": [ @@ -71032,7 +92599,10 @@ 0.03, 0.03 ], - "limit": 8192 + "limit": 8192, + "max_output": 8192, + "open": true, + "released": "2025-06-30" }, "fastino/gliner2-multi-large-v1": { "cost": [ @@ -71041,7 +92611,10 @@ 0.03, 0.03 ], - "limit": 8192 + "limit": 8192, + "max_output": 8192, + "open": true, + "released": "2025-11-30" }, "fastino/gliner2-multi-v1": { "cost": [ @@ -71050,7 +92623,10 @@ 0.03, 0.03 ], - "limit": 8192 + "limit": 8192, + "max_output": 8192, + "open": true, + "released": "2025-11-30" }, "fastino/gliner2-privacy-filter-PII-multi": { "cost": [ @@ -71059,7 +92635,10 @@ 0.03, 0.03 ], - "limit": 8192 + "limit": 8192, + "max_output": 8192, + "open": true, + "released": "2026-04-30" }, "fastino/gliner2.5-base-v1": { "cost": [ @@ -71068,7 +92647,10 @@ 0.03, 0.03 ], - "limit": 4096 + "limit": 4096, + "max_output": 4096, + "open": true, + "released": "2026-08-24" }, "fastino/gliner2.5-multi-v1": { "cost": [ @@ -71077,7 +92659,10 @@ 0.03, 0.03 ], - "limit": 4096 + "limit": 4096, + "max_output": 4096, + "open": true, + "released": "2026-08-24" }, "gpt-5.5": { "cost": [ @@ -71086,7 +92671,10 @@ 0.5, 5.0 ], + "knowledge": "2025-12-01", "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23", "status": "deprecated" }, "gpt-5.6-luna": { @@ -71096,7 +92684,10 @@ 0.1, 1.25 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "status": "deprecated" }, "gpt-5.6-sol": { @@ -71106,7 +92697,10 @@ 0.5, 6.25 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "status": "deprecated" }, "gpt-5.6-terra": { @@ -71116,7 +92710,10 @@ 0.25, 3.125 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "status": "deprecated" }, "moonshotai/Kimi-K3": { @@ -71127,6 +92724,9 @@ 3.0 ], "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-07-16", "status": "deprecated" }, "moonshotai/Kimi-K3-Fast": { @@ -71137,6 +92737,9 @@ 4.5 ], "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-07-16", "status": "deprecated" }, "nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16": { @@ -71146,7 +92749,11 @@ 0.035, 0.07 ], - "limit": 65536 + "knowledge": "2025-09", + "limit": 65536, + "max_output": 4096, + "open": true, + "released": "2026-08-11" }, "nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4": { "cost": [ @@ -71155,7 +92762,10 @@ 0.04, 0.08 ], - "limit": 262144 + "limit": 262144, + "max_output": 4096, + "open": true, + "released": "2026-10-15" }, "zai-org/GLM-5.2": { "cost": [ @@ -71165,6 +92775,9 @@ 1.4 ], "limit": 1040000, + "max_output": 128000, + "open": true, + "released": "2026-06-13", "status": "deprecated" } }, @@ -71179,7 +92792,10 @@ 0.021, 0.26 ], + "knowledge": "2023-08-31", "limit": 189096, + "max_output": 8192, + "released": "2024-03-13", "status": "deprecated" }, "anthropic/claude-haiku-3.5": { @@ -71189,7 +92805,10 @@ 0.068, 0.85 ], + "knowledge": "2024-07-31", "limit": 189096, + "max_output": 8192, + "released": "2024-10-22", "status": "deprecated" }, "anthropic/claude-haiku-4.5": { @@ -71199,7 +92818,10 @@ 0.0859, 1.0732 ], - "limit": 192000 + "knowledge": "2025-02-28", + "limit": 192000, + "max_output": 64000, + "released": "2025-10-15" }, "anthropic/claude-opus-4": { "cost": [ @@ -71208,7 +92830,10 @@ 1.3, 16.0 ], + "knowledge": "2025-03-31", "limit": 192512, + "max_output": 28672, + "released": "2025-05-22", "status": "deprecated" }, "anthropic/claude-opus-4.1": { @@ -71218,7 +92843,10 @@ 1.3, 16.0 ], + "knowledge": "2025-03-31", "limit": 196608, + "max_output": 32000, + "released": "2025-08-05", "status": "deprecated" }, "anthropic/claude-opus-4.5": { @@ -71228,7 +92856,10 @@ 0.4293, 5.3662 ], - "limit": 196608 + "knowledge": "2025-05", + "limit": 196608, + "max_output": 64000, + "released": "2025-11-24" }, "anthropic/claude-opus-4.6": { "cost": [ @@ -71237,7 +92868,10 @@ 0.4293, 5.3662 ], - "limit": 983040 + "knowledge": "2025-05-31", + "limit": 983040, + "max_output": 128000, + "released": "2026-02-05" }, "anthropic/claude-opus-4.7": { "cost": [ @@ -71246,7 +92880,10 @@ 0.4293, 5.3662 ], - "limit": 1048576 + "knowledge": "2026-01-31", + "limit": 1048576, + "max_output": 128000, + "released": "2026-04-16" }, "anthropic/claude-opus-4.8": { "cost": [ @@ -71255,7 +92892,10 @@ 0.4293, 5.3662 ], - "limit": 1048576 + "knowledge": "2026-01", + "limit": 1048576, + "max_output": 128000, + "released": "2026-05-28" }, "anthropic/claude-sonnet-3.5": { "cost": [ @@ -71264,7 +92904,10 @@ 0.26, 3.2 ], + "knowledge": "2024-04-30", "limit": 189096, + "max_output": 8192, + "released": "2024-10-22", "status": "deprecated" }, "anthropic/claude-sonnet-3.5-june": { @@ -71275,6 +92918,8 @@ 3.2 ], "limit": 189096, + "max_output": 8192, + "released": "2024-11-18", "status": "deprecated" }, "anthropic/claude-sonnet-3.7": { @@ -71284,7 +92929,10 @@ 0.26, 3.2 ], + "knowledge": "2024-10-31", "limit": 196608, + "max_output": 128000, + "released": "2025-02-19", "status": "deprecated" }, "anthropic/claude-sonnet-4": { @@ -71294,7 +92942,10 @@ 0.26, 3.2 ], + "knowledge": "2025-03-31", "limit": 983040, + "max_output": 64000, + "released": "2025-05-22", "status": "deprecated" }, "anthropic/claude-sonnet-4.5": { @@ -71304,7 +92955,10 @@ 0.2576, 3.2197 ], - "limit": 983040 + "knowledge": "2025-07-31", + "limit": 983040, + "max_output": 32768, + "released": "2025-09-29" }, "anthropic/claude-sonnet-4.6": { "cost": [ @@ -71313,7 +92967,10 @@ 0.2576, 3.2197 ], - "limit": 983040 + "knowledge": "2025-08-31", + "limit": 983040, + "max_output": 128000, + "released": "2026-02-17" }, "cerebras/gpt-oss-120b-cs": { "cost": [ @@ -71322,7 +92979,10 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-06", + "limit": 128000, + "open": true, + "released": "2025-08-05" }, "cerebras/llama-3.1-8b-cs": { "cost": [ @@ -71331,7 +92991,10 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2023-12", + "limit": 128000, + "open": true, + "released": "2024-07-23" }, "empiriolabs/deepseek-v4-flash-el": { "cost": [ @@ -71340,7 +93003,11 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "empiriolabs/deepseek-v4-pro-el": { "cost": [ @@ -71349,7 +93016,11 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "fireworks-ai/kimi-k2.5-fw": { "cost": [ @@ -71358,7 +93029,11 @@ 0.0, 0.0 ], + "knowledge": "2025-01", "limit": 262144, + "max_output": 16384, + "open": true, + "released": "2026-01-27", "status": "deprecated" }, "google/gemini-2.0-flash": { @@ -71368,7 +93043,10 @@ 0.0, 0.0 ], + "knowledge": "2024-06", "limit": 990000, + "max_output": 8192, + "released": "2024-12-11", "status": "deprecated" }, "google/gemini-2.0-flash-lite": { @@ -71378,7 +93056,10 @@ 0.0, 0.0 ], + "knowledge": "2024-06", "limit": 990000, + "max_output": 8192, + "released": "2024-12-11", "status": "deprecated" }, "google/gemini-2.5-flash": { @@ -71388,7 +93069,10 @@ 0.021, 0.0 ], + "knowledge": "2025-01", "limit": 1065535, + "max_output": 65535, + "released": "2025-06-17", "status": "deprecated" }, "google/gemini-2.5-flash-lite": { @@ -71398,7 +93082,10 @@ 0.0, 0.0 ], + "knowledge": "2025-01", "limit": 1024000, + "max_output": 64000, + "released": "2025-06-17", "status": "deprecated" }, "google/gemini-2.5-pro": { @@ -71408,7 +93095,10 @@ 0.087, 0.0 ], + "knowledge": "2025-01", "limit": 1065535, + "max_output": 65535, + "released": "2025-06-17", "status": "deprecated" }, "google/gemini-3-flash": { @@ -71418,7 +93108,10 @@ 0.0404, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2025-12-17" }, "google/gemini-3.1-flash-lite": { "cost": [ @@ -71427,7 +93120,10 @@ 0.0, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-05-07" }, "google/gemini-3.1-pro": { "cost": [ @@ -71436,7 +93132,10 @@ 0.202, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-02-19" }, "google/gemini-3.5-flash": { "cost": [ @@ -71445,7 +93144,10 @@ 0.1515, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-05-19" }, "google/gemini-3.5-flash-lite": { "cost": [ @@ -71454,7 +93156,10 @@ 0.0303, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-07-21" }, "google/gemini-3.6-flash": { "cost": [ @@ -71463,7 +93168,10 @@ 0.0758, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-07-21" }, "google/gemini-3.7-flash": { "cost": [ @@ -71472,7 +93180,10 @@ 0.0758, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-08-13" }, "google/gemini-3.8-flash": { "cost": [ @@ -71481,7 +93192,9 @@ 0.0758, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65536, + "released": "2026-09-02" }, "google/gemini-deep-research": { "cost": [ @@ -71491,6 +93204,7 @@ 0.0 ], "limit": 1048576, + "released": "2025-12-11", "status": "deprecated" }, "google/gemini-omni-1.1-flash": { @@ -71500,7 +93214,10 @@ 0.0, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 57920, + "released": "2026-08-27", + "type": "video" }, "google/gemma-4-31b": { "cost": [ @@ -71509,7 +93226,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 8192, + "open": true, + "released": "2026-04-02" }, "google/nano-banana": { "cost": [ @@ -71518,8 +93239,11 @@ 0.021, 0.0 ], + "knowledge": "2024-06", "limit": 65536, - "status": "deprecated" + "released": "2025-08-26", + "status": "deprecated", + "type": "image" }, "google/nano-banana-pro": { "cost": [ @@ -71528,7 +93252,10 @@ 0.202, 0.0 ], - "limit": 65536 + "knowledge": "2025-01", + "limit": 65536, + "released": "2025-11-20", + "type": "image" }, "novita/deepseek-v3.2": { "cost": [ @@ -71537,7 +93264,10 @@ 0.1313, 0.0 ], - "limit": 128000 + "knowledge": "2024-07", + "limit": 128000, + "open": true, + "released": "2025-12-01" }, "novita/glm-4.6": { "cost": [ @@ -71545,7 +93275,10 @@ 2.2222, 0.1111, 0.0 - ] + ], + "knowledge": "2025-04", + "open": true, + "released": "2025-09-30" }, "novita/glm-4.7-flash": { "cost": [ @@ -71554,7 +93287,11 @@ 0.0, 0.0 ], - "limit": 200000 + "knowledge": "2025-04", + "limit": 200000, + "max_output": 65500, + "open": true, + "released": "2026-01-19" }, "novita/glm-5": { "cost": [ @@ -71563,7 +93300,10 @@ 0.2, 0.0 ], - "limit": 205000 + "limit": 205000, + "max_output": 131072, + "open": true, + "released": "2026-02-12" }, "novita/kimi-k2.5": { "cost": [ @@ -71572,7 +93312,11 @@ 0.1, 0.0 ], + "knowledge": "2025-01", "limit": 128000, + "max_output": 262144, + "open": true, + "released": "2026-01-27", "status": "deprecated" }, "novita/kimi-k2.6": { @@ -71582,7 +93326,11 @@ 0.1616, 0.0 ], - "limit": 262144 + "knowledge": "2025-04", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-20" }, "novita/minimax-m2.1": { "cost": [ @@ -71591,7 +93339,10 @@ 0.1515, 0.0 ], - "limit": 205000 + "limit": 205000, + "max_output": 131072, + "open": true, + "released": "2025-12-23" }, "openai/chatgpt-4o-latest": { "cost": [ @@ -71601,6 +93352,8 @@ 0.0 ], "limit": 128000, + "max_output": 8192, + "released": "2024-08-14", "status": "deprecated" }, "openai/gpt-3.5-turbo": { @@ -71610,7 +93363,10 @@ 0.0, 0.0 ], + "knowledge": "2021-09-01", "limit": 16384, + "max_output": 2048, + "released": "2023-03-01", "status": "deprecated" }, "openai/gpt-3.5-turbo-instruct": { @@ -71621,6 +93377,8 @@ 0.0 ], "limit": 3500, + "max_output": 1024, + "released": "2023-09-20", "status": "deprecated" }, "openai/gpt-3.5-turbo-raw": { @@ -71630,7 +93388,10 @@ 0.0, 0.0 ], + "knowledge": "2021-09-01", "limit": 4524, + "max_output": 2048, + "released": "2023-03-01", "status": "deprecated" }, "openai/gpt-4-turbo": { @@ -71640,7 +93401,10 @@ 0.0, 0.0 ], + "knowledge": "2023-12", "limit": 128000, + "max_output": 4096, + "released": "2023-11-06", "status": "deprecated" }, "openai/gpt-4.1": { @@ -71650,7 +93414,10 @@ 0.4545, 0.0 ], - "limit": 1047576 + "knowledge": "2024-04", + "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14" }, "openai/gpt-4.1-mini": { "cost": [ @@ -71659,7 +93426,10 @@ 0.0909, 0.0 ], - "limit": 1047576 + "knowledge": "2024-04", + "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14" }, "openai/gpt-4.1-nano": { "cost": [ @@ -71668,7 +93438,10 @@ 0.022, 0.0 ], + "knowledge": "2024-04", "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14", "status": "deprecated" }, "openai/gpt-4o-aug": { @@ -71678,7 +93451,10 @@ 1.1364, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 8192, + "released": "2024-08-06" }, "openai/gpt-4o-mini": { "cost": [ @@ -71687,7 +93463,10 @@ 0.0682, 0.0 ], - "limit": 124096 + "knowledge": "2023-09", + "limit": 124096, + "max_output": 4096, + "released": "2024-07-18" }, "openai/gpt-4o-mini-search": { "cost": [ @@ -71697,6 +93476,8 @@ 0.0 ], "limit": 128000, + "max_output": 8192, + "released": "2025-03-11", "status": "deprecated" }, "openai/gpt-4o-search": { @@ -71706,7 +93487,9 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 8192, + "released": "2025-03-11" }, "openai/gpt-5": { "cost": [ @@ -71715,7 +93498,10 @@ 0.1136, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "openai/gpt-5-chat": { "cost": [ @@ -71724,7 +93510,10 @@ 0.11, 0.0 ], + "knowledge": "2024-09-30", "limit": 128000, + "max_output": 16384, + "released": "2025-08-07", "status": "deprecated" }, "openai/gpt-5-codex": { @@ -71734,7 +93523,10 @@ 0.0, 0.0 ], + "knowledge": "2024-09-30", "limit": 400000, + "max_output": 128000, + "released": "2025-09-15", "status": "deprecated" }, "openai/gpt-5-mini": { @@ -71744,7 +93536,10 @@ 0.0227, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "openai/gpt-5-nano": { "cost": [ @@ -71753,7 +93548,10 @@ 0.0045, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "openai/gpt-5-pro": { "cost": [ @@ -71762,7 +93560,10 @@ 0.0, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-10-06" }, "openai/gpt-5.1": { "cost": [ @@ -71771,7 +93572,10 @@ 0.1136, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "openai/gpt-5.1-codex": { "cost": [ @@ -71780,7 +93584,10 @@ 0.11, 0.0 ], + "knowledge": "2024-09-30", "limit": 400000, + "max_output": 128000, + "released": "2025-11-13", "status": "deprecated" }, "openai/gpt-5.1-codex-max": { @@ -71790,7 +93597,10 @@ 0.11, 0.0 ], + "knowledge": "2024-09-30", "limit": 400000, + "max_output": 128000, + "released": "2025-11-13", "status": "deprecated" }, "openai/gpt-5.1-codex-mini": { @@ -71800,7 +93610,10 @@ 0.022, 0.0 ], + "knowledge": "2024-09-30", "limit": 400000, + "max_output": 128000, + "released": "2025-11-13", "status": "deprecated" }, "openai/gpt-5.1-instant": { @@ -71810,7 +93623,10 @@ 0.11, 0.0 ], + "knowledge": "2024-09-30", "limit": 128000, + "max_output": 16384, + "released": "2025-11-13", "status": "deprecated" }, "openai/gpt-5.2": { @@ -71820,7 +93636,10 @@ 0.1591, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "openai/gpt-5.2-codex": { "cost": [ @@ -71829,7 +93648,10 @@ 0.16, 0.0 ], + "knowledge": "2025-08-31", "limit": 400000, + "max_output": 128000, + "released": "2025-12-11", "status": "deprecated" }, "openai/gpt-5.2-instant": { @@ -71839,7 +93661,10 @@ 0.16, 0.0 ], + "knowledge": "2025-08-31", "limit": 128000, + "max_output": 16384, + "released": "2025-12-11", "status": "deprecated" }, "openai/gpt-5.2-pro": { @@ -71849,7 +93674,10 @@ 0.0, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "openai/gpt-5.3-codex": { "cost": [ @@ -71858,7 +93686,10 @@ 0.1591, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-02-05" }, "openai/gpt-5.3-codex-spark": { "cost": [ @@ -71867,7 +93698,10 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2025-08-31", + "limit": 128000, + "max_output": 16384, + "released": "2026-02-05" }, "openai/gpt-5.3-instant": { "cost": [ @@ -71876,7 +93710,10 @@ 0.16, 0.0 ], + "knowledge": "2025-08-31", "limit": 128000, + "max_output": 16384, + "released": "2026-03-03", "status": "deprecated" }, "openai/gpt-5.4": { @@ -71886,7 +93723,10 @@ 0.2273, 0.0 ], - "limit": 1050000 + "knowledge": "2025-08-31", + "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05" }, "openai/gpt-5.4-mini": { "cost": [ @@ -71895,7 +93735,10 @@ 0.0682, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "openai/gpt-5.4-nano": { "cost": [ @@ -71904,7 +93747,10 @@ 0.0182, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "openai/gpt-5.4-pro": { "cost": [ @@ -71913,7 +93759,10 @@ 0.0, 0.0 ], - "limit": 1050000 + "knowledge": "2025-08-31", + "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05" }, "openai/gpt-5.5": { "cost": [ @@ -71922,7 +93771,10 @@ 0.4545, 0.0 ], - "limit": 400000 + "knowledge": "2025-12-01", + "limit": 400000, + "max_output": 128000, + "released": "2026-04-23" }, "openai/gpt-5.5-pro": { "cost": [ @@ -71931,7 +93783,10 @@ 0.0, 0.0 ], - "limit": 400000 + "knowledge": "2025-12-01", + "limit": 400000, + "max_output": 128000, + "released": "2026-04-23" }, "openai/gpt-image-2": { "cost": [ @@ -71939,7 +93794,9 @@ 30.303, 1.2626, 0.0 - ] + ], + "released": "2026-04-21", + "type": "image" }, "openai/o1": { "cost": [ @@ -71948,7 +93805,10 @@ 0.0, 0.0 ], + "knowledge": "2023-09", "limit": 200000, + "max_output": 100000, + "released": "2024-12-05", "status": "deprecated" }, "openai/o1-pro": { @@ -71958,7 +93818,10 @@ 0.0, 0.0 ], + "knowledge": "2023-09", "limit": 200000, + "max_output": 100000, + "released": "2025-03-19", "status": "deprecated" }, "openai/o3": { @@ -71968,7 +93831,10 @@ 0.4545, 0.0 ], - "limit": 200000 + "knowledge": "2024-05", + "limit": 200000, + "max_output": 100000, + "released": "2025-04-16" }, "openai/o3-deep-research": { "cost": [ @@ -71977,7 +93843,10 @@ 2.2, 0.0 ], + "knowledge": "2024-05", "limit": 200000, + "max_output": 100000, + "released": "2025-06-26", "status": "deprecated" }, "openai/o3-mini": { @@ -71987,7 +93856,10 @@ 0.0, 0.0 ], + "knowledge": "2024-05", "limit": 200000, + "max_output": 100000, + "released": "2024-12-20", "status": "deprecated" }, "openai/o3-mini-high": { @@ -71997,7 +93869,10 @@ 0.0, 0.0 ], + "knowledge": "2024-05", "limit": 200000, + "max_output": 100000, + "released": "2024-12-20", "status": "deprecated" }, "openai/o3-pro": { @@ -72007,7 +93882,10 @@ 0.0, 0.0 ], - "limit": 200000 + "knowledge": "2024-05", + "limit": 200000, + "max_output": 100000, + "released": "2025-06-10" }, "openai/o4-mini": { "cost": [ @@ -72016,7 +93894,10 @@ 0.25, 0.0 ], + "knowledge": "2024-05", "limit": 200000, + "max_output": 100000, + "released": "2025-04-16", "status": "deprecated" }, "openai/o4-mini-deep-research": { @@ -72026,7 +93907,10 @@ 0.45, 0.0 ], + "knowledge": "2024-05", "limit": 200000, + "max_output": 100000, + "released": "2025-06-26", "status": "deprecated" }, "xai/grok-3": { @@ -72036,7 +93920,9 @@ 0.75, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 8192, + "released": "2025-04-11" }, "xai/grok-3-mini": { "cost": [ @@ -72045,7 +93931,9 @@ 0.075, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 8192, + "released": "2025-04-11" }, "xai/grok-4": { "cost": [ @@ -72055,6 +93943,8 @@ 0.0 ], "limit": 256000, + "max_output": 128000, + "released": "2025-07-10", "status": "deprecated" }, "xai/grok-4-fast-non-reasoning": { @@ -72065,6 +93955,8 @@ 0.0 ], "limit": 2000000, + "max_output": 128000, + "released": "2025-12-18", "status": "deprecated" }, "xai/grok-4-fast-reasoning": { @@ -72075,6 +93967,8 @@ 0.0 ], "limit": 2000000, + "max_output": 128000, + "released": "2025-12-18", "status": "deprecated" }, "xai/grok-4.20-multi-agent": { @@ -72084,7 +93978,8 @@ 0.202, 0.0 ], - "limit": 128000 + "limit": 128000, + "released": "2026-03-13" }, "xai/grok-code-fast-1": { "cost": [ @@ -72093,7 +93988,9 @@ 0.02, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 128000, + "released": "2025-09-02" } }, "name": "Poe" @@ -72107,7 +94004,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-04-28" }, "poolside/laguna-s-2.1": { "cost": [ @@ -72116,7 +94016,10 @@ 0.0, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 32768, + "open": true, + "released": "2026-07-21" }, "poolside/laguna-xs-2.1": { "cost": [ @@ -72125,7 +94028,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-07-02" } }, "name": "Poolside" @@ -72139,7 +94045,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-09" }, "anthropic/claude-fable-5.1": { "cost": [ @@ -72148,7 +94057,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-01" }, "anthropic/claude-opus-4.6": { "cost": [ @@ -72157,7 +94069,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-05" }, "anthropic/claude-opus-4.7": { "cost": [ @@ -72166,7 +94081,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-16" }, "anthropic/claude-opus-4.8": { "cost": [ @@ -72175,7 +94093,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2026-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-28" }, "anthropic/claude-opus-5": { "cost": [ @@ -72184,7 +94105,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2026-05", + "limit": 1000000, + "max_output": 128000, + "released": "2026-07-24" }, "anthropic/claude-opus-5.5": { "cost": [ @@ -72193,7 +94117,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-22" }, "anthropic/claude-sonnet-4.6": { "cost": [ @@ -72202,7 +94129,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-08-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-17" }, "anthropic/claude-sonnet-5": { "cost": [ @@ -72211,7 +94141,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-30" }, "anthropic/claude-sonnet-5.5": { "cost": [ @@ -72220,7 +94153,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-28" }, "deepseek/deepseek-v4-flash": { "cost": [ @@ -72229,7 +94165,11 @@ 0.0, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 943717, + "open": true, + "released": "2026-04-24" }, "deepseek/deepseek-v4-flash-0731": { "cost": [ @@ -72238,7 +94178,11 @@ 0.0, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 943718, + "open": true, + "released": "2026-07-31" }, "deepseek/deepseek-v4-pro": { "cost": [ @@ -72247,16 +94191,24 @@ 0.0, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "deepseek/deepseek-v4.1-flash": { "cost": [ 0.3, 1.2, - 0.03, + 0.006, 0.3 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-09-10" }, "deepseek/deepseek-v4.1-flash-1017": { "cost": [ @@ -72265,7 +94217,11 @@ 0.006, 0.3 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-10-17" }, "google/gemini-3-flash-preview": { "cost": [ @@ -72274,7 +94230,10 @@ 0.0, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2025-12-17" }, "google/gemini-3.1-pro-preview": { "cost": [ @@ -72283,7 +94242,10 @@ 0.0, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-02-19" }, "google/gemini-3.5-flash": { "cost": [ @@ -72292,7 +94254,10 @@ 0.0, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-05-19" }, "google/gemini-3.6-flash": { "cost": [ @@ -72301,7 +94266,10 @@ 0.0, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-07-21" }, "google/gemini-3.7-flash": { "cost": [ @@ -72310,7 +94278,10 @@ 0.0, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-08-13" }, "google/gemini-3.8-flash": { "cost": [ @@ -72319,7 +94290,9 @@ 0.0, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65536, + "released": "2026-09-02" }, "google/gemini-4-argon": { "cost": [ @@ -72328,7 +94301,10 @@ 0.0, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 943718, + "released": "2026-10-13" }, "google/gemma-3-27b-it": { "cost": [ @@ -72337,7 +94313,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-08", + "limit": 131072, + "max_output": 117964, + "open": true, + "released": "2025-03-12" }, "meta-llama/llama-3.3-70b-instruct": { "cost": [ @@ -72346,7 +94326,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2023-12", + "limit": 131072, + "max_output": 16384, + "open": true, + "released": "2024-12-06" }, "meta/muse-spark-open": { "cost": [ @@ -72355,7 +94339,11 @@ 0.0, 0.0 ], - "limit": 1048576 + "knowledge": "2026-01-04", + "limit": 1048576, + "max_output": 943718, + "open": true, + "released": "2026-10-15" }, "mistralai/mistral-large-2512": { "cost": [ @@ -72364,7 +94352,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2024-11", + "limit": 262144, + "max_output": 209715, + "open": true, + "released": "2025-12-02" }, "mistralai/mistral-nemo": { "cost": [ @@ -72373,7 +94365,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-07", + "limit": 131072, + "max_output": 16384, + "open": true, + "released": "2024-07-18" }, "mistralai/mistral-small-2603": { "cost": [ @@ -72382,7 +94378,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-06", + "limit": 262144, + "max_output": 209715, + "open": true, + "released": "2026-03-16" }, "mistralai/mixtral-8x22b-instruct": { "cost": [ @@ -72391,7 +94391,11 @@ 0.0, 0.0 ], - "limit": 65536 + "knowledge": "2024-01-31", + "limit": 65536, + "max_output": 52428, + "open": true, + "released": "2024-04-17" }, "moonshotai/kimi-k2-0905": { "cost": [ @@ -72400,7 +94404,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 98304, + "open": true, + "released": "2025-09-05" }, "moonshotai/kimi-k3": { "cost": [ @@ -72409,7 +94416,21 @@ 0.0, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 943718, + "open": true, + "released": "2026-07-16" + }, + "moonshotai/kimi-k3.1-pro": { + "cost": [ + 2.0, + 10.0, + 0.0, + 0.0 + ], + "limit": 1048576, + "max_output": 943718, + "released": "2026-10-23" }, "openai/gpt-4.1": { "cost": [ @@ -72418,7 +94439,10 @@ 0.0, 0.0 ], - "limit": 1047576 + "knowledge": "2024-04", + "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14" }, "openai/gpt-4.1-mini": { "cost": [ @@ -72427,7 +94451,10 @@ 0.0, 0.0 ], - "limit": 1047576 + "knowledge": "2024-04", + "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14" }, "openai/gpt-4.1-nano": { "cost": [ @@ -72436,7 +94463,10 @@ 0.0, 0.0 ], - "limit": 1047576 + "knowledge": "2024-04", + "limit": 1047576, + "max_output": 942818, + "released": "2025-04-14" }, "openai/gpt-4o": { "cost": [ @@ -72445,7 +94475,10 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-05-13" }, "openai/gpt-4o-mini": { "cost": [ @@ -72454,7 +94487,10 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-07-18" }, "openai/gpt-5": { "cost": [ @@ -72463,7 +94499,10 @@ 0.0, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "openai/gpt-5-mini": { "cost": [ @@ -72472,7 +94511,10 @@ 0.0, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "openai/gpt-5-nano": { "cost": [ @@ -72481,7 +94523,10 @@ 0.0, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "openai/gpt-5.1": { "cost": [ @@ -72490,7 +94535,10 @@ 0.0, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "openai/gpt-5.2": { "cost": [ @@ -72499,7 +94547,10 @@ 0.0, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "openai/gpt-5.3-codex": { "cost": [ @@ -72508,7 +94559,10 @@ 0.0, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-02-05" }, "openai/gpt-5.4": { "cost": [ @@ -72517,7 +94571,10 @@ 0.0, 0.0 ], - "limit": 1050000 + "knowledge": "2025-08-31", + "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05" }, "openai/gpt-5.4-mini": { "cost": [ @@ -72526,7 +94583,10 @@ 0.0, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "openai/gpt-5.4-nano": { "cost": [ @@ -72535,7 +94595,10 @@ 0.0, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "openai/gpt-5.4-pro": { "cost": [ @@ -72544,7 +94607,10 @@ 0.0, 0.0 ], - "limit": 1050000 + "knowledge": "2025-08-31", + "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05" }, "openai/gpt-5.5": { "cost": [ @@ -72553,7 +94619,10 @@ 0.0, 0.0 ], - "limit": 1050000 + "knowledge": "2025-12-01", + "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23" }, "openai/gpt-5.6-luna": { "cost": [ @@ -72562,7 +94631,10 @@ 0.0, 0.0 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "openai/gpt-5.6-luna-pro": { "cost": [ @@ -72571,7 +94643,10 @@ 0.0, 0.0 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "openai/gpt-5.6-sol": { "cost": [ @@ -72580,7 +94655,10 @@ 0.0, 0.0 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "openai/gpt-5.6-sol-pro": { "cost": [ @@ -72589,7 +94667,10 @@ 0.0, 0.0 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "openai/gpt-5.6-terra": { "cost": [ @@ -72598,7 +94679,10 @@ 0.0, 0.0 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "openai/gpt-5.6-terra-pro": { "cost": [ @@ -72607,7 +94691,10 @@ 0.0, 0.0 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "openai/gpt-6-astra": { "cost": [ @@ -72616,7 +94703,10 @@ 0.0, 0.0 ], - "limit": 1050000 + "knowledge": "2026-04-30", + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-04" }, "openai/gpt-6-luna": { "cost": [ @@ -72625,7 +94715,10 @@ 0.0, 0.0 ], - "limit": 1050000 + "knowledge": "2026-05-18", + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22" }, "openai/gpt-6-sol": { "cost": [ @@ -72634,7 +94727,10 @@ 0.0, 0.0 ], - "limit": 1050000 + "knowledge": "2026-04-20", + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22" }, "openai/gpt-6.1-sol": { "cost": [ @@ -72643,7 +94739,10 @@ 0.0, 0.0 ], - "limit": 1050000 + "knowledge": "2026-04-30", + "limit": 1050000, + "max_output": 128000, + "released": "2026-09-29" }, "openai/gpt-oss-120b": { "cost": [ @@ -72652,7 +94751,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 65536, + "open": true, + "released": "2025-08-05" }, "openai/gpt-oss-20b": { "cost": [ @@ -72661,7 +94764,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "qwen/qwen3-30b-a3b-instruct-2507": { "cost": [ @@ -72670,7 +94777,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 235929, + "open": true, + "released": "2025-07-28" }, "qwen/qwen3-coder-next": { "cost": [ @@ -72679,7 +94789,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-09", + "limit": 262144, + "max_output": 235929, + "open": true, + "released": "2026-02-03" }, "qwen/qwen3-vl-235b-a22b-instruct": { "cost": [ @@ -72688,7 +94802,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-03-31", + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2025-09-23" }, "qwen/qwen3-vl-30b-a3b-instruct": { "cost": [ @@ -72697,7 +94815,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 16384, + "open": true, + "released": "2025-10-04" }, "qwen/qwen3.8-27b": { "cost": [ @@ -72706,7 +94827,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 235929, + "open": true, + "released": "2026-08-14" }, "x-ai/grok-4.6": { "cost": [ @@ -72715,7 +94839,10 @@ 0.0, 0.0 ], - "limit": 500000 + "knowledge": "2026-02-01", + "limit": 500000, + "max_output": 450000, + "released": "2026-08-12" }, "x-ai/grok-4.7": { "cost": [ @@ -72724,7 +94851,10 @@ 0.0, 0.0 ], - "limit": 500000 + "knowledge": "2026-05", + "limit": 500000, + "max_output": 450000, + "released": "2026-09-21" }, "z-ai/glm-5.2": { "cost": [ @@ -72733,16 +94863,22 @@ 0.0, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 943718, + "open": true, + "released": "2026-06-13" }, "z-ai/glm-5.3": { "cost": [ - 1.4, - 4.4, - 0.26, - 1.4 + 0.98, + 3.08, + 0.182, + 0.98 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "z-ai/glm-5.3-flash": { "cost": [ @@ -72751,7 +94887,10 @@ 0.03, 0.15 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-08-26" } }, "name": "Prime Inference" @@ -72766,6 +94905,9 @@ 0.0 ], "limit": 8192, + "max_output": 8192, + "open": true, + "released": "2026-01-27", "status": "beta" }, "glm-5.3": { @@ -72775,7 +94917,10 @@ 0.1733, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "glm-5.3-flash": { "cost": [ @@ -72784,7 +94929,10 @@ 0.0578, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-26" }, "glm-flash-latest": { "cost": [ @@ -72793,7 +94941,10 @@ 0.0578, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-26" }, "glm-latest": { "cost": [ @@ -72802,7 +94953,10 @@ 0.1733, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "gpt-oss-120b": { "cost": [ @@ -72811,7 +94965,11 @@ 0.0462, 0.0 ], - "limit": 128000 + "knowledge": "2024-06", + "limit": 128000, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "kimi-k2.6": { "cost": [ @@ -72820,7 +94978,11 @@ 0.1733, 0.0 ], + "knowledge": "2025-01", "limit": 256000, + "max_output": 262144, + "open": true, + "released": "2026-04-20", "status": "deprecated" }, "kimi-latest": { @@ -72830,7 +94992,11 @@ 0.1733, 0.0 ], + "knowledge": "2025-01", "limit": 256000, + "max_output": 262144, + "open": true, + "released": "2026-04-20", "status": "deprecated" }, "qwen3-embedding-4b": { @@ -72840,7 +95006,12 @@ 0.0, 0.0 ], - "limit": 32000 + "knowledge": "2025-06", + "limit": 32000, + "max_output": 2560, + "open": true, + "released": "2025-06-05", + "type": "embedding" }, "voxtral-mini-3b": { "cost": [ @@ -72849,7 +95020,11 @@ 0.0, 0.0 ], - "limit": 32000 + "limit": 32000, + "max_output": 32000, + "open": true, + "released": "2025-07-15", + "type": "transcription" }, "whisper-large-v3": { "cost": [ @@ -72858,7 +95033,11 @@ 0.0, 0.0 ], - "limit": 448 + "limit": 448, + "max_output": 4096, + "open": true, + "released": "2023-11-06", + "type": "transcription" } }, "name": "Privatemode AI" @@ -72872,7 +95051,10 @@ 0.0, 0.0 ], - "limit": 200000 + "knowledge": "2025-07-31", + "limit": 200000, + "max_output": 64000, + "released": "2025-10-15" }, "claude-opus-4-5-20251101": { "cost": [ @@ -72881,7 +95063,10 @@ 0.0, 0.0 ], + "knowledge": "2025-03", "limit": 200000, + "max_output": 32000, + "released": "2025-11-24", "status": "deprecated" }, "claude-sonnet-4-5-20250929": { @@ -72891,7 +95076,10 @@ 0.0, 0.0 ], + "knowledge": "2025-07-31", "limit": 200000, + "max_output": 64000, + "released": "2025-09-29", "status": "deprecated" }, "gemini-2.5-flash": { @@ -72901,7 +95089,10 @@ 0.0, 0.0 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2025-06-17", "tiers": [ { "cost": [ @@ -72924,7 +95115,10 @@ 0.0, 0.0 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2025-12-17", "tiers": [ { "cost": [ @@ -72947,7 +95141,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-11", + "limit": 1000000, + "max_output": 65000, + "released": "2025-11-18" }, "gpt-5-mini": { "cost": [ @@ -72956,7 +95153,10 @@ 0.0, 0.0 ], - "limit": 200000 + "knowledge": "2024-09-30", + "limit": 200000, + "max_output": 64000, + "released": "2025-08-07" }, "gpt-5.2": { "cost": [ @@ -72965,7 +95165,10 @@ 0.0, 0.0 ], + "knowledge": "2025-08-31", "limit": 400000, + "max_output": 128000, + "released": "2025-12-11", "status": "deprecated" }, "gpt-5.2-codex": { @@ -72975,7 +95178,10 @@ 0.0, 0.0 ], + "knowledge": "2025-08-31", "limit": 400000, + "max_output": 128000, + "released": "2025-12-11", "status": "deprecated" } }, @@ -72991,6 +95197,9 @@ 0.0 ], "limit": 1000000, + "max_output": 80000, + "open": true, + "released": "2025-06-17", "status": "deprecated" }, "deepseek-r1": { @@ -73000,7 +95209,11 @@ 0.0, 0.0 ], + "knowledge": "2024-07", "limit": 128000, + "max_output": 32000, + "open": true, + "released": "2025-01-20", "status": "deprecated" }, "deepseek-r1-0528": { @@ -73011,6 +95224,9 @@ 0.0 ], "limit": 128000, + "max_output": 32000, + "open": true, + "released": "2025-05-28", "status": "deprecated" }, "deepseek-v3": { @@ -73021,6 +95237,9 @@ 0.0 ], "limit": 128000, + "max_output": 16000, + "open": true, + "released": "2024-12-26", "status": "deprecated" }, "deepseek-v3.1": { @@ -73031,6 +95250,9 @@ 0.0 ], "limit": 128000, + "max_output": 32000, + "open": true, + "released": "2025-08-21", "status": "deprecated" }, "deepseek/deepseek-v3.1-terminus": { @@ -73041,6 +95263,8 @@ 0.0 ], "limit": 128000, + "max_output": 32000, + "released": "2025-09-22", "status": "deprecated" }, "deepseek/deepseek-v3.1-terminus-thinking": { @@ -73051,6 +95275,8 @@ 0.0 ], "limit": 128000, + "max_output": 32000, + "released": "2025-09-22", "status": "deprecated" }, "deepseek/deepseek-v3.2-251201": { @@ -73060,7 +95286,11 @@ 0.02898551, 0.0 ], + "knowledge": "2024-07", "limit": 128000, + "max_output": 32000, + "open": true, + "released": "2025-12-01", "status": "deprecated" }, "deepseek/deepseek-v3.2-exp": { @@ -73071,6 +95301,8 @@ 0.0 ], "limit": 128000, + "max_output": 32000, + "released": "2025-09-29", "status": "deprecated" }, "deepseek/deepseek-v3.2-exp-thinking": { @@ -73081,6 +95313,8 @@ 0.0 ], "limit": 128000, + "max_output": 32000, + "released": "2025-09-29", "status": "deprecated" }, "doubao-1.5-pro-32k": { @@ -73091,6 +95325,8 @@ 0.0 ], "limit": 128000, + "max_output": 12000, + "released": "2025-08-05", "status": "deprecated" }, "doubao-1.5-thinking-pro": { @@ -73101,6 +95337,8 @@ 0.0 ], "limit": 128000, + "max_output": 16000, + "released": "2025-08-05", "status": "deprecated" }, "doubao-1.5-vision-pro": { @@ -73111,6 +95349,8 @@ 0.0 ], "limit": 128000, + "max_output": 16000, + "released": "2025-08-05", "status": "deprecated" }, "doubao-seed-1.6": { @@ -73121,6 +95361,8 @@ 0.0 ], "limit": 256000, + "max_output": 32000, + "released": "2025-10-15", "status": "deprecated", "tiers": [ { @@ -73157,6 +95399,8 @@ 0.0 ], "limit": 256000, + "max_output": 32000, + "released": "2025-08-28", "status": "deprecated", "tiers": [ { @@ -73193,6 +95437,8 @@ 0.0 ], "limit": 256000, + "max_output": 32000, + "released": "2025-08-15", "status": "deprecated", "tiers": [ { @@ -73229,6 +95475,8 @@ 0.0 ], "limit": 256000, + "max_output": 128000, + "released": "2026-02-14", "status": "deprecated", "tiers": [ { @@ -73265,6 +95513,8 @@ 0.0 ], "limit": 256000, + "max_output": 32000, + "released": "2026-02-14", "tiers": [ { "cost": [ @@ -73300,6 +95550,8 @@ 0.0 ], "limit": 256000, + "max_output": 32000, + "released": "2026-02-14", "tiers": [ { "cost": [ @@ -73335,6 +95587,8 @@ 0.0 ], "limit": 256000, + "max_output": 128000, + "released": "2026-02-14", "status": "deprecated", "tiers": [ { @@ -73370,7 +95624,11 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 131072, + "max_output": 98304, + "open": true, + "released": "2025-07-28", "status": "deprecated" }, "kimi-k2": { @@ -73380,7 +95638,11 @@ 0.0, 0.0 ], + "knowledge": "2024-12-31", "limit": 128000, + "max_output": 128000, + "open": true, + "released": "2025-07-11", "status": "deprecated" }, "meituan/longcat-flash-lite": { @@ -73391,6 +95653,8 @@ 0.0 ], "limit": 256000, + "max_output": 320000, + "released": "2026-02-06", "status": "deprecated" }, "mimo-v2-flash": { @@ -73400,7 +95664,11 @@ 0.01, 0.0 ], + "knowledge": "2024-12-01", "limit": 256000, + "max_output": 256000, + "open": true, + "released": "2025-12-16", "status": "deprecated" }, "minimax/minimax-m2": { @@ -73411,6 +95679,9 @@ 0.0 ], "limit": 200000, + "max_output": 128000, + "open": true, + "released": "2025-10-27", "status": "deprecated" }, "minimax/minimax-m2.1": { @@ -73421,6 +95692,9 @@ 0.0 ], "limit": 204800, + "max_output": 128000, + "open": true, + "released": "2025-12-23", "status": "deprecated" }, "minimax/minimax-m2.5": { @@ -73430,7 +95704,10 @@ 0.0, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 128000, + "open": true, + "released": "2026-02-12" }, "minimax/minimax-m2.5-highspeed": { "cost": [ @@ -73440,6 +95717,9 @@ 0.0 ], "limit": 204800, + "max_output": 128000, + "open": true, + "released": "2026-02-13", "status": "deprecated" }, "moonshotai/kimi-k2-thinking": { @@ -73449,7 +95729,11 @@ 0.0, 0.0 ], + "knowledge": "2024-08", "limit": 256000, + "max_output": 100000, + "open": true, + "released": "2025-11-06", "status": "deprecated" }, "moonshotai/kimi-k2.5": { @@ -73459,7 +95743,11 @@ 0.0, 0.0 ], + "knowledge": "2025-01", "limit": 256000, + "max_output": 256000, + "open": true, + "released": "2026-01-27", "status": "deprecated" }, "qwen-max-2025-01-25": { @@ -73469,7 +95757,10 @@ 0.0, 0.0 ], + "knowledge": "2024-04", "limit": 128000, + "max_output": 4096, + "released": "2024-04-03", "status": "deprecated" }, "qwen-turbo": { @@ -73479,7 +95770,10 @@ 0.0, 0.0 ], + "knowledge": "2024-04", "limit": 1000000, + "max_output": 4096, + "released": "2024-11-01", "status": "deprecated" }, "qwen-vl-max-2025-01-25": { @@ -73490,6 +95784,8 @@ 0.0 ], "limit": 128000, + "max_output": 4096, + "released": "2025-08-05", "status": "deprecated" }, "qwen2.5-vl-72b-instruct": { @@ -73499,7 +95795,11 @@ 0.0, 0.0 ], + "knowledge": "2024-04", "limit": 128000, + "max_output": 8192, + "open": true, + "released": "2025-01-26", "status": "deprecated" }, "qwen3-235b-a22b": { @@ -73509,7 +95809,11 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 128000, + "max_output": 32000, + "open": true, + "released": "2025-04-28", "status": "deprecated" }, "qwen3-235b-a22b-instruct-2507": { @@ -73520,6 +95824,9 @@ 0.0 ], "limit": 262144, + "max_output": 64000, + "open": true, + "released": "2025-07-21", "status": "deprecated" }, "qwen3-235b-a22b-thinking-2507": { @@ -73530,6 +95837,9 @@ 0.0 ], "limit": 262144, + "max_output": 4096, + "open": true, + "released": "2025-07-25", "status": "deprecated" }, "qwen3-30b-a3b": { @@ -73540,6 +95850,9 @@ 0.0 ], "limit": 40000, + "max_output": 4096, + "open": true, + "released": "2025-04-28", "status": "deprecated" }, "qwen3-30b-a3b-instruct-2507": { @@ -73550,6 +95863,9 @@ 0.0 ], "limit": 128000, + "max_output": 32000, + "open": true, + "released": "2025-07-28", "status": "deprecated" }, "qwen3-30b-a3b-thinking-2507": { @@ -73560,6 +95876,8 @@ 0.0 ], "limit": 126000, + "max_output": 32000, + "released": "2026-02-04", "status": "deprecated" }, "qwen3-32b": { @@ -73569,7 +95887,11 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 40000, + "max_output": 4096, + "open": true, + "released": "2025-04-28", "status": "deprecated" }, "qwen3-coder-480b-a35b-instruct": { @@ -73579,7 +95901,11 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 262000, + "max_output": 4096, + "open": true, + "released": "2025-07-22", "status": "deprecated", "tiers": [ { @@ -73615,7 +95941,10 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 262144, + "max_output": 65536, + "released": "2025-09-23", "status": "deprecated", "tiers": [ { @@ -73651,7 +95980,10 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 256000, + "max_output": 64000, + "released": "2025-09-05", "status": "deprecated", "tiers": [ { @@ -73687,7 +96019,11 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-09", "status": "deprecated" }, "qwen3-next-80b-a3b-thinking": { @@ -73697,7 +96033,11 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-09", "status": "deprecated" }, "qwen3-vl-30b-a3b-thinking": { @@ -73708,6 +96048,8 @@ 0.0 ], "limit": 128000, + "max_output": 32000, + "released": "2026-02-09", "status": "deprecated" }, "qwen3.5-397b-a17b": { @@ -73718,6 +96060,9 @@ 0.0 ], "limit": 256000, + "max_output": 64000, + "open": true, + "released": "2026-02-15", "tiers": [ { "cost": [ @@ -73740,7 +96085,11 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 200000, + "max_output": 200000, + "open": true, + "released": "2025-09-30", "status": "deprecated" }, "z-ai/glm-4.7": { @@ -73750,7 +96099,11 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 200000, + "max_output": 200000, + "open": true, + "released": "2025-12-22", "status": "deprecated" }, "z-ai/glm-5": { @@ -73761,6 +96114,9 @@ 0.0 ], "limit": 200000, + "max_output": 128000, + "open": true, + "released": "2026-02-12", "tiers": [ { "cost": [ @@ -73788,7 +96144,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-04-02" }, "gpt-oss-120b": { "cost": [ @@ -73797,7 +96157,11 @@ 0.0, 0.0 ], + "knowledge": "2024-06", "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05", "status": "deprecated" }, "gpt-oss-20b": { @@ -73807,7 +96171,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "qwen3.5-0.8b": { "cost": [ @@ -73816,7 +96184,10 @@ 0.0, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 8192, + "open": true, + "released": "2026-03-02" }, "qwen3.5-2b": { "cost": [ @@ -73825,7 +96196,10 @@ 0.0, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 8192, + "open": true, + "released": "2026-03-02" }, "qwen3.5-4b": { "cost": [ @@ -73834,7 +96208,10 @@ 0.0, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 8192, + "open": true, + "released": "2026-03-02" }, "qwen3.5-9b": { "cost": [ @@ -73843,7 +96220,10 @@ 0.0, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 8192, + "open": true, + "released": "2026-02-23" }, "qwen3.6-27b": { "cost": [ @@ -73852,7 +96232,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-04-22" }, "qwen3.6-35b-a3b": { "cost": [ @@ -73861,7 +96244,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-04-17" } }, "name": "QVAC" @@ -73875,7 +96261,11 @@ 0.0, 0.0 ], - "limit": 1048576 + "knowledge": "2026-06-30", + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-10-05" } }, "name": "Reflection" @@ -73889,7 +96279,11 @@ 0.0, 0.0 ], - "limit": 30000 + "knowledge": "2025-09", + "limit": 30000, + "max_output": 30000, + "open": true, + "released": "2025-09-02" }, "brick-complexity-pro": { "cost": [ @@ -73898,7 +96292,9 @@ 0.0, 0.0 ], - "limit": 100000 + "limit": 100000, + "max_output": 15000, + "released": "2026-02-06" }, "brick-v1-beta": { "cost": [ @@ -73908,6 +96304,8 @@ 0.0 ], "limit": 100000, + "max_output": 15000, + "released": "2026-02-06", "status": "beta" }, "deepseek-ocr-2": { @@ -73917,7 +96315,10 @@ 0.0, 0.0 ], - "limit": 4000 + "limit": 4000, + "max_output": 4000, + "open": true, + "released": "2026-01-27" }, "faster-whisper-large-v3": { "cost": [ @@ -73926,7 +96327,11 @@ 0.0, 0.0 ], - "limit": 448 + "limit": 448, + "max_output": 4096, + "open": true, + "released": "2023-11-06", + "type": "transcription" }, "gemma4-31b": { "cost": [ @@ -73935,7 +96340,11 @@ 0.0, 0.0 ], - "limit": 100000 + "knowledge": "2025-01", + "limit": 100000, + "max_output": 100000, + "open": true, + "released": "2026-04-02" }, "glm5.2": { "cost": [ @@ -73944,7 +96353,10 @@ 0.0, 0.0 ], - "limit": 96000 + "limit": 96000, + "max_output": 96000, + "open": true, + "released": "2026-06-13" }, "gpt-oss-120b": { "cost": [ @@ -73953,7 +96365,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-06", + "limit": 128000, + "max_output": 16384, + "open": true, + "released": "2025-08-05" }, "gpt-oss-20b": { "cost": [ @@ -73962,7 +96378,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-06", + "limit": 128000, + "max_output": 16384, + "open": true, + "released": "2025-08-05" }, "llama-3.3-70b-instruct": { "cost": [ @@ -73971,7 +96391,11 @@ 0.0, 0.0 ], + "knowledge": "2023-12", "limit": 128000, + "max_output": 16384, + "open": true, + "released": "2024-12-06", "status": "deprecated" }, "mistral-small-4-119b": { @@ -73981,7 +96405,11 @@ 0.0, 0.0 ], - "limit": 256000 + "knowledge": "2025-06", + "limit": 256000, + "max_output": 16384, + "open": true, + "released": "2026-03-16" }, "qwen-image": { "cost": [ @@ -73990,7 +96418,10 @@ 0.0, 0.0 ], - "limit": 8192 + "limit": 8192, + "max_output": 4096, + "released": "2026-03-01", + "type": "image" }, "qwen3-coder-next": { "cost": [ @@ -73999,7 +96430,11 @@ 0.0, 0.0 ], + "knowledge": "2025-09", "limit": 262144, + "max_output": 16384, + "open": true, + "released": "2026-02-03", "status": "deprecated" }, "qwen3-embedding-8b": { @@ -74009,7 +96444,11 @@ 0.0, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 8192, + "open": true, + "released": "2025-06-05", + "type": "embedding" }, "qwen3-reranker-4b": { "cost": [ @@ -74018,7 +96457,11 @@ 0.0, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 8192, + "open": true, + "released": "2026-02-01", + "type": "reranking" }, "qwen3.5-122b": { "cost": [ @@ -74027,7 +96470,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 16384, + "open": true, + "released": "2026-02-23" }, "qwen3.5-9b": { "cost": [ @@ -74036,7 +96482,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 8192, + "open": true, + "released": "2026-02-23" }, "qwen3.8-27b": { "cost": [ @@ -74045,7 +96494,10 @@ 0.0, 0.0 ], - "limit": 120000 + "limit": 120000, + "max_output": 120000, + "open": true, + "released": "2026-08-14" } }, "name": "Regolo AI" @@ -74059,7 +96511,10 @@ 1.1, 13.75 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-09" }, "claude-fable-5.1": { "cost": [ @@ -74068,7 +96523,10 @@ 0.25, 12.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-01" }, "claude-fable-5.1@eu": { "cost": [ @@ -74077,7 +96535,10 @@ 0.275, 13.75 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-01" }, "claude-fable-5@eu": { "cost": [ @@ -74086,7 +96547,10 @@ 1.1, 13.75 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-09" }, "claude-haiku-4-5": { "cost": [ @@ -74095,7 +96559,10 @@ 0.1, 1.25 ], - "limit": 200000 + "knowledge": "2025-02-28", + "limit": 200000, + "max_output": 64000, + "released": "2025-10-15" }, "claude-haiku-4-5@eu": { "cost": [ @@ -74104,7 +96571,10 @@ 0.11, 1.375 ], - "limit": 200000 + "knowledge": "2025-02-28", + "limit": 200000, + "max_output": 64000, + "released": "2025-10-15" }, "claude-haiku-5-5": { "cost": [ @@ -74113,7 +96583,10 @@ 0.01, 0.13 ], + "knowledge": "2026-06", "limit": 1000000, + "max_output": 128000, + "released": "2026-10-07", "tiers": [ { "cost": [ @@ -74136,7 +96609,10 @@ 0.02, 0.14 ], + "knowledge": "2026-06", "limit": 1000000, + "max_output": 128000, + "released": "2026-10-07", "tiers": [ { "cost": [ @@ -74159,7 +96635,10 @@ 1.5, 18.75 ], - "limit": 200000 + "knowledge": "2025-03-31", + "limit": 200000, + "max_output": 32000, + "released": "2025-08-05" }, "claude-opus-4-5": { "cost": [ @@ -74168,7 +96647,10 @@ 0.5, 6.25 ], - "limit": 200000 + "knowledge": "2025-05", + "limit": 200000, + "max_output": 64000, + "released": "2025-11-24" }, "claude-opus-4-5@eu": { "cost": [ @@ -74177,7 +96659,10 @@ 0.55, 6.875 ], - "limit": 200000 + "knowledge": "2025-05", + "limit": 200000, + "max_output": 64000, + "released": "2025-11-24" }, "claude-opus-4-6": { "cost": [ @@ -74186,7 +96671,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2025-05-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-05" }, "claude-opus-4-6@eu": { "cost": [ @@ -74195,7 +96683,10 @@ 0.55, 6.875 ], - "limit": 1000000 + "knowledge": "2025-05-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-05" }, "claude-opus-4-7": { "cost": [ @@ -74204,7 +96695,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-16" }, "claude-opus-4-7@eu": { "cost": [ @@ -74213,7 +96707,10 @@ 0.55, 6.875 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-16" }, "claude-opus-4-8": { "cost": [ @@ -74222,7 +96719,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-28" }, "claude-opus-4-8@eu": { "cost": [ @@ -74231,7 +96731,10 @@ 0.55, 6.875 ], - "limit": 1000000 + "knowledge": "2026-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-28" }, "claude-opus-5": { "cost": [ @@ -74240,7 +96743,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-05", + "limit": 1000000, + "max_output": 128000, + "released": "2026-07-24" }, "claude-opus-5-5": { "cost": [ @@ -74249,7 +96755,10 @@ 0.2, 5.0 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-22" }, "claude-opus-5-5@eu": { "cost": [ @@ -74258,7 +96767,10 @@ 0.22, 5.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-22" }, "claude-opus-5@eu": { "cost": [ @@ -74267,7 +96779,10 @@ 0.55, 6.875 ], - "limit": 1000000 + "knowledge": "2026-05", + "limit": 1000000, + "max_output": 128000, + "released": "2026-07-24" }, "claude-sonnet-4-5": { "cost": [ @@ -74276,7 +96791,10 @@ 0.3, 3.75 ], + "knowledge": "2025-07-31", "limit": 1000000, + "max_output": 64000, + "released": "2025-09-29", "tiers": [ { "cost": [ @@ -74299,7 +96817,10 @@ 0.3, 4.125 ], + "knowledge": "2025-07-31", "limit": 1000000, + "max_output": 64000, + "released": "2025-09-29", "tiers": [ { "cost": [ @@ -74322,7 +96843,10 @@ 0.3, 3.75 ], - "limit": 1000000 + "knowledge": "2025-08-31", + "limit": 1000000, + "max_output": 64000, + "released": "2026-02-17" }, "claude-sonnet-4-6@eu": { "cost": [ @@ -74331,7 +96855,10 @@ 0.3, 4.125 ], - "limit": 1000000 + "knowledge": "2025-08-31", + "limit": 1000000, + "max_output": 64000, + "released": "2026-02-17" }, "claude-sonnet-4@eu": { "cost": [ @@ -74340,7 +96867,10 @@ 0.3, 3.75 ], + "knowledge": "2025-03-31", "limit": 1000000, + "max_output": 64000, + "released": "2025-05-22", "status": "deprecated", "tiers": [ { @@ -74364,7 +96894,10 @@ 0.2, 2.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-30" }, "claude-sonnet-5-5": { "cost": [ @@ -74373,7 +96906,10 @@ 0.2, 2.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-28" }, "claude-sonnet-5-5@eu": { "cost": [ @@ -74382,7 +96918,10 @@ 0.22, 2.75 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-28" }, "claude-sonnet-5@eu": { "cost": [ @@ -74391,7 +96930,10 @@ 0.22, 2.75 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-30" }, "deepseek-v4-flash": { "cost": [ @@ -74400,7 +96942,11 @@ 0.07, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-04-24" }, "deepseek-v4-flash-0731": { "cost": [ @@ -74409,7 +96955,11 @@ 0.07, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-31" }, "deepseek-v4-flash-0731@eu": { "cost": [ @@ -74418,7 +96968,11 @@ 0.07, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-31" }, "deepseek-v4-pro": { "cost": [ @@ -74427,7 +96981,11 @@ 0.044, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-04-24" }, "deepseek-v4-pro-0813": { "cost": [ @@ -74436,7 +96994,10 @@ 0.044, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-13" }, "deepseek-v4-pro-0813@eu": { "cost": [ @@ -74445,7 +97006,10 @@ 0.44, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65536, + "open": true, + "released": "2026-08-13" }, "deepseek-v4-pro@eu": { "cost": [ @@ -74454,7 +97018,11 @@ 0.44, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-04-24" }, "deepseek-v4.1-flash": { "cost": [ @@ -74463,7 +97031,11 @@ 0.05, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 393216, + "open": true, + "released": "2026-09-10" }, "deepseek-v4.1-flash-1017": { "cost": [ @@ -74472,7 +97044,11 @@ 0.05, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 393216, + "open": true, + "released": "2026-10-17" }, "deepseek-v4.1-flash-1017@eu": { "cost": [ @@ -74481,7 +97057,11 @@ 0.05, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 393216, + "open": true, + "released": "2026-10-17" }, "deepseek-v4.1-flash@eu": { "cost": [ @@ -74490,7 +97070,11 @@ 0.05, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 393216, + "open": true, + "released": "2026-09-10" }, "devstral-latest": { "cost": [ @@ -74499,7 +97083,9 @@ 0.44, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 256000, + "released": "2026-05-27" }, "devstral-latest@eu": { "cost": [ @@ -74508,7 +97094,9 @@ 0.44, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 256000, + "released": "2026-05-27" }, "fugu-ultra": { "cost": [ @@ -74518,6 +97106,8 @@ 0.0 ], "limit": 1048576, + "max_output": 131072, + "released": "2026-06-15", "tiers": [ { "cost": [ @@ -74540,7 +97130,10 @@ 0.01, 0.18333 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65535, + "released": "2025-06-17" }, "gemini-2.5-flash@eu": { "cost": [ @@ -74549,7 +97142,10 @@ 0.075, 0.55 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65535, + "released": "2025-06-17" }, "gemini-2.5-pro@eu": { "cost": [ @@ -74558,7 +97154,10 @@ 0.31, 2.375 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65535, + "released": "2025-06-17", "tiers": [ { "cost": [ @@ -74581,7 +97180,11 @@ 0.2, 4.5 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 32768, + "released": "2026-05-28", + "type": "image" }, "gemini-3.1-flash-image": { "cost": [ @@ -74590,7 +97193,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2025-01", + "limit": 131072, + "max_output": 32768, + "released": "2026-05-28", + "type": "image" }, "gemini-3.1-flash-lite": { "cost": [ @@ -74599,7 +97206,10 @@ 0.025, 0.08333 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65535, + "released": "2026-05-07" }, "gemini-3.1-flash-lite@eu": { "cost": [ @@ -74608,7 +97218,10 @@ 0.0275, 0.091663 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65535, + "released": "2026-05-07" }, "gemini-3.1-pro-preview": { "cost": [ @@ -74617,7 +97230,10 @@ 0.2, 4.5 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65535, + "released": "2026-02-19", "tiers": [ { "cost": [ @@ -74640,7 +97256,10 @@ 0.15, 1.583 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65535, + "released": "2026-05-19" }, "gemini-3.5-flash-lite": { "cost": [ @@ -74649,7 +97268,10 @@ 0.03, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65535, + "released": "2026-07-21" }, "gemini-3.5-flash-lite@eu": { "cost": [ @@ -74658,7 +97280,10 @@ 0.033, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65535, + "released": "2026-07-21" }, "gemini-3.5-flash@eu": { "cost": [ @@ -74667,7 +97292,10 @@ 0.165, 1.7413 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65535, + "released": "2026-05-19" }, "gemini-3.6-flash": { "cost": [ @@ -74676,7 +97304,10 @@ 0.15, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65535, + "released": "2026-07-21" }, "gemini-3.7-flash": { "cost": [ @@ -74685,7 +97316,10 @@ 0.075, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65535, + "released": "2026-08-13" }, "gemini-3.7-flash@eu": { "cost": [ @@ -74694,7 +97328,10 @@ 0.0825, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65535, + "released": "2026-08-13" }, "gemini-3.8-flash": { "cost": [ @@ -74703,7 +97340,9 @@ 0.075, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65535, + "released": "2026-09-02" }, "gemini-3.8-flash@eu": { "cost": [ @@ -74712,7 +97351,9 @@ 0.0825, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65535, + "released": "2026-09-02" }, "gemini-4-argon": { "cost": [ @@ -74721,7 +97362,10 @@ 0.1, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-10-13" }, "gemini-4-argon@eu": { "cost": [ @@ -74730,7 +97374,10 @@ 0.11, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-10-13" }, "gemma-4-26b-a4b-it": { "cost": [ @@ -74739,7 +97386,10 @@ 0.07, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-04-02" }, "gemma-4-31b-it": { "cost": [ @@ -74748,7 +97398,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 8192, + "open": true, + "released": "2026-04-02" }, "glm-5.1": { "cost": [ @@ -74757,7 +97411,10 @@ 0.26, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 128000, + "open": true, + "released": "2026-04-07" }, "glm-5.1@eu": { "cost": [ @@ -74766,7 +97423,10 @@ 1.4, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 131072, + "open": true, + "released": "2026-04-07" }, "glm-5.2": { "cost": [ @@ -74775,7 +97435,10 @@ 0.16, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "glm-5.2-fast": { "cost": [ @@ -74784,7 +97447,9 @@ 0.21, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-07-13" }, "glm-5.2@eu": { "cost": [ @@ -74794,6 +97459,9 @@ 0.0 ], "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-06-13", "status": "deprecated" }, "glm-5.3": { @@ -74803,7 +97471,10 @@ 0.26, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-08-14" }, "glm-5.3-flash": { "cost": [ @@ -74812,7 +97483,10 @@ 0.07, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 262144, + "open": true, + "released": "2026-08-26" }, "glm-5.3-flash@eu": { "cost": [ @@ -74821,7 +97495,10 @@ 0.07, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 262144, + "open": true, + "released": "2026-08-26" }, "glm-5.3@eu": { "cost": [ @@ -74830,7 +97507,10 @@ 0.26, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-08-14" }, "gpt-4.1-mini@eu": { "cost": [ @@ -74839,7 +97519,10 @@ 0.11, 0.0 ], - "limit": 1047576 + "knowledge": "2024-04", + "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14" }, "gpt-4.1-nano@eu": { "cost": [ @@ -74848,7 +97531,10 @@ 0.0275, 0.0 ], - "limit": 1047576 + "knowledge": "2024-04", + "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14" }, "gpt-4.1@eu": { "cost": [ @@ -74857,7 +97543,10 @@ 0.55, 0.0 ], - "limit": 1047576 + "knowledge": "2024-04", + "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14" }, "gpt-4o-mini@eu": { "cost": [ @@ -74866,7 +97555,10 @@ 0.0825, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16000, + "released": "2024-07-18" }, "gpt-5-mini@eu": { "cost": [ @@ -74875,7 +97567,10 @@ 0.0275, 0.0 ], - "limit": 200000 + "knowledge": "2024-05-30", + "limit": 200000, + "max_output": 100000, + "released": "2025-08-07" }, "gpt-5-nano@eu": { "cost": [ @@ -74884,7 +97579,10 @@ 0.0055, 0.0 ], - "limit": 200000 + "knowledge": "2024-05-30", + "limit": 200000, + "max_output": 100000, + "released": "2025-08-07" }, "gpt-5.1@eu": { "cost": [ @@ -74893,7 +97591,10 @@ 0.1375, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "gpt-5.3-codex": { "cost": [ @@ -74902,7 +97603,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-02-05" }, "gpt-5.4": { "cost": [ @@ -74911,7 +97615,10 @@ 0.275, 0.0 ], - "limit": 1050000 + "knowledge": "2025-08-31", + "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05" }, "gpt-5.4-mini": { "cost": [ @@ -74920,7 +97627,10 @@ 0.075, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "gpt-5.4-nano": { "cost": [ @@ -74929,7 +97639,10 @@ 0.02, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "gpt-5.4-pro": { "cost": [ @@ -74938,7 +97651,10 @@ 30.0, 0.0 ], - "limit": 1050000 + "knowledge": "2025-08-31", + "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05" }, "gpt-5.4@eu": { "cost": [ @@ -74947,7 +97663,10 @@ 0.275, 0.0 ], + "knowledge": "2025-08-31", "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05", "tiers": [ { "cost": [ @@ -74970,7 +97689,10 @@ 0.55, 0.0 ], - "limit": 1050000 + "knowledge": "2025-12-01", + "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23" }, "gpt-5.5-pro": { "cost": [ @@ -74979,7 +97701,10 @@ 0.0, 0.0 ], - "limit": 1050000 + "knowledge": "2025-12-01", + "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23" }, "gpt-5.5@eu": { "cost": [ @@ -74988,7 +97713,10 @@ 0.55, 0.0 ], + "knowledge": "2025-12-01", "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23", "tiers": [ { "cost": [ @@ -75011,7 +97739,10 @@ 0.02, 0.25 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -75034,7 +97765,10 @@ 0.022, 0.275 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -75057,7 +97791,10 @@ 0.4, 5.0 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -75080,7 +97817,10 @@ 0.44, 5.5 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -75103,7 +97843,10 @@ 0.2, 2.5 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -75126,7 +97869,10 @@ 0.22, 2.75 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -75149,7 +97895,10 @@ 0.1375, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "gpt-6-astra": { "cost": [ @@ -75158,7 +97907,10 @@ 1.0, 12.5 ], + "knowledge": "2026-04-30", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-04", "tiers": [ { "cost": [ @@ -75181,7 +97933,10 @@ 0.01, 0.125 ], + "knowledge": "2026-05-18", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -75204,7 +97959,10 @@ 0.012, 0.15 ], + "knowledge": "2026-05-18", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -75227,7 +97985,10 @@ 0.2, 2.5 ], + "knowledge": "2026-04-20", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -75250,7 +98011,10 @@ 0.24, 3.0 ], + "knowledge": "2026-04-20", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -75273,7 +98037,10 @@ 0.1, 2.5 ], + "knowledge": "2026-04-30", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-29", "tiers": [ { "cost": [ @@ -75296,7 +98063,10 @@ 0.12, 3.0 ], + "knowledge": "2026-04-30", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-29", "tiers": [ { "cost": [ @@ -75312,6 +98082,58 @@ } ] }, + "gpt-6.1-terra": { + "cost": [ + 1.0, + 5.0, + 0.05, + 1.25 + ], + "knowledge": "2026-06-01", + "limit": 1050000, + "max_output": 128000, + "released": "2026-10-26", + "tiers": [ + { + "cost": [ + 2.0, + 7.5, + 0.1, + 2.5 + ], + "tier": { + "size": 272000, + "type": "context" + } + } + ] + }, + "gpt-6.1-terra@eu": { + "cost": [ + 1.2, + 6.0, + 0.06, + 1.5 + ], + "knowledge": "2026-06-01", + "limit": 1050000, + "max_output": 128000, + "released": "2026-10-26", + "tiers": [ + { + "cost": [ + 2.4, + 9.0, + 0.12, + 3.0 + ], + "tier": { + "size": 272000, + "type": "context" + } + } + ] + }, "grok-4.2-beta": { "cost": [ 2.0, @@ -75320,6 +98142,8 @@ 2.0 ], "limit": 2000000, + "max_output": 30000, + "released": "2026-03-09", "tiers": [ { "cost": [ @@ -75343,6 +98167,8 @@ 1.25 ], "limit": 1000000, + "max_output": 30000, + "released": "2026-04-17", "tiers": [ { "cost": [ @@ -75366,6 +98192,8 @@ 2.0 ], "limit": 500000, + "max_output": 500000, + "released": "2026-07-08", "tiers": [ { "cost": [ @@ -75388,7 +98216,10 @@ 0.5, 2.0 ], + "knowledge": "2026-02-01", "limit": 500000, + "max_output": 500000, + "released": "2026-08-12", "tiers": [ { "cost": [ @@ -75411,7 +98242,10 @@ 0.5, 2.0 ], - "limit": 500000 + "knowledge": "2026-05", + "limit": 500000, + "max_output": 500000, + "released": "2026-09-21" }, "grok-build-0.1": { "cost": [ @@ -75420,7 +98254,9 @@ 0.1, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 256000, + "released": "2026-04-16" }, "hy3": { "cost": [ @@ -75429,7 +98265,10 @@ 0.035, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-07-06" }, "inkling": { "cost": [ @@ -75438,7 +98277,10 @@ 0.374, 0.0 ], - "limit": 65536 + "limit": 65536, + "max_output": 32768, + "open": true, + "released": "2026-07-15" }, "inkling-256k": { "cost": [ @@ -75447,7 +98289,10 @@ 0.374, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-07-15" }, "kat-coder-pro": { "cost": [ @@ -75456,7 +98301,9 @@ 0.0, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 256000, + "released": "2026-03-27" }, "kimi-k2.5@eu": { "cost": [ @@ -75465,7 +98312,11 @@ 0.72, 0.72 ], - "limit": 128000 + "knowledge": "2025-01", + "limit": 128000, + "max_output": 16000, + "open": true, + "released": "2026-01-27" }, "kimi-k2.6": { "cost": [ @@ -75474,7 +98325,11 @@ 0.16, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-20" }, "kimi-k2.6@eu": { "cost": [ @@ -75483,7 +98338,11 @@ 0.95, 0.0 ], - "limit": 256000 + "knowledge": "2025-01", + "limit": 256000, + "max_output": 128000, + "open": true, + "released": "2026-04-20" }, "kimi-k2.7-code": { "cost": [ @@ -75492,7 +98351,11 @@ 0.19, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-06-12" }, "kimi-k2.7-code@eu": { "cost": [ @@ -75501,7 +98364,11 @@ 0.31, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-06-12" }, "kimi-k3": { "cost": [ @@ -75510,7 +98377,32 @@ 0.45, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 262144, + "open": true, + "released": "2026-07-16" + }, + "kimi-k3.1-pro": { + "cost": [ + 2.0, + 10.0, + 0.2, + 2.0 + ], + "limit": 1048576, + "max_output": 1048576, + "released": "2026-10-23" + }, + "kimi-k3.1-pro-highspeed": { + "cost": [ + 4.0, + 20.0, + 0.2, + 4.0 + ], + "limit": 1048576, + "max_output": 1048576, + "released": "2026-10-23" }, "kimi-k3@eu": { "cost": [ @@ -75519,7 +98411,10 @@ 0.45, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 262144, + "open": true, + "released": "2026-07-16" }, "laguna-m.1": { "cost": [ @@ -75529,6 +98424,9 @@ 0.0 ], "limit": 32768, + "max_output": 32768, + "open": true, + "released": "2026-04-28", "status": "deprecated" }, "laguna-xs.2": { @@ -75539,6 +98437,9 @@ 0.0 ], "limit": 32768, + "max_output": 32768, + "open": true, + "released": "2026-04-28", "status": "deprecated" }, "leanstral-1-5": { @@ -75548,7 +98449,9 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "released": "2026-05-27" }, "leanstral-1-5@eu": { "cost": [ @@ -75557,7 +98460,9 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "released": "2026-05-27" }, "ling-2.6-1t": { "cost": [ @@ -75566,7 +98471,9 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "released": "2026-04-23" }, "ling-2.6-flash": { "cost": [ @@ -75575,7 +98482,9 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "released": "2026-04-21" }, "ling-3.0-tiny": { "cost": [ @@ -75584,7 +98493,9 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "released": "2026-08-05" }, "mimo-v2.5": { "cost": [ @@ -75593,7 +98504,11 @@ 0.0028, 0.0 ], - "limit": 1048576 + "knowledge": "2024-12", + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-04-22" }, "mimo-v2.5-pro": { "cost": [ @@ -75602,7 +98517,11 @@ 0.0036, 0.0 ], - "limit": 1048576 + "knowledge": "2024-12", + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-04-22" }, "mimo-v2.6-flash": { "cost": [ @@ -75611,7 +98530,10 @@ 0.0027, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-09-22" }, "mimo-v2.6-pro": { "cost": [ @@ -75620,7 +98542,10 @@ 0.0036, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-09-22" }, "minimax-m2.7": { "cost": [ @@ -75629,7 +98554,10 @@ 0.06, 1.2 ], - "limit": 200000 + "limit": 200000, + "max_output": 128000, + "open": true, + "released": "2026-03-18" }, "minimax-m2.7-highspeed": { "cost": [ @@ -75638,7 +98566,10 @@ 0.06, 1.2 ], - "limit": 200000 + "limit": 200000, + "max_output": 128000, + "open": true, + "released": "2026-03-18" }, "minimax-m3": { "cost": [ @@ -75647,7 +98578,10 @@ 0.06, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 128000, + "open": true, + "released": "2026-06-01" }, "minimax-m3.1-flash": { "cost": [ @@ -75656,7 +98590,20 @@ 0.015, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 128000, + "released": "2026-10-19" + }, + "minimax-m3.1-flash@eu": { + "cost": [ + 0.3, + 1.2, + 0.07, + 0.0 + ], + "limit": 1048576, + "max_output": 1048576, + "released": "2026-10-19" }, "minimax-m3@eu": { "cost": [ @@ -75665,7 +98612,10 @@ 0.1, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-06-01" }, "mistral-large-4": { "cost": [ @@ -75674,7 +98624,9 @@ 0.07, 0.0 ], - "limit": 524288 + "limit": 524288, + "max_output": 262144, + "released": "2026-10-06" }, "mistral-large-4@eu": { "cost": [ @@ -75683,7 +98635,9 @@ 0.07, 0.0 ], - "limit": 524288 + "limit": 524288, + "max_output": 262144, + "released": "2026-10-06" }, "mistral-medium-3-5": { "cost": [ @@ -75692,7 +98646,9 @@ 1.65, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 209715, + "released": "2026-04-30" }, "mistral-medium-3-5@eu": { "cost": [ @@ -75701,7 +98657,9 @@ 1.65, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 209715, + "released": "2026-04-30" }, "mistral-medium-latest": { "cost": [ @@ -75710,7 +98668,10 @@ 0.44, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2026-04-29" }, "mistral-medium-latest@eu": { "cost": [ @@ -75719,7 +98680,10 @@ 0.44, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2026-04-29" }, "mistral-small-2603": { "cost": [ @@ -75728,7 +98692,11 @@ 0.165, 0.0 ], - "limit": 256000 + "knowledge": "2025-06", + "limit": 256000, + "max_output": 256000, + "open": true, + "released": "2026-03-16" }, "mistral-small-2603@eu": { "cost": [ @@ -75737,7 +98705,11 @@ 0.165, 0.0 ], - "limit": 256000 + "knowledge": "2025-06", + "limit": 256000, + "max_output": 256000, + "open": true, + "released": "2026-03-16" }, "muse-glimmer-30b": { "cost": [ @@ -75746,7 +98718,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2026-01-04", + "limit": 131072, + "max_output": 20480, + "open": true, + "released": "2026-08-10" }, "muse-spark-1.3": { "cost": [ @@ -75755,7 +98731,9 @@ 0.15, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 943718, + "released": "2026-09-02" }, "muse-spark-open": { "cost": [ @@ -75764,7 +98742,11 @@ 0.15, 0.0 ], - "limit": 1048576 + "knowledge": "2026-01-04", + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-10-15" }, "muse-wonder-1.0": { "cost": [ @@ -75773,7 +98755,9 @@ 0.2, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 943718, + "released": "2026-10-12" }, "nemotron-3-nano-omni": { "cost": [ @@ -75782,7 +98766,9 @@ 0.06, 0.0 ], - "limit": 300000 + "limit": 300000, + "max_output": 300000, + "released": "2026-05-20" }, "nemotron-3-nano-omni-30b-a3b-reasoning": { "cost": [ @@ -75791,7 +98777,10 @@ 0.0, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 20480, + "open": true, + "released": "2026-04-28" }, "nemotron-3-nano-omni@eu": { "cost": [ @@ -75800,7 +98789,9 @@ 0.06, 0.0 ], - "limit": 300000 + "limit": 300000, + "max_output": 300000, + "released": "2026-05-20" }, "nemotron-3-super-120b-a12b": { "cost": [ @@ -75809,7 +98800,11 @@ 0.0, 0.0 ], - "limit": 1048576 + "knowledge": "2025-06", + "limit": 1048576, + "max_output": 65536, + "open": true, + "released": "2026-03-11" }, "nemotron-3-ultra-550b-a55b": { "cost": [ @@ -75818,7 +98813,11 @@ 0.0, 0.0 ], - "limit": 1048576 + "knowledge": "2025-09", + "limit": 1048576, + "max_output": 65536, + "open": true, + "released": "2026-06-04" }, "nemotron-3-ultra-nvfp4": { "cost": [ @@ -75827,7 +98826,9 @@ 0.12, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "released": "2026-06-13" }, "nemotron-3.5-content-safety": { "cost": [ @@ -75836,7 +98837,10 @@ 0.0, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 8192, + "open": true, + "released": "2026-06-02" }, "nemotron-3.5-lightning-30b-a3b": { "cost": [ @@ -75845,7 +98849,11 @@ 0.0, 0.0 ], - "limit": 1048576 + "knowledge": "2025-09", + "limit": 1048576, + "max_output": 65536, + "open": true, + "released": "2026-08-11" }, "nemotron-lightning-3.5-30b-a3b": { "cost": [ @@ -75854,7 +98862,9 @@ 0.01, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "released": "2026-08-15" }, "nvidia-nemotron-3-super-120b-a12b": { "cost": [ @@ -75863,7 +98873,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-06", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-03-11" }, "nvidia-nemotron-3-ultra": { "cost": [ @@ -75872,7 +98886,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-09", + "limit": 262144, + "max_output": 131072, + "open": true, + "released": "2026-06-04" }, "o4-mini@eu": { "cost": [ @@ -75881,7 +98899,10 @@ 0.3025, 0.0 ], - "limit": 200000 + "knowledge": "2024-05", + "limit": 200000, + "max_output": 100000, + "released": "2025-04-16" }, "qwen3.5-27b": { "cost": [ @@ -75890,7 +98911,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-23" }, "qwen3.5-2b": { "cost": [ @@ -75899,7 +98923,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 81920, + "open": true, + "released": "2026-03-02" }, "qwen3.5-35b-a3b": { "cost": [ @@ -75908,7 +98935,10 @@ 0.05, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-23" }, "qwen3.6-plus": { "cost": [ @@ -75917,7 +98947,10 @@ 0.05, 0.625 ], - "limit": 1000000 + "knowledge": "2025-04", + "limit": 1000000, + "max_output": 65536, + "released": "2026-04-02" }, "qwen3.7-max": { "cost": [ @@ -75926,7 +98959,9 @@ 0.25, 3.125 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-05-21" }, "qwen3.7-plus": { "cost": [ @@ -75935,7 +98970,10 @@ 0.032, 0.4 ], - "limit": 1048576 + "knowledge": "2025-04", + "limit": 1048576, + "max_output": 131072, + "released": "2026-06-02" }, "qwen3.8-2.4T-A95B": { "cost": [ @@ -75944,7 +98982,10 @@ 0.2, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-08-12" }, "qwen3.8-2.4T-A95B@eu": { "cost": [ @@ -75953,7 +98994,10 @@ 0.63, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 262144, + "open": true, + "released": "2026-08-12" }, "qwen3.8-flash": { "cost": [ @@ -75962,7 +99006,9 @@ 0.016, 0.2 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-08-26" }, "qwen3.8-flash-next": { "cost": [ @@ -75971,7 +99017,10 @@ 0.05, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-08-27" }, "qwen3.8-flash-next@eu": { "cost": [ @@ -75980,7 +99029,10 @@ 0.05, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-08-27" }, "qwen3.8-max": { "cost": [ @@ -75989,7 +99041,9 @@ 0.25, 2.5 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-08-03" }, "ring-2.6-1t": { "cost": [ @@ -75998,7 +99052,9 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "released": "2026-05-08" }, "seed-1.8": { "cost": [ @@ -76007,7 +99063,9 @@ 0.05, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 64000, + "released": "2025-12-28" }, "seed-2.0-code": { "cost": [ @@ -76016,7 +99074,9 @@ 0.1, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 131072, + "released": "2026-02-14" }, "seed-2.0-mini": { "cost": [ @@ -76025,7 +99085,9 @@ 0.02, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 32000, + "released": "2026-02-14" }, "seed-2.0-pro": { "cost": [ @@ -76034,7 +99096,9 @@ 0.1, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 128000, + "released": "2026-02-14" }, "step-3.7-flash": { "cost": [ @@ -76043,7 +99107,11 @@ 0.04, 0.0 ], - "limit": 262144 + "knowledge": "2026-03-01", + "limit": 262144, + "max_output": 256000, + "open": true, + "released": "2026-05-29" }, "step-5-preview": { "cost": [ @@ -76052,7 +99120,10 @@ 0.05, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65536, + "open": true, + "released": "2026-09-16" } }, "name": "Requesty" @@ -76066,7 +99137,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2026-01", + "limit": 1000000, + "max_output": 32000, + "released": "2026-05-28" }, "claude-sonnet-4-6": { "cost": [ @@ -76075,7 +99149,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-08-31", + "limit": 1000000, + "max_output": 64000, + "released": "2026-02-17" }, "deepseek-v4-flash": { "cost": [ @@ -76084,7 +99161,11 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 64000, + "open": true, + "released": "2026-04-24" }, "deepseek-v4-pro": { "cost": [ @@ -76093,7 +99174,11 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 64000, + "open": true, + "released": "2026-04-24" }, "glm-5.2": { "cost": [ @@ -76102,7 +99187,10 @@ 0.0, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 32000, + "open": true, + "released": "2026-06-13" }, "glm-5.2-nitro": { "cost": [ @@ -76111,7 +99199,10 @@ 0.0, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 32000, + "open": true, + "released": "2026-06-13" }, "gpt-5.6-luna": { "cost": [ @@ -76120,7 +99211,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2026-02-16", + "limit": 1000000, + "max_output": 128000, + "released": "2026-07-09" }, "gpt-5.6-sol": { "cost": [ @@ -76129,7 +99223,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2026-02-16", + "limit": 1000000, + "max_output": 128000, + "released": "2026-07-09" }, "gpt-5.6-terra": { "cost": [ @@ -76138,7 +99235,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2026-02-16", + "limit": 1000000, + "max_output": 128000, + "released": "2026-07-09" }, "kimi-k2.6": { "cost": [ @@ -76147,7 +99247,11 @@ 0.0, 0.0 ], - "limit": 200000 + "knowledge": "2025-01", + "limit": 200000, + "max_output": 32000, + "open": true, + "released": "2026-04-20" }, "kimi-k2.6-nitro": { "cost": [ @@ -76156,7 +99260,11 @@ 0.0, 0.0 ], - "limit": 200000 + "knowledge": "2025-01", + "limit": 200000, + "max_output": 32000, + "open": true, + "released": "2026-04-20" }, "kimi-k2.7-code": { "cost": [ @@ -76165,7 +99273,11 @@ 0.0, 0.0 ], - "limit": 200000 + "knowledge": "2025-01", + "limit": 200000, + "max_output": 32000, + "open": true, + "released": "2026-06-12" }, "kimi-k2.7-code-nitro": { "cost": [ @@ -76174,7 +99286,11 @@ 0.0, 0.0 ], - "limit": 200000 + "knowledge": "2025-01", + "limit": 200000, + "max_output": 32000, + "open": true, + "released": "2026-06-12" }, "nemotron-3-ultra": { "cost": [ @@ -76183,7 +99299,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2025-09", + "limit": 131072, + "max_output": 32000, + "open": true, + "released": "2026-06-04" }, "qwen3.5-9b": { "cost": [ @@ -76192,7 +99312,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32000, + "open": true, + "released": "2026-02-23" } }, "name": "routing.run" @@ -76207,6 +99330,9 @@ 0.0 ], "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-08-12", "status": "deprecated" }, "Qwen/Qwen3.8-27B": { @@ -76216,7 +99342,10 @@ 0.01, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-08-14" }, "deepseek-ai/DeepSeek-V4-Flash-0731": { "cost": [ @@ -76225,7 +99354,11 @@ 0.01, 0.0 ], + "knowledge": "2025-05", "limit": 1048576, + "max_output": 32768, + "open": true, + "released": "2026-07-31", "status": "deprecated" }, "deepseek-ai/DeepSeek-V4-Pro-0813": { @@ -76236,6 +99369,9 @@ 0.0 ], "limit": 1048576, + "max_output": 32768, + "open": true, + "released": "2026-08-13", "status": "deprecated" }, "nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16": { @@ -76245,7 +99381,11 @@ 0.01, 0.0 ], - "limit": 262144 + "knowledge": "2025-09", + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-08-11" }, "ornith-ai/Ornith-1.5-35B-A3B": { "cost": [ @@ -76254,7 +99394,10 @@ 0.01, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-08-18" }, "zai-org/GLM-5.3": { "cost": [ @@ -76263,7 +99406,10 @@ 0.13, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 32768, + "open": true, + "released": "2026-08-14" }, "zai-org/GLM-5.3-Flash": { "cost": [ @@ -76272,7 +99418,10 @@ 0.03, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 32768, + "open": true, + "released": "2026-08-26" } }, "name": "RunInfra" @@ -76287,6 +99436,8 @@ 0.0 ], "limit": 1000000, + "max_output": 1000000, + "released": "2026-06-15", "tiers": [ { "cost": [ @@ -76310,6 +99461,8 @@ 0.0 ], "limit": 1000000, + "max_output": 1000000, + "released": "2026-06-15", "tiers": [ { "cost": [ @@ -76332,7 +99485,9 @@ 0.15, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "released": "2026-08-03" } }, "name": "Sakana AI" @@ -76346,7 +99501,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-17" } }, "name": "SaladCloud AI Gateway" @@ -76360,7 +99518,10 @@ 0.0, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 7168, + "open": true, + "released": "2025-08-21" }, "DeepSeek-V3.2": { "cost": [ @@ -76369,7 +99530,11 @@ 0.0, 0.0 ], - "limit": 32768 + "knowledge": "2024-07", + "limit": 32768, + "max_output": 7168, + "open": true, + "released": "2025-12-01" }, "Meta-Llama-3.3-70B-Instruct": { "cost": [ @@ -76378,7 +99543,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2023-12", + "limit": 131072, + "max_output": 3072, + "open": true, + "released": "2024-12-06" }, "MiniMax-M3": { "cost": [ @@ -76387,7 +99556,10 @@ 0.06, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-06-01" }, "gemma-4-31B-it": { "cost": [ @@ -76396,7 +99568,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2025-01", + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2026-04-02" }, "gpt-oss-120b": { "cost": [ @@ -76405,7 +99581,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2025-08-05" } }, "name": "SambaNova" @@ -76419,7 +99599,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-10", + "limit": 1000000, + "max_output": 64000, + "released": "2025-12-02" }, "amazon--nova-micro": { "cost": [ @@ -76428,7 +99611,10 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-10", + "limit": 128000, + "max_output": 8192, + "released": "2024-12-03" }, "amazon--nova-pro": { "cost": [ @@ -76437,7 +99623,10 @@ 0.0, 0.0 ], - "limit": 300000 + "knowledge": "2024-10", + "limit": 300000, + "max_output": 8192, + "released": "2024-12-03" }, "amazon--titan-embed-text": { "cost": [ @@ -76446,7 +99635,9 @@ 0.0, 0.0 ], - "limit": 8192 + "limit": 8192, + "max_output": 1536, + "released": "2024-04-30" }, "anthropic--claude-3-haiku": { "cost": [ @@ -76455,7 +99646,10 @@ 0.03, 0.3 ], - "limit": 200000 + "knowledge": "2023-08-31", + "limit": 200000, + "max_output": 4096, + "released": "2024-03-13" }, "anthropic--claude-4-opus": { "cost": [ @@ -76464,7 +99658,10 @@ 1.5, 18.75 ], + "knowledge": "2025-03-31", "limit": 200000, + "max_output": 32000, + "released": "2025-05-22", "status": "deprecated" }, "anthropic--claude-4-sonnet": { @@ -76474,7 +99671,10 @@ 0.3, 3.75 ], + "knowledge": "2025-03-31", "limit": 200000, + "max_output": 64000, + "released": "2025-05-22", "status": "deprecated" }, "anthropic--claude-4.5-haiku": { @@ -76484,7 +99684,10 @@ 0.1, 1.25 ], - "limit": 200000 + "knowledge": "2025-02-28", + "limit": 200000, + "max_output": 64000, + "released": "2025-10-15" }, "anthropic--claude-4.5-opus": { "cost": [ @@ -76493,7 +99696,10 @@ 0.5, 6.25 ], - "limit": 200000 + "knowledge": "2025-05", + "limit": 200000, + "max_output": 64000, + "released": "2025-11-24" }, "anthropic--claude-4.5-sonnet": { "cost": [ @@ -76502,7 +99708,10 @@ 0.3, 3.75 ], - "limit": 200000 + "knowledge": "2025-07-31", + "limit": 200000, + "max_output": 64000, + "released": "2025-09-29" }, "anthropic--claude-4.6-opus": { "cost": [ @@ -76511,7 +99720,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2025-05-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-05" }, "anthropic--claude-4.6-sonnet": { "cost": [ @@ -76520,7 +99732,10 @@ 0.3, 3.75 ], - "limit": 1000000 + "knowledge": "2025-08-31", + "limit": 1000000, + "max_output": 64000, + "released": "2026-02-17" }, "anthropic--claude-4.7-opus": { "cost": [ @@ -76529,7 +99744,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-16" }, "anthropic--claude-4.8-opus": { "cost": [ @@ -76538,7 +99756,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-28" }, "cohere--command-a-reasoning": { "cost": [ @@ -76547,7 +99768,11 @@ 0.0, 0.0 ], + "knowledge": "2024-06-01", "limit": 256000, + "max_output": 32000, + "open": true, + "released": "2025-08-21", "status": "deprecated" }, "gemini-2.5-flash": { @@ -76557,7 +99782,10 @@ 0.03, 0.0 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2025-06-17", "status": "deprecated" }, "gemini-2.5-flash-lite": { @@ -76567,7 +99795,10 @@ 0.01, 0.0 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2025-06-17", "status": "deprecated" }, "gemini-2.5-pro": { @@ -76577,7 +99808,10 @@ 0.125, 0.0 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2025-06-17", "status": "deprecated" }, "gemini-3.1-flash-lite": { @@ -76587,7 +99821,10 @@ 0.025, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-05-07" }, "gemini-3.5-flash": { "cost": [ @@ -76596,7 +99833,10 @@ 0.15, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-05-19" }, "gpt-4.1": { "cost": [ @@ -76605,7 +99845,10 @@ 0.5, 0.0 ], + "knowledge": "2024-04", "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14", "status": "deprecated" }, "gpt-4.1-mini": { @@ -76615,7 +99858,10 @@ 0.1, 0.0 ], + "knowledge": "2024-04", "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14", "status": "deprecated" }, "gpt-4.1-nano": { @@ -76625,7 +99871,10 @@ 0.0, 0.0 ], + "knowledge": "2024-04", "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14", "status": "deprecated" }, "gpt-5": { @@ -76635,7 +99884,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "gpt-5-mini": { "cost": [ @@ -76644,7 +99896,10 @@ 0.025, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "gpt-5-nano": { "cost": [ @@ -76653,7 +99908,10 @@ 0.005, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "gpt-5.2": { "cost": [ @@ -76662,7 +99920,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "gpt-5.4": { "cost": [ @@ -76671,7 +99932,10 @@ 0.25, 0.0 ], - "limit": 1050000 + "knowledge": "2025-08-31", + "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05" }, "gpt-5.5": { "cost": [ @@ -76680,7 +99944,10 @@ 0.5, 0.0 ], - "limit": 1050000 + "knowledge": "2025-12-01", + "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23" }, "gpt-5.6-luna": { "cost": [ @@ -76689,7 +99956,10 @@ 0.02, 0.0 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -76712,7 +99982,10 @@ 0.4, 0.0 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -76735,7 +100008,10 @@ 0.2, 0.0 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -76758,7 +100034,10 @@ 0.0, 0.0 ], + "knowledge": "2025-05", "limit": 128000, + "max_output": 128000, + "released": "2025-05-07", "status": "deprecated" }, "mistralai--mistral-small": { @@ -76768,7 +100047,11 @@ 0.0, 0.0 ], + "knowledge": "2025-06", "limit": 128000, + "max_output": 128000, + "open": true, + "released": "2026-03-16", "status": "deprecated" }, "sonar": { @@ -76778,7 +100061,10 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2025-09-01", + "limit": 128000, + "max_output": 4096, + "released": "2024-01-01" }, "sonar-deep-research": { "cost": [ @@ -76787,7 +100073,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2025-01", + "limit": 128000, + "max_output": 32768, + "reasoning": 3.0, + "released": "2025-02-01" }, "sonar-pro": { "cost": [ @@ -76796,7 +100086,10 @@ 0.0, 0.0 ], - "limit": 200000 + "knowledge": "2025-09-01", + "limit": 200000, + "max_output": 8192, + "released": "2024-01-01" }, "text-embedding-3-large": { "cost": [ @@ -76805,7 +100098,10 @@ 0.0, 0.0 ], - "limit": 8191 + "limit": 8191, + "max_output": 3072, + "released": "2024-01-25", + "type": "embedding" }, "text-embedding-3-small": { "cost": [ @@ -76814,7 +100110,10 @@ 0.0, 0.0 ], - "limit": 8191 + "limit": 8191, + "max_output": 1536, + "released": "2024-01-25", + "type": "embedding" } }, "name": "SAP AI Core" @@ -76828,7 +100127,10 @@ 0.05263423, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2026-02-18" } }, "name": "Sarvam AI" @@ -76842,7 +100144,10 @@ 0.0, 0.0 ], - "limit": 8191 + "limit": 8191, + "open": true, + "released": "2024-07-25", + "type": "embedding" }, "deepseek-v4-flash-0731": { "cost": [ @@ -76851,7 +100156,11 @@ 0.0936, 0.0 ], + "knowledge": "2025-05", "limit": 256000, + "max_output": 32768, + "open": true, + "released": "2026-07-31", "status": "beta" }, "deepseek-v4.1-flash": { @@ -76861,7 +100170,11 @@ 0.134, 0.0 ], + "knowledge": "2025-05", "limit": 256000, + "max_output": 32768, + "open": true, + "released": "2026-09-10", "status": "beta" }, "gemma-4-26b-a4b-it": { @@ -76871,7 +100184,11 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 256000, + "max_output": 16384, + "open": true, + "released": "2026-04-02", "status": "beta" }, "glm-5.2": { @@ -76881,7 +100198,10 @@ 0.0, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 16384, + "open": true, + "released": "2026-06-13" }, "glm-5.3": { "cost": [ @@ -76891,6 +100211,9 @@ 0.0 ], "limit": 256000, + "max_output": 16384, + "open": true, + "released": "2026-08-14", "status": "beta" }, "gpt-oss-120b": { @@ -76900,7 +100223,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-06", + "limit": 128000, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "lightonocr-3-0.8b": { "cost": [ @@ -76909,7 +100236,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 16384, + "open": true, + "released": "2026-10-08" }, "llama-3.3-70b-instruct": { "cost": [ @@ -76918,7 +100248,11 @@ 0.0, 0.0 ], - "limit": 100000 + "knowledge": "2023-12", + "limit": 100000, + "max_output": 16384, + "open": true, + "released": "2024-12-06" }, "mistral-medium-3.5-128b": { "cost": [ @@ -76927,7 +100261,10 @@ 0.0, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 16384, + "open": true, + "released": "2026-04-29" }, "mistral-small-3.2-24b-instruct-2506": { "cost": [ @@ -76936,7 +100273,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2025-03", + "limit": 128000, + "max_output": 32768, + "open": true, + "released": "2025-06-20" }, "qwen3-235b-a22b-instruct-2507": { "cost": [ @@ -76945,7 +100286,11 @@ 0.0, 0.0 ], - "limit": 260000 + "knowledge": "2025-04", + "limit": 260000, + "max_output": 16384, + "open": true, + "released": "2025-07-21" }, "qwen3-embedding-8b": { "cost": [ @@ -76954,7 +100299,10 @@ 0.0, 0.0 ], - "limit": 32768 + "limit": 32768, + "open": true, + "released": "2025-06-05", + "type": "embedding" }, "qwen3.5-397b-a17b": { "cost": [ @@ -76963,7 +100311,11 @@ 0.0, 0.0 ], - "limit": 256000 + "knowledge": "2025-04", + "limit": 256000, + "max_output": 16384, + "open": true, + "released": "2026-02-15" }, "qwen3.6-35b-a3b": { "cost": [ @@ -76972,7 +100324,11 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 128000, + "max_output": 16384, + "open": true, + "released": "2026-04-17", "status": "beta" }, "qwen3.8-27b": { @@ -76983,6 +100339,9 @@ 0.0 ], "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-08-14", "status": "beta" } }, @@ -76997,7 +100356,11 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "DeepSeek-V4-Flash-0731": { "cost": [ @@ -77006,7 +100369,11 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-07-31" }, "DeepSeek-V4-Pro": { "cost": [ @@ -77015,7 +100382,11 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "DeepSeek-V4-Pro-0813": { "cost": [ @@ -77024,7 +100395,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-08-13" }, "DeepSeek-V4.1-Flash": { "cost": [ @@ -77033,7 +100407,11 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-09-10" }, "GLM-5": { "cost": [ @@ -77042,7 +100420,10 @@ 0.0, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-02-12" }, "GLM-5.1": { "cost": [ @@ -77051,7 +100432,10 @@ 0.0, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 131072, + "open": true, + "released": "2026-04-07" }, "GLM-5.2": { "cost": [ @@ -77060,7 +100444,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "GLM-5.3": { "cost": [ @@ -77069,7 +100456,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "GLM-5.3-Flash": { "cost": [ @@ -77078,7 +100468,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-26" }, "Kimi-K2.5": { "cost": [ @@ -77087,7 +100480,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-01-27" }, "Kimi-K2.6": { "cost": [ @@ -77096,7 +100493,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-20" }, "Kimi-K2.7-Code": { "cost": [ @@ -77105,7 +100506,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-06-12" }, "Kimi-K3": { "cost": [ @@ -77114,7 +100519,10 @@ 0.0, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-16" }, "MiniMax-M2.5": { "cost": [ @@ -77123,7 +100531,10 @@ 0.0, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-02-12" }, "MiniMax-M2.7": { "cost": [ @@ -77132,7 +100543,10 @@ 0.0, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-03-18" }, "MiniMax-M3": { "cost": [ @@ -77141,7 +100555,10 @@ 0.0, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 512000, + "open": true, + "released": "2026-06-01" }, "Qwen3.8-Flash": { "cost": [ @@ -77150,7 +100567,9 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-08-26" }, "Qwen3.8-Max": { "cost": [ @@ -77159,7 +100578,9 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-08-03" } }, "name": "SCNet Token Plan" @@ -77173,7 +100594,10 @@ 0.111, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "MiniMax-M2.7": { "cost": [ @@ -77182,7 +100606,10 @@ 0.05, 0.0 ], - "limit": 196608 + "limit": 196608, + "max_output": 196608, + "open": true, + "released": "2026-03-18" }, "Qwen3.8-Max": { "cost": [ @@ -77191,7 +100618,9 @@ 0.17, 2.5 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-08-03" }, "gpt-oss-120b": { "cost": [ @@ -77200,7 +100629,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2025-08-05" } }, "name": "SCX.ai" @@ -77214,7 +100647,11 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 65536, + "open": true, + "released": "2026-04-24" }, "deepseek-v4-pro": { "cost": [ @@ -77223,7 +100660,10 @@ 0.0, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65536, + "open": true, + "released": "2026-08-13" }, "deepseek-v4.1-flash": { "cost": [ @@ -77232,7 +100672,11 @@ 0.0, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 65536, + "open": true, + "released": "2026-09-10" }, "glm-5.2": { "cost": [ @@ -77241,7 +100685,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "kimi-k3": { "cost": [ @@ -77250,7 +100697,10 @@ 0.0, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65536, + "open": true, + "released": "2026-07-16" }, "sensenova-6.8-flash-lite": { "cost": [ @@ -77259,7 +100709,9 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "released": "2026-08-11" } }, "name": "SenseNova (China)" @@ -77273,7 +100725,10 @@ 0.0, 0.0 ], - "limit": 262000 + "limit": 262000, + "max_output": 262000, + "open": true, + "released": "2025-09-04" }, "MiniMaxAI/MiniMax-M2.5": { "cost": [ @@ -77283,6 +100738,9 @@ 0.0 ], "limit": 197000, + "max_output": 131000, + "open": true, + "released": "2026-02-12", "status": "deprecated" }, "MiniMaxAI/MiniMax-M3": { @@ -77292,7 +100750,10 @@ 0.06, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131000, + "open": true, + "released": "2026-06-01" }, "Qwen/Qwen2.5-72B-Instruct": { "cost": [ @@ -77301,7 +100762,10 @@ 0.0, 0.0 ], - "limit": 33000 + "limit": 33000, + "max_output": 4000, + "open": true, + "released": "2024-09-18" }, "Qwen/Qwen2.5-7B-Instruct": { "cost": [ @@ -77310,7 +100774,10 @@ 0.0, 0.0 ], - "limit": 33000 + "limit": 33000, + "max_output": 4000, + "open": true, + "released": "2024-09-19" }, "Qwen/Qwen3-14B": { "cost": [ @@ -77319,7 +100786,10 @@ 0.0, 0.0 ], - "limit": 131000 + "limit": 131000, + "max_output": 131000, + "open": true, + "released": "2025-04-30" }, "Qwen/Qwen3-30B-A3B-Instruct-2507": { "cost": [ @@ -77328,7 +100798,10 @@ 0.0, 0.0 ], - "limit": 262000 + "limit": 262000, + "max_output": 262000, + "open": true, + "released": "2025-07-28" }, "Qwen/Qwen3-32B": { "cost": [ @@ -77337,7 +100810,11 @@ 0.0, 0.0 ], - "limit": 131000 + "knowledge": "2025-04", + "limit": 131000, + "max_output": 131000, + "open": true, + "released": "2025-04-28" }, "Qwen/Qwen3-8B": { "cost": [ @@ -77346,7 +100823,10 @@ 0.0, 0.0 ], - "limit": 131000 + "limit": 131000, + "max_output": 131000, + "open": true, + "released": "2025-04-29" }, "Qwen/Qwen3-Coder-30B-A3B-Instruct": { "cost": [ @@ -77355,7 +100835,11 @@ 0.0, 0.0 ], - "limit": 262000 + "knowledge": "2025-04", + "limit": 262000, + "max_output": 262000, + "open": true, + "released": "2025-07-31" }, "Qwen/Qwen3-Coder-480B-A35B-Instruct": { "cost": [ @@ -77364,7 +100848,11 @@ 0.0, 0.0 ], - "limit": 262000 + "knowledge": "2025-04", + "limit": 262000, + "max_output": 262000, + "open": true, + "released": "2025-07-22" }, "Qwen/Qwen3-VL-30B-A3B-Instruct": { "cost": [ @@ -77373,7 +100861,10 @@ 0.0, 0.0 ], - "limit": 262000 + "limit": 262000, + "max_output": 262000, + "open": true, + "released": "2025-10-04" }, "Qwen/Qwen3-VL-30B-A3B-Thinking": { "cost": [ @@ -77382,7 +100873,10 @@ 0.0, 0.0 ], - "limit": 262000 + "limit": 262000, + "max_output": 262000, + "open": true, + "released": "2025-10-11" }, "Qwen/Qwen3-VL-32B-Instruct": { "cost": [ @@ -77391,7 +100885,10 @@ 0.0, 0.0 ], - "limit": 262000 + "limit": 262000, + "max_output": 262000, + "open": true, + "released": "2025-10-21" }, "Qwen/Qwen3-VL-32B-Thinking": { "cost": [ @@ -77400,7 +100897,10 @@ 0.0, 0.0 ], - "limit": 262000 + "limit": 262000, + "max_output": 262000, + "open": true, + "released": "2025-10-21" }, "Qwen/Qwen3-VL-8B-Instruct": { "cost": [ @@ -77409,7 +100909,10 @@ 0.0, 0.0 ], - "limit": 262000 + "limit": 262000, + "max_output": 262000, + "open": true, + "released": "2025-10-15" }, "Qwen/Qwen3.5-122B-A10B": { "cost": [ @@ -77418,7 +100921,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-02-23" }, "Qwen/Qwen3.5-27B": { "cost": [ @@ -77427,7 +100933,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-02-23" }, "Qwen/Qwen3.5-35B-A3B": { "cost": [ @@ -77436,7 +100945,10 @@ 0.15, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-02-23" }, "Qwen/Qwen3.5-397B-A17B": { "cost": [ @@ -77446,6 +100958,9 @@ 0.0 ], "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-02-15", "status": "deprecated" }, "Qwen/Qwen3.5-9B": { @@ -77455,7 +100970,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-02-23" }, "Qwen/Qwen3.6-27B": { "cost": [ @@ -77464,7 +100982,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-22" }, "Qwen/Qwen3.6-35B-A3B": { "cost": [ @@ -77473,7 +100994,10 @@ 0.15, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-17" }, "Qwen/Qwen3.8-2.4T-A95B": { "cost": [ @@ -77482,7 +101006,10 @@ 0.25, 0.0 ], - "limit": 1049000 + "limit": 1049000, + "max_output": 131000, + "open": true, + "released": "2026-08-12" }, "deepseek-ai/DeepSeek-R1": { "cost": [ @@ -77491,7 +101018,10 @@ 0.0, 0.0 ], - "limit": 164000 + "limit": 164000, + "max_output": 164000, + "open": true, + "released": "2025-05-28" }, "deepseek-ai/DeepSeek-V3": { "cost": [ @@ -77500,7 +101030,10 @@ 0.0, 0.0 ], - "limit": 164000 + "limit": 164000, + "max_output": 164000, + "open": true, + "released": "2025-03-24" }, "deepseek-ai/DeepSeek-V3.1": { "cost": [ @@ -77509,7 +101042,10 @@ 0.0, 0.0 ], - "limit": 164000 + "limit": 164000, + "max_output": 164000, + "open": true, + "released": "2025-08-21" }, "deepseek-ai/DeepSeek-V3.1-Terminus": { "cost": [ @@ -77518,7 +101054,10 @@ 0.0, 0.0 ], - "limit": 164000 + "limit": 164000, + "max_output": 164000, + "open": true, + "released": "2025-09-29" }, "deepseek-ai/DeepSeek-V3.2": { "cost": [ @@ -77527,7 +101066,11 @@ 0.135, 0.0 ], - "limit": 164000 + "knowledge": "2024-07", + "limit": 164000, + "max_output": 164000, + "open": true, + "released": "2025-12-01" }, "deepseek-ai/DeepSeek-V3.2-Exp": { "cost": [ @@ -77536,7 +101079,10 @@ 0.0, 0.0 ], - "limit": 164000 + "limit": 164000, + "max_output": 164000, + "open": true, + "released": "2025-10-10" }, "deepseek-ai/DeepSeek-V4-Flash": { "cost": [ @@ -77545,7 +101091,11 @@ 0.028, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "deepseek-ai/DeepSeek-V4-Flash-0731": { "cost": [ @@ -77554,7 +101104,11 @@ 0.014, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-07-31" }, "deepseek-ai/DeepSeek-V4-Flash-Vision-Exp": { "cost": [ @@ -77563,7 +101117,10 @@ 0.028, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-08-21" }, "deepseek-ai/DeepSeek-V4-Pro": { "cost": [ @@ -77572,7 +101129,11 @@ 0.135, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "deepseek-ai/DeepSeek-V4-Pro-0813": { "cost": [ @@ -77581,7 +101142,10 @@ 0.044, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-08-13" }, "google/gemma-4-12B-it": { "cost": [ @@ -77590,7 +101154,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-06-09" }, "google/gemma-4-26B-A4B-it": { "cost": [ @@ -77599,7 +101166,10 @@ 0.05, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-02" }, "google/gemma-4-31B-it": { "cost": [ @@ -77608,7 +101178,11 @@ 0.25, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-02" }, "inclusionAI/Ling-flash-2.0": { "cost": [ @@ -77617,7 +101191,10 @@ 0.0, 0.0 ], - "limit": 131000 + "limit": 131000, + "max_output": 131000, + "open": true, + "released": "2025-09-18" }, "meituan-longcat/LongCat-2.0": { "cost": [ @@ -77626,7 +101203,10 @@ 0.015, 0.0 ], - "limit": 1049000 + "limit": 1049000, + "max_output": 131072, + "open": true, + "released": "2026-06-30" }, "moonshotai/Kimi-K2.5": { "cost": [ @@ -77635,7 +101215,11 @@ 0.07, 0.0 ], - "limit": 262000 + "knowledge": "2025-01", + "limit": 262000, + "max_output": 262000, + "open": true, + "released": "2026-01-27" }, "moonshotai/Kimi-K2.6": { "cost": [ @@ -77644,7 +101228,11 @@ 0.14, 0.0 ], - "limit": 262000 + "knowledge": "2025-01", + "limit": 262000, + "max_output": 262000, + "open": true, + "released": "2026-04-20" }, "moonshotai/Kimi-K2.7-Code": { "cost": [ @@ -77653,7 +101241,11 @@ 0.17993, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-06-12" }, "moonshotai/Kimi-K3": { "cost": [ @@ -77662,7 +101254,10 @@ 0.27, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 262000, + "open": true, + "released": "2026-07-16" }, "nex-agi/Nex-N2-Pro": { "cost": [ @@ -77672,6 +101267,9 @@ 0.0 ], "limit": 262144, + "max_output": 256000, + "open": true, + "released": "2026-06-02", "status": "deprecated" }, "openai/gpt-oss-120b": { @@ -77681,7 +101279,11 @@ 0.0, 0.0 ], - "limit": 131000 + "knowledge": "2024-06", + "limit": 131000, + "max_output": 8000, + "open": true, + "released": "2025-08-05" }, "openai/gpt-oss-20b": { "cost": [ @@ -77690,7 +101292,11 @@ 0.0, 0.0 ], - "limit": 131000 + "knowledge": "2024-06", + "limit": 131000, + "max_output": 8000, + "open": true, + "released": "2025-08-05" }, "stepfun-ai/Step-3.5-Flash": { "cost": [ @@ -77699,7 +101305,11 @@ 0.0, 0.0 ], - "limit": 262000 + "knowledge": "2025-01", + "limit": 262000, + "max_output": 66000, + "open": true, + "released": "2026-01-29" }, "tencent/Hunyuan-A13B-Instruct": { "cost": [ @@ -77708,7 +101318,10 @@ 0.0, 0.0 ], - "limit": 131000 + "limit": 131000, + "max_output": 131000, + "open": true, + "released": "2025-06-30" }, "tencent/Hy3": { "cost": [ @@ -77717,7 +101330,10 @@ 0.033, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-07-06" }, "zai-org/GLM-4.5-Air": { "cost": [ @@ -77726,7 +101342,11 @@ 0.0, 0.0 ], - "limit": 131000 + "knowledge": "2025-04", + "limit": 131000, + "max_output": 131000, + "open": true, + "released": "2025-07-28" }, "zai-org/GLM-5": { "cost": [ @@ -77735,7 +101355,10 @@ 0.2, 0.0 ], - "limit": 205000 + "limit": 205000, + "max_output": 131072, + "open": true, + "released": "2026-02-12" }, "zai-org/GLM-5.1": { "cost": [ @@ -77744,7 +101367,10 @@ 0.6, 0.0 ], - "limit": 205000 + "limit": 205000, + "max_output": 131000, + "open": true, + "released": "2026-04-07" }, "zai-org/GLM-5.2": { "cost": [ @@ -77753,7 +101379,10 @@ 0.26, 0.0 ], - "limit": 1049000 + "limit": 1049000, + "max_output": 262000, + "open": true, + "released": "2026-06-13" }, "zai-org/GLM-5.3": { "cost": [ @@ -77762,7 +101391,10 @@ 0.26, 0.0 ], - "limit": 1049000 + "limit": 1049000, + "max_output": 262000, + "open": true, + "released": "2026-08-14" }, "zai-org/GLM-5.3-Flash": { "cost": [ @@ -77771,7 +101403,10 @@ 0.03, 0.0 ], - "limit": 1049000 + "limit": 1049000, + "max_output": 262000, + "open": true, + "released": "2026-08-26" }, "zai-org/GLM-5V-Turbo": { "cost": [ @@ -77780,7 +101415,9 @@ 0.24, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 131072, + "released": "2026-04-01" } }, "name": "SiliconFlow" @@ -77794,7 +101431,10 @@ 0.0, 0.0 ], - "limit": 262000 + "limit": 262000, + "max_output": 262000, + "open": true, + "released": "2025-09-04" }, "PaddlePaddle/PaddleOCR-VL-1.5": { "cost": [ @@ -77803,7 +101443,10 @@ 0.0, 0.0 ], - "limit": 16384 + "limit": 16384, + "max_output": 16384, + "open": true, + "released": "2026-01-29" }, "Pro/deepseek-ai/DeepSeek-R1": { "cost": [ @@ -77812,7 +101455,10 @@ 0.05977899, 0.0 ], - "limit": 164000 + "limit": 164000, + "max_output": 164000, + "open": true, + "released": "2025-05-28" }, "Pro/deepseek-ai/DeepSeek-V3": { "cost": [ @@ -77821,7 +101467,10 @@ 0.0298895, 0.0 ], - "limit": 164000 + "limit": 164000, + "max_output": 164000, + "open": true, + "released": "2025-03-24" }, "Pro/deepseek-ai/DeepSeek-V3.1-Terminus": { "cost": [ @@ -77830,7 +101479,10 @@ 0.05977899, 0.0 ], - "limit": 164000 + "limit": 164000, + "max_output": 164000, + "open": true, + "released": "2025-09-29" }, "Pro/deepseek-ai/DeepSeek-V3.2": { "cost": [ @@ -77839,7 +101491,11 @@ 0.05977899, 0.0 ], - "limit": 164000 + "knowledge": "2024-07", + "limit": 164000, + "max_output": 164000, + "open": true, + "released": "2025-12-01" }, "Pro/moonshotai/Kimi-K2.5": { "cost": [ @@ -77848,7 +101504,11 @@ 0.07, 0.0 ], + "knowledge": "2025-01", "limit": 262000, + "max_output": 262000, + "open": true, + "released": "2026-01-27", "status": "deprecated" }, "Pro/moonshotai/Kimi-K2.6": { @@ -77858,7 +101518,11 @@ 0.16439223, 0.0 ], - "limit": 262000 + "knowledge": "2025-01", + "limit": 262000, + "max_output": 262000, + "open": true, + "released": "2026-04-20" }, "Pro/zai-org/GLM-5": { "cost": [ @@ -77868,6 +101532,9 @@ 0.0 ], "limit": 205000, + "max_output": 205000, + "open": true, + "released": "2026-02-12", "status": "deprecated" }, "Pro/zai-org/GLM-5.1": { @@ -77878,6 +101545,9 @@ 0.0 ], "limit": 205000, + "max_output": 205000, + "open": true, + "released": "2026-04-07", "tiers": [ { "cost": [ @@ -77900,7 +101570,10 @@ 0.0, 0.0 ], - "limit": 33000 + "limit": 33000, + "max_output": 4000, + "open": true, + "released": "2024-09-18" }, "Qwen/Qwen2.5-7B-Instruct": { "cost": [ @@ -77909,7 +101582,10 @@ 0.0, 0.0 ], - "limit": 33000 + "limit": 33000, + "max_output": 4000, + "open": true, + "released": "2024-09-19" }, "Qwen/Qwen3-14B": { "cost": [ @@ -77918,7 +101594,10 @@ 0.0, 0.0 ], - "limit": 131000 + "limit": 131000, + "max_output": 131000, + "open": true, + "released": "2025-04-30" }, "Qwen/Qwen3-30B-A3B-Instruct-2507": { "cost": [ @@ -77927,7 +101606,10 @@ 0.0, 0.0 ], - "limit": 262000 + "limit": 262000, + "max_output": 262000, + "open": true, + "released": "2025-07-28" }, "Qwen/Qwen3-32B": { "cost": [ @@ -77936,7 +101618,11 @@ 0.0, 0.0 ], - "limit": 131000 + "knowledge": "2025-04", + "limit": 131000, + "max_output": 131000, + "open": true, + "released": "2025-04-28" }, "Qwen/Qwen3-8B": { "cost": [ @@ -77945,7 +101631,10 @@ 0.0, 0.0 ], - "limit": 131000 + "limit": 131000, + "max_output": 131000, + "open": true, + "released": "2025-04-29" }, "Qwen/Qwen3-Coder-30B-A3B-Instruct": { "cost": [ @@ -77954,7 +101643,11 @@ 0.0, 0.0 ], - "limit": 262000 + "knowledge": "2025-04", + "limit": 262000, + "max_output": 262000, + "open": true, + "released": "2025-07-31" }, "Qwen/Qwen3-VL-30B-A3B-Instruct": { "cost": [ @@ -77963,7 +101656,10 @@ 0.0, 0.0 ], - "limit": 262000 + "limit": 262000, + "max_output": 262000, + "open": true, + "released": "2025-10-04" }, "Qwen/Qwen3-VL-30B-A3B-Thinking": { "cost": [ @@ -77972,7 +101668,10 @@ 0.0, 0.0 ], - "limit": 262000 + "limit": 262000, + "max_output": 262000, + "open": true, + "released": "2025-10-11" }, "Qwen/Qwen3-VL-32B-Instruct": { "cost": [ @@ -77981,7 +101680,10 @@ 0.0, 0.0 ], - "limit": 262000 + "limit": 262000, + "max_output": 262000, + "open": true, + "released": "2025-10-21" }, "Qwen/Qwen3-VL-32B-Thinking": { "cost": [ @@ -77990,7 +101692,10 @@ 0.0, 0.0 ], - "limit": 262000 + "limit": 262000, + "max_output": 262000, + "open": true, + "released": "2025-10-21" }, "Qwen/Qwen3-VL-8B-Instruct": { "cost": [ @@ -77999,7 +101704,10 @@ 0.0, 0.0 ], - "limit": 262000 + "limit": 262000, + "max_output": 262000, + "open": true, + "released": "2025-10-15" }, "Qwen/Qwen3.5-122B-A10B": { "cost": [ @@ -78008,7 +101716,11 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-23", "tiers": [ { "cost": [ @@ -78031,7 +101743,11 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-23", "tiers": [ { "cost": [ @@ -78054,7 +101770,11 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-23", "tiers": [ { "cost": [ @@ -78077,7 +101797,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-04", + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-03-02" }, "Qwen/Qwen3.5-9B": { "cost": [ @@ -78086,7 +101810,11 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-23", "tiers": [ { "cost": [ @@ -78109,7 +101837,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-04", + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-04-17" }, "deepseek-ai/DeepSeek-OCR": { "cost": [ @@ -78118,7 +101850,10 @@ 0.0, 0.0 ], - "limit": 8192 + "limit": 8192, + "max_output": 8192, + "open": true, + "released": "2025-10-20" }, "deepseek-ai/DeepSeek-R1": { "cost": [ @@ -78127,7 +101862,10 @@ 0.05977899, 0.0 ], - "limit": 164000 + "limit": 164000, + "max_output": 164000, + "open": true, + "released": "2025-05-28" }, "deepseek-ai/DeepSeek-V3": { "cost": [ @@ -78136,7 +101874,10 @@ 0.0298895, 0.0 ], - "limit": 164000 + "limit": 164000, + "max_output": 164000, + "open": true, + "released": "2025-03-24" }, "deepseek-ai/DeepSeek-V3.1-Terminus": { "cost": [ @@ -78145,7 +101886,10 @@ 0.05977899, 0.0 ], - "limit": 164000 + "limit": 164000, + "max_output": 164000, + "open": true, + "released": "2025-09-29" }, "deepseek-ai/DeepSeek-V3.2": { "cost": [ @@ -78154,7 +101898,11 @@ 0.05977899, 0.0 ], - "limit": 164000 + "knowledge": "2024-07", + "limit": 164000, + "max_output": 164000, + "open": true, + "released": "2025-12-01" }, "deepseek-ai/DeepSeek-V4-Flash": { "cost": [ @@ -78163,7 +101911,11 @@ 0.04483424, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "deepseek-ai/DeepSeek-V4-Pro": { "cost": [ @@ -78172,7 +101924,11 @@ 0.14944748, 0.0 ], - "limit": 1049000 + "knowledge": "2025-05", + "limit": 1049000, + "max_output": 393000, + "open": true, + "released": "2026-04-24" }, "inclusionAI/Ling-flash-2.0": { "cost": [ @@ -78181,7 +101937,10 @@ 0.0, 0.0 ], - "limit": 131000 + "limit": 131000, + "max_output": 131000, + "open": true, + "released": "2025-09-18" }, "stepfun-ai/Step-3.5-Flash": { "cost": [ @@ -78190,7 +101949,11 @@ 0.0, 0.0 ], - "limit": 262000 + "knowledge": "2025-01", + "limit": 262000, + "max_output": 262000, + "open": true, + "released": "2026-01-29" }, "tencent/Hunyuan-A13B-Instruct": { "cost": [ @@ -78199,7 +101962,10 @@ 0.0, 0.0 ], - "limit": 131000 + "limit": 131000, + "max_output": 131000, + "open": true, + "released": "2025-06-30" }, "zai-org/GLM-4.5-Air": { "cost": [ @@ -78208,7 +101974,11 @@ 0.0, 0.0 ], - "limit": 131000 + "knowledge": "2025-04", + "limit": 131000, + "max_output": 131000, + "open": true, + "released": "2025-07-28" }, "zai-org/GLM-5.2": { "cost": [ @@ -78217,7 +101987,10 @@ 0.29889496, 0.0 ], - "limit": 1049000 + "limit": 1049000, + "max_output": 262000, + "open": true, + "released": "2026-06-13" } }, "name": "SiliconFlow (China)" @@ -78231,7 +102004,10 @@ 1.0, 12.5 ], + "knowledge": "2026-01-31", "limit": 1000000, + "max_output": 128000, + "released": "2026-06-09", "status": "beta" }, "claude-haiku-4-5": { @@ -78241,7 +102017,10 @@ 0.1, 1.25 ], - "limit": 200000 + "knowledge": "2025-02-28", + "limit": 200000, + "max_output": 64000, + "released": "2025-10-15" }, "claude-opus-4-5": { "cost": [ @@ -78250,7 +102029,10 @@ 0.5, 6.25 ], - "limit": 200000 + "knowledge": "2025-05", + "limit": 200000, + "max_output": 64000, + "released": "2025-11-24" }, "claude-opus-4-6": { "cost": [ @@ -78259,7 +102041,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2025-05-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-05" }, "claude-opus-4-7": { "cost": [ @@ -78268,7 +102053,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-16" }, "claude-opus-4-8": { "cost": [ @@ -78277,7 +102065,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-28" }, "claude-opus-5": { "cost": [ @@ -78286,7 +102077,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-05", + "limit": 1000000, + "max_output": 128000, + "released": "2026-07-24" }, "claude-sonnet-4-5": { "cost": [ @@ -78295,7 +102089,10 @@ 0.3, 3.75 ], - "limit": 200000 + "knowledge": "2025-07-31", + "limit": 200000, + "max_output": 64000, + "released": "2025-09-29" }, "claude-sonnet-4-6": { "cost": [ @@ -78304,7 +102101,10 @@ 0.3, 3.75 ], - "limit": 1000000 + "knowledge": "2025-08-31", + "limit": 1000000, + "max_output": 64000, + "released": "2026-02-17" }, "claude-sonnet-5": { "cost": [ @@ -78313,7 +102113,10 @@ 0.2, 2.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 64000, + "released": "2026-06-30" }, "mistral-large2": { "cost": [ @@ -78322,7 +102125,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-03-31", + "limit": 128000, + "max_output": 8192, + "open": true, + "released": "2024-07-24" }, "openai-gpt-4.1": { "cost": [ @@ -78331,7 +102138,10 @@ 0.5, 0.0 ], - "limit": 128000 + "knowledge": "2024-04", + "limit": 128000, + "max_output": 32000, + "released": "2025-04-14" }, "openai-gpt-5": { "cost": [ @@ -78340,7 +102150,10 @@ 0.13, 0.0 ], - "limit": 272000 + "knowledge": "2024-09-30", + "limit": 272000, + "max_output": 8192, + "released": "2025-08-07" }, "openai-gpt-5-mini": { "cost": [ @@ -78349,7 +102162,10 @@ 0.03, 0.0 ], - "limit": 272000 + "knowledge": "2024-05-30", + "limit": 272000, + "max_output": 8192, + "released": "2025-08-07" }, "openai-gpt-5-nano": { "cost": [ @@ -78358,7 +102174,10 @@ 0.01, 0.0 ], - "limit": 272000 + "knowledge": "2024-05-30", + "limit": 272000, + "max_output": 8192, + "released": "2025-08-07" }, "openai-gpt-5.1": { "cost": [ @@ -78367,7 +102186,10 @@ 0.13, 0.0 ], - "limit": 272000 + "knowledge": "2024-09-30", + "limit": 272000, + "max_output": 8192, + "released": "2025-11-13" }, "openai-gpt-5.2": { "cost": [ @@ -78376,7 +102198,10 @@ 0.18, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "openai-gpt-5.4": { "cost": [ @@ -78385,7 +102210,10 @@ 0.25, 0.0 ], + "knowledge": "2025-08-31", "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05", "tiers": [ { "cost": [ @@ -78408,7 +102236,10 @@ 0.5, 0.0 ], + "knowledge": "2025-12-01", "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23", "status": "beta", "tiers": [ { @@ -78432,7 +102263,10 @@ 0.02, 0.25 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -78455,7 +102289,10 @@ 0.4, 5.0 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -78478,7 +102315,10 @@ 0.2, 2.5 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -78506,7 +102346,11 @@ 0.0, 0.0 ], - "limit": 218000 + "knowledge": "2025-03-31", + "limit": 218000, + "max_output": 16384, + "open": true, + "released": "2025-09-23" }, "Qwen/Qwen3-VL-Embedding-8B": { "cost": [ @@ -78515,7 +102359,11 @@ 0.0, 0.0 ], - "limit": 32000 + "limit": 32000, + "max_output": 4096, + "open": true, + "released": "2026-02-05", + "type": "embedding" }, "Qwen/Qwen3.6-27B": { "cost": [ @@ -78525,6 +102373,9 @@ 0.0 ], "limit": 262144, + "max_output": 16384, + "open": true, + "released": "2026-04-22", "status": "deprecated" }, "cortecs/Llama-3.3-70B-Instruct-FP8-Dynamic": { @@ -78534,7 +102385,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2023-12", + "limit": 128000, + "max_output": 4096, + "open": true, + "released": "2024-12-06" }, "google/gemma-3-27b-it": { "cost": [ @@ -78543,7 +102398,11 @@ 0.0, 0.0 ], + "knowledge": "2024-08", "limit": 37000, + "max_output": 4096, + "open": true, + "released": "2025-03-12", "status": "deprecated" }, "intfloat/e5-mistral-7b-instruct": { @@ -78553,7 +102412,11 @@ 0.0, 0.0 ], - "limit": 4096 + "limit": 4096, + "max_output": 4096, + "open": true, + "released": "2023-12-11", + "type": "embedding" }, "openai/gpt-oss-120b": { "cost": [ @@ -78562,7 +102425,11 @@ 0.0, 0.0 ], - "limit": 131000 + "knowledge": "2024-06", + "limit": 131000, + "max_output": 8192, + "open": true, + "released": "2025-08-05" }, "openai/gpt-oss-20b": { "cost": [ @@ -78571,7 +102438,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 8192, + "open": true, + "released": "2025-08-05" } }, "name": "STACKIT" @@ -78585,7 +102456,10 @@ 1.0, 12.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 50000, + "released": "2026-06-09" }, "anthropic/claude-fable-5.1": { "cost": [ @@ -78594,7 +102468,10 @@ 0.25, 12.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 50000, + "released": "2026-09-01" }, "anthropic/claude-haiku-5.5": { "cost": [ @@ -78603,7 +102480,10 @@ 0.01, 0.125 ], + "knowledge": "2026-06", "limit": 1000000, + "max_output": 50000, + "released": "2026-10-07", "tiers": [ { "cost": [ @@ -78626,7 +102506,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-05", + "limit": 1000000, + "max_output": 50000, + "released": "2026-07-24" }, "anthropic/claude-opus-5.5": { "cost": [ @@ -78635,7 +102518,10 @@ 0.2, 5.0 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 50000, + "released": "2026-09-22" }, "anthropic/claude-sonnet-5": { "cost": [ @@ -78644,7 +102530,10 @@ 0.2, 2.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 50000, + "released": "2026-06-30" }, "anthropic/claude-sonnet-5.5": { "cost": [ @@ -78653,7 +102542,10 @@ 0.1, 2.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 50000, + "released": "2026-09-28" }, "deepseek/deepseek-v4-flash": { "cost": [ @@ -78662,7 +102554,11 @@ 0.01652, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 50000, + "open": true, + "released": "2026-04-24" }, "deepseek/deepseek-v4-flash-0731": { "cost": [ @@ -78671,7 +102567,11 @@ 0.014, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 50000, + "open": true, + "released": "2026-07-31" }, "deepseek/deepseek-v4-pro": { "cost": [ @@ -78680,7 +102580,11 @@ 0.2088, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 50000, + "open": true, + "released": "2026-04-24" }, "deepseek/deepseek-v4-pro-0813": { "cost": [ @@ -78689,7 +102593,10 @@ 0.1122, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 50000, + "open": true, + "released": "2026-08-13" }, "deepseek/deepseek-v4.1-flash": { "cost": [ @@ -78698,7 +102605,11 @@ 0.0042, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 50000, + "open": true, + "released": "2026-09-10" }, "google/gemini-2.5-flash": { "cost": [ @@ -78707,7 +102618,10 @@ 0.03, 0.083333 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 50000, + "released": "2025-06-17" }, "google/gemini-2.5-pro": { "cost": [ @@ -78716,7 +102630,10 @@ 0.125, 0.375 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 50000, + "released": "2025-06-17", "tiers": [ { "cost": [ @@ -78739,7 +102656,10 @@ 0.2, 0.375 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 50000, + "released": "2026-02-19", "tiers": [ { "cost": [ @@ -78762,7 +102682,10 @@ 0.03, 0.083333 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 50000, + "released": "2026-07-21" }, "google/gemini-3.8-flash": { "cost": [ @@ -78771,7 +102694,9 @@ 0.075, 0.041667 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 50000, + "released": "2026-09-02" }, "minimax/minimax-m3": { "cost": [ @@ -78780,7 +102705,10 @@ 0.06, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 50000, + "open": true, + "released": "2026-06-01" }, "mistralai/mistral-large-4-0": { "cost": [ @@ -78789,7 +102717,9 @@ 0.07, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 50000, + "released": "2026-10-06" }, "moonshotai/kimi-k3": { "cost": [ @@ -78798,7 +102728,10 @@ 0.3, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 50000, + "open": true, + "released": "2026-07-16" }, "openai/gpt-5.6-luna": { "cost": [ @@ -78807,7 +102740,10 @@ 0.02, 0.25 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 50000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -78830,7 +102766,10 @@ 0.4, 5.0 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 50000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -78853,7 +102792,10 @@ 0.2, 2.5 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 50000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -78876,7 +102818,10 @@ 1.0, 12.5 ], + "knowledge": "2026-04-30", "limit": 1050000, + "max_output": 50000, + "released": "2026-09-04", "tiers": [ { "cost": [ @@ -78899,7 +102844,10 @@ 0.01, 0.125 ], + "knowledge": "2026-05-18", "limit": 1050000, + "max_output": 50000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -78923,6 +102871,8 @@ 0.038 ], "limit": 1000000, + "max_output": 50000, + "released": "2026-07-15", "tiers": [ { "cost": [ @@ -78957,7 +102907,9 @@ 0.295, 1.84375 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 50000, + "released": "2026-05-21" }, "qwen/qwen3.7-plus": { "cost": [ @@ -78966,7 +102918,10 @@ 0.064, 0.4 ], + "knowledge": "2025-04", "limit": 1000000, + "max_output": 50000, + "released": "2026-06-02", "tiers": [ { "cost": [ @@ -78989,7 +102944,10 @@ 0.085, 0.53125 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-08-14" }, "qwen/qwen3.8-flash": { "cost": [ @@ -78998,7 +102956,9 @@ 0.016, 0.2 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 50000, + "released": "2026-08-26" }, "qwen/qwen3.8-max-0902": { "cost": [ @@ -79007,7 +102967,9 @@ 0.25, 2.5 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 50000, + "released": "2026-09-02" }, "x-ai/grok-4.3": { "cost": [ @@ -79017,6 +102979,8 @@ 0.0 ], "limit": 1000000, + "max_output": 30000, + "released": "2026-04-17", "tiers": [ { "cost": [ @@ -79039,7 +103003,11 @@ 0.0028, 0.0 ], - "limit": 1048576 + "knowledge": "2024-12", + "limit": 1048576, + "max_output": 50000, + "open": true, + "released": "2026-04-22" }, "xiaomi/mimo-v2.5-pro": { "cost": [ @@ -79048,7 +103016,11 @@ 0.0036, 0.0 ], - "limit": 1048576 + "knowledge": "2024-12", + "limit": 1048576, + "max_output": 50000, + "open": true, + "released": "2026-04-22" }, "xiaomi/mimo-v2.6-flash": { "cost": [ @@ -79057,7 +103029,10 @@ 0.0028, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 50000, + "open": true, + "released": "2026-09-22" }, "xiaomi/mimo-v2.6-pro": { "cost": [ @@ -79066,7 +103041,10 @@ 0.0036, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 50000, + "open": true, + "released": "2026-09-22" }, "z-ai/glm-5.2": { "cost": [ @@ -79075,7 +103053,10 @@ 0.105, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 50000, + "open": true, + "released": "2026-06-13" }, "z-ai/glm-5.3": { "cost": [ @@ -79084,7 +103065,10 @@ 0.26, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 50000, + "open": true, + "released": "2026-08-14" }, "z-ai/glm-5.3-flash": { "cost": [ @@ -79093,7 +103077,10 @@ 0.012, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 50000, + "open": true, + "released": "2026-08-26" } }, "name": "Standard Compute" @@ -79107,7 +103094,11 @@ 0.02092, 0.0 ], - "limit": 256000 + "knowledge": "2025-01", + "limit": 256000, + "max_output": 256000, + "open": true, + "released": "2026-01-29" }, "step-3.5-flash-2603": { "cost": [ @@ -79116,7 +103107,11 @@ 0.02092, 0.0 ], - "limit": 256000 + "knowledge": "2025-01", + "limit": 256000, + "max_output": 256000, + "open": true, + "released": "2026-04-02" }, "step-3.7-flash": { "cost": [ @@ -79125,7 +103120,11 @@ 0.04035, 0.0 ], - "limit": 256000 + "knowledge": "2026-03-01", + "limit": 256000, + "max_output": 256000, + "open": true, + "released": "2026-05-29" }, "step-5-preview": { "cost": [ @@ -79134,7 +103133,10 @@ 0.10461, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 65536, + "open": true, + "released": "2026-09-16" } }, "name": "StepFun (China)" @@ -79148,7 +103150,11 @@ 0.02, 0.0 ], - "limit": 256000 + "knowledge": "2025-01", + "limit": 256000, + "max_output": 256000, + "open": true, + "released": "2026-01-29" }, "step-3.5-flash-2603": { "cost": [ @@ -79157,7 +103163,11 @@ 0.02, 0.0 ], - "limit": 256000 + "knowledge": "2025-01", + "limit": 256000, + "max_output": 256000, + "open": true, + "released": "2026-04-02" }, "step-3.7-flash": { "cost": [ @@ -79166,7 +103176,11 @@ 0.04, 0.0 ], - "limit": 256000 + "knowledge": "2026-03-01", + "limit": 256000, + "max_output": 256000, + "open": true, + "released": "2026-05-29" }, "step-5-preview": { "cost": [ @@ -79175,7 +103189,10 @@ 0.1, 0.0 ], - "limit": 1024000 + "limit": 1024000, + "max_output": 65536, + "open": true, + "released": "2026-09-16" } }, "name": "StepFun (Global)" @@ -79189,7 +103206,11 @@ 0.0028, 0.0 ], - "limit": 5000000 + "knowledge": "2025-05", + "limit": 5000000, + "max_output": 384000, + "open": true, + "released": "2026-09-10" }, "subconscious/glm-5.3-marathon": { "cost": [ @@ -79198,7 +103219,10 @@ 0.26, 0.0 ], - "limit": 5000000 + "limit": 5000000, + "max_output": 131072, + "open": true, + "released": "2026-08-14" } }, "name": "Subconscious" @@ -79212,7 +103236,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 131072, + "open": true, + "released": "2025-07-21" }, "Qwen/Qwen3-235B-A22B-Thinking-2507": { "cost": [ @@ -79221,7 +103248,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 131072, + "open": true, + "released": "2025-07-25" }, "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": { "cost": [ @@ -79230,7 +103260,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-04", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2025-07-22" }, "deepseek-ai/DeepSeek-R1-0528": { "cost": [ @@ -79239,7 +103273,10 @@ 0.0, 0.0 ], - "limit": 75000 + "limit": 75000, + "max_output": 163840, + "open": true, + "released": "2025-05-28" }, "deepseek-ai/DeepSeek-V3-0324": { "cost": [ @@ -79248,7 +103285,10 @@ 0.0, 0.0 ], - "limit": 75000 + "limit": 75000, + "max_output": 163840, + "open": true, + "released": "2025-03-24" }, "deepseek-ai/DeepSeek-V3.1": { "cost": [ @@ -79257,7 +103297,10 @@ 0.0, 0.0 ], - "limit": 75000 + "limit": 75000, + "max_output": 163840, + "open": true, + "released": "2025-08-21" }, "openai/gpt-oss-120b": { "cost": [ @@ -79266,7 +103309,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "zai-org/GLM-4.5-Air": { "cost": [ @@ -79275,7 +103322,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2025-04", + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2025-07-28" }, "zai-org/GLM-4.5-FP8": { "cost": [ @@ -79284,7 +103335,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2025-04", + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2025-07-28" } }, "name": "submodel" @@ -79299,6 +103354,9 @@ 0.0 ], "limit": 524288, + "max_output": 65536, + "open": true, + "released": "2026-06-01", "status": "deprecated" }, "hf:Qwen/Qwen3.6-27B": { @@ -79309,6 +103367,9 @@ 0.0 ], "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-04-22", "status": "deprecated" }, "hf:deepseek-ai/DeepSeek-V4.1-Flash": { @@ -79318,7 +103379,11 @@ 0.03, 0.0 ], - "limit": 524288 + "knowledge": "2025-05", + "limit": 524288, + "max_output": 65536, + "open": true, + "released": "2026-09-10" }, "hf:deepseek-ai/DeepSeek-V4.1-Flash-1017": { "cost": [ @@ -79327,7 +103392,11 @@ 0.03, 0.0 ], - "limit": 524288 + "knowledge": "2025-05", + "limit": 524288, + "max_output": 65536, + "open": true, + "released": "2026-10-17" }, "hf:moonshotai/Kimi-K2.7-Code": { "cost": [ @@ -79336,7 +103405,11 @@ 0.95, 0.0 ], + "knowledge": "2025-01", "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-06-12", "status": "deprecated" }, "hf:moonshotai/Kimi-K3": { @@ -79346,7 +103419,10 @@ 0.45, 0.0 ], - "limit": 524288 + "limit": 524288, + "max_output": 65536, + "open": true, + "released": "2026-07-16" }, "hf:nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4": { "cost": [ @@ -79355,7 +103431,11 @@ 0.06, 0.0 ], - "limit": 262144 + "knowledge": "2025-06", + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-03-11" }, "hf:openai/gpt-oss-120b": { "cost": [ @@ -79364,7 +103444,11 @@ 0.02, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 65536, + "open": true, + "released": "2025-08-05" }, "hf:zai-org/GLM-4.7-Flash": { "cost": [ @@ -79373,7 +103457,11 @@ 0.02, 0.0 ], - "limit": 196608 + "knowledge": "2025-04", + "limit": 196608, + "max_output": 65536, + "open": true, + "released": "2026-01-19" }, "hf:zai-org/GLM-5.2": { "cost": [ @@ -79383,6 +103471,9 @@ 0.0 ], "limit": 524288, + "max_output": 65536, + "open": true, + "released": "2026-06-13", "status": "deprecated" }, "hf:zai-org/GLM-5.3": { @@ -79392,7 +103483,10 @@ 0.26, 0.0 ], - "limit": 524288 + "limit": 524288, + "max_output": 65536, + "open": true, + "released": "2026-08-14" }, "hf:zai-org/GLM-5.3-Flash": { "cost": [ @@ -79401,7 +103495,10 @@ 0.04, 0.0 ], - "limit": 524288 + "limit": 524288, + "max_output": 65536, + "open": true, + "released": "2026-08-26" } }, "name": "Synthetic" @@ -79415,7 +103512,10 @@ 1.0, 12.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-09" }, "anthropic/claude-fable-5-1": { "cost": [ @@ -79424,7 +103524,10 @@ 0.25, 12.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-01" }, "anthropic/claude-haiku-4-5": { "cost": [ @@ -79433,7 +103536,10 @@ 0.1, 1.25 ], - "limit": 200000 + "knowledge": "2025-02-28", + "limit": 200000, + "max_output": 64000, + "released": "2025-10-15" }, "anthropic/claude-haiku-4-5-20251001": { "cost": [ @@ -79442,7 +103548,10 @@ 0.1, 1.25 ], - "limit": 200000 + "knowledge": "2025-02-28", + "limit": 200000, + "max_output": 64000, + "released": "2025-10-15" }, "anthropic/claude-opus-4-5": { "cost": [ @@ -79451,7 +103560,10 @@ 0.5, 6.25 ], - "limit": 200000 + "knowledge": "2025-05", + "limit": 200000, + "max_output": 64000, + "released": "2025-11-24" }, "anthropic/claude-opus-4-5-20251101": { "cost": [ @@ -79460,7 +103572,10 @@ 0.5, 6.25 ], - "limit": 200000 + "knowledge": "2025-05", + "limit": 200000, + "max_output": 64000, + "released": "2025-11-24" }, "anthropic/claude-opus-4-6": { "cost": [ @@ -79469,7 +103584,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2025-05-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-05" }, "anthropic/claude-opus-4-7": { "cost": [ @@ -79478,7 +103596,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-16" }, "anthropic/claude-opus-4-8": { "cost": [ @@ -79487,7 +103608,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-28" }, "anthropic/claude-opus-5": { "cost": [ @@ -79496,7 +103620,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-05", + "limit": 1000000, + "max_output": 128000, + "released": "2026-07-24" }, "anthropic/claude-sonnet-4-5": { "cost": [ @@ -79505,7 +103632,10 @@ 0.3, 3.75 ], - "limit": 200000 + "knowledge": "2025-07-31", + "limit": 200000, + "max_output": 64000, + "released": "2025-09-29" }, "anthropic/claude-sonnet-4-5-20250929": { "cost": [ @@ -79514,7 +103644,10 @@ 0.3, 3.75 ], - "limit": 200000 + "knowledge": "2025-07-31", + "limit": 200000, + "max_output": 64000, + "released": "2025-09-29" }, "anthropic/claude-sonnet-4-6": { "cost": [ @@ -79523,7 +103656,10 @@ 0.3, 3.75 ], - "limit": 1000000 + "knowledge": "2025-08-31", + "limit": 1000000, + "max_output": 64000, + "released": "2026-02-17" }, "anthropic/claude-sonnet-5": { "cost": [ @@ -79532,7 +103668,10 @@ 0.2, 2.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-30" }, "cerebras/gpt-oss-120b": { "cost": [ @@ -79541,7 +103680,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 40960, + "open": true, + "released": "2025-08-05" }, "cerebras/qwen-3.8-27b": { "cost": [ @@ -79550,7 +103693,10 @@ 0.0, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 40960, + "open": true, + "released": "2026-08-14" }, "deepseek/deepseek-flash": { "cost": [ @@ -79559,7 +103705,11 @@ 0.003, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-09-10" }, "deepseek/deepseek-v4-pro": { "cost": [ @@ -79568,7 +103718,10 @@ 0.022, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-08-13" }, "google/gemini-3-flash-preview": { "cost": [ @@ -79577,7 +103730,10 @@ 0.05, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2025-12-17" }, "google/gemini-3.1-flash-lite": { "cost": [ @@ -79586,7 +103742,10 @@ 0.025, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-05-07" }, "google/gemini-3.1-pro-preview": { "cost": [ @@ -79595,7 +103754,10 @@ 0.2, 0.0 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2026-02-19", "tiers": [ { "cost": [ @@ -79618,7 +103780,10 @@ 0.2, 0.0 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2026-02-19", "tiers": [ { "cost": [ @@ -79641,7 +103806,10 @@ 0.15, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-05-19" }, "google/gemini-3.5-flash-lite": { "cost": [ @@ -79650,7 +103818,10 @@ 0.03, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-07-21" }, "google/gemini-3.6-flash": { "cost": [ @@ -79659,7 +103830,10 @@ 0.075, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-07-21" }, "google/gemini-3.7-flash": { "cost": [ @@ -79668,7 +103842,10 @@ 0.075, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-08-13" }, "google/gemini-3.8-flash": { "cost": [ @@ -79677,7 +103854,9 @@ 0.075, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 65536, + "released": "2026-09-02" }, "google/gemini-embedding-001": { "cost": [ @@ -79686,7 +103865,11 @@ 0.0, 0.0 ], - "limit": 2048 + "knowledge": "2025-05", + "limit": 2048, + "max_output": 1, + "released": "2025-05-20", + "type": "embedding" }, "google/gemini-embedding-2": { "cost": [ @@ -79695,7 +103878,11 @@ 0.0, 0.0 ], - "limit": 8192 + "knowledge": "2025-11", + "limit": 8192, + "max_output": 1, + "released": "2026-04-22", + "type": "embedding" }, "google/gemini-flash-latest": { "cost": [ @@ -79704,7 +103891,10 @@ 0.075, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-08-13" }, "google/gemini-flash-lite-latest": { "cost": [ @@ -79713,7 +103903,10 @@ 0.03, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-07-21" }, "groq/allam-2-7b": { "cost": [ @@ -79722,7 +103915,10 @@ 0.0, 0.0 ], - "limit": 4096 + "limit": 4096, + "max_output": 4096, + "open": true, + "released": "2025-01-23" }, "groq/openai/gpt-oss-120b": { "cost": [ @@ -79731,7 +103927,11 @@ 0.075, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 65536, + "open": true, + "released": "2025-08-05" }, "groq/openai/gpt-oss-20b": { "cost": [ @@ -79740,7 +103940,11 @@ 0.0375, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 65536, + "open": true, + "released": "2025-08-05" }, "groq/qwen/qwen3.8-27b": { "cost": [ @@ -79749,7 +103953,10 @@ 0.4, 0.0 ], - "limit": 131042 + "limit": 131042, + "max_output": 16384, + "open": true, + "released": "2026-08-14" }, "minimax/MiniMax-M2.7": { "cost": [ @@ -79759,6 +103966,9 @@ 0.375 ], "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-03-18", "status": "deprecated" }, "minimax/MiniMax-M2.7-highspeed": { @@ -79769,6 +103979,9 @@ 0.375 ], "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-03-18", "status": "deprecated" }, "minimax/MiniMax-M3": { @@ -79779,6 +103992,9 @@ 0.0 ], "limit": 1048576, + "max_output": 512000, + "open": true, + "released": "2026-06-01", "tiers": [ { "cost": [ @@ -79801,7 +104017,10 @@ 0.0, 0.0 ], - "limit": 8000 + "limit": 8000, + "max_output": 3072, + "released": "2023-12-11", + "type": "embedding" }, "mistral/mistral-large-2512": { "cost": [ @@ -79810,7 +104029,11 @@ 0.05, 0.0 ], - "limit": 262144 + "knowledge": "2024-11", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2025-12-02" }, "mistral/mistral-large-latest": { "cost": [ @@ -79819,7 +104042,11 @@ 0.05, 0.0 ], - "limit": 262144 + "knowledge": "2024-11", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2024-11-01" }, "mistral/mistral-medium-2604": { "cost": [ @@ -79828,7 +104055,10 @@ 0.15, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-29" }, "mistral/mistral-medium-latest": { "cost": [ @@ -79837,7 +104067,10 @@ 0.15, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-29" }, "mistral/mistral-small-2603": { "cost": [ @@ -79846,7 +104079,11 @@ 0.015, 0.0 ], - "limit": 256000 + "knowledge": "2025-06", + "limit": 256000, + "max_output": 256000, + "open": true, + "released": "2026-03-16" }, "mistral/mistral-small-latest": { "cost": [ @@ -79855,7 +104092,11 @@ 0.015, 0.0 ], - "limit": 256000 + "knowledge": "2025-06", + "limit": 256000, + "max_output": 256000, + "open": true, + "released": "2026-03-16" }, "mistral/voxtral-small-latest": { "cost": [ @@ -79864,7 +104105,10 @@ 0.0, 0.0 ], - "limit": 32000 + "limit": 32000, + "max_output": 32000, + "open": true, + "released": "2025-07-15" }, "mistral/zai-glm-5-2": { "cost": [ @@ -79874,6 +104118,9 @@ 0.0 ], "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-13", "status": "deprecated" }, "mistral/zai-glm-5-3": { @@ -79883,7 +104130,10 @@ 0.14, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "moonshot/kimi-k2.6": { "cost": [ @@ -79892,7 +104142,11 @@ 0.16, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-20" }, "moonshot/kimi-k2.7-code": { "cost": [ @@ -79901,7 +104155,11 @@ 0.19, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-06-12" }, "moonshot/kimi-k2.7-code-highspeed": { "cost": [ @@ -79910,7 +104168,11 @@ 0.38, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-06-12" }, "moonshot/kimi-k3": { "cost": [ @@ -79919,7 +104181,10 @@ 0.3, 3.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-16" }, "xai/grok-4.20-0309-non-reasoning": { "cost": [ @@ -79929,6 +104194,8 @@ 0.0 ], "limit": 1000000, + "max_output": 30000, + "released": "2026-03-09", "tiers": [ { "cost": [ @@ -79952,6 +104219,8 @@ 0.0 ], "limit": 1000000, + "max_output": 30000, + "released": "2026-03-09", "tiers": [ { "cost": [ @@ -79975,6 +104244,8 @@ 0.0 ], "limit": 1000000, + "max_output": 30000, + "released": "2026-04-17", "tiers": [ { "cost": [ @@ -79998,6 +104269,8 @@ 0.0 ], "limit": 500000, + "max_output": 500000, + "released": "2026-07-08", "tiers": [ { "cost": [ @@ -80020,7 +104293,10 @@ 0.5, 0.0 ], + "knowledge": "2026-02-01", "limit": 500000, + "max_output": 500000, + "released": "2026-08-12", "tiers": [ { "cost": [ @@ -80043,7 +104319,10 @@ 0.5, 0.0 ], + "knowledge": "2026-05", "limit": 500000, + "max_output": 500000, + "released": "2026-09-21", "tiers": [ { "cost": [ @@ -80067,6 +104346,8 @@ 0.0 ], "limit": 256000, + "max_output": 256000, + "released": "2026-04-16", "tiers": [ { "cost": [ @@ -80089,7 +104370,10 @@ 0.0028, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-09-22" }, "xiaomi-mimo/mimo-v2.6-pro": { "cost": [ @@ -80098,7 +104382,10 @@ 0.0036, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-09-22" }, "xiaomi-mimo/mimo-v2.6-pro-ultraspeed": { "cost": [ @@ -80107,7 +104394,10 @@ 0.036, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-09-21" }, "zai/glm-4.5": { "cost": [ @@ -80116,7 +104406,11 @@ 0.11, 0.0 ], - "limit": 131072 + "knowledge": "2025-04", + "limit": 131072, + "max_output": 98304, + "open": true, + "released": "2025-07-28" }, "zai/glm-4.5-air": { "cost": [ @@ -80125,7 +104419,11 @@ 0.03, 0.0 ], - "limit": 131072 + "knowledge": "2025-04", + "limit": 131072, + "max_output": 98304, + "open": true, + "released": "2025-07-28" }, "zai/glm-4.5-flash": { "cost": [ @@ -80134,7 +104432,10 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2025-04", + "limit": 131072, + "max_output": 98304, + "released": "2025-07-28" }, "zai/glm-4.5v": { "cost": [ @@ -80143,7 +104444,11 @@ 0.11, 0.0 ], - "limit": 64000 + "knowledge": "2025-04", + "limit": 64000, + "max_output": 16384, + "open": true, + "released": "2025-08-11" }, "zai/glm-4.6": { "cost": [ @@ -80152,7 +104457,11 @@ 0.11, 0.0 ], - "limit": 204800 + "knowledge": "2025-04", + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-09-30" }, "zai/glm-4.6v": { "cost": [ @@ -80161,7 +104470,11 @@ 0.05, 0.0 ], - "limit": 128000 + "knowledge": "2025-04", + "limit": 128000, + "max_output": 32768, + "open": true, + "released": "2025-12-08" }, "zai/glm-4.6v-flash": { "cost": [ @@ -80170,7 +104483,10 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 32768, + "open": true, + "released": "2025-12-08" }, "zai/glm-4.7": { "cost": [ @@ -80179,7 +104495,11 @@ 0.11, 0.0 ], - "limit": 204800 + "knowledge": "2025-04", + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-12-22" }, "zai/glm-4.7-flash": { "cost": [ @@ -80188,7 +104508,11 @@ 0.0, 0.0 ], - "limit": 200000 + "knowledge": "2025-04", + "limit": 200000, + "max_output": 131072, + "open": true, + "released": "2026-01-19" }, "zai/glm-4.7-flashx": { "cost": [ @@ -80197,7 +104521,11 @@ 0.01, 0.0 ], - "limit": 200000 + "knowledge": "2025-04", + "limit": 200000, + "max_output": 131072, + "open": true, + "released": "2026-01-19" }, "zai/glm-5": { "cost": [ @@ -80206,7 +104534,10 @@ 0.2, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-02-12" }, "zai/glm-5-turbo": { "cost": [ @@ -80215,7 +104546,9 @@ 0.24, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 131072, + "released": "2026-03-16" }, "zai/glm-5.1": { "cost": [ @@ -80224,7 +104557,10 @@ 0.26, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 131072, + "open": true, + "released": "2026-04-07" }, "zai/glm-5.2": { "cost": [ @@ -80233,7 +104569,10 @@ 0.26, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "zai/glm-5.3": { "cost": [ @@ -80242,7 +104581,10 @@ 0.26, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "zai/glm-5.3-flash": { "cost": [ @@ -80251,7 +104593,10 @@ 0.03, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-26" }, "zai/glm-5.3-flashx": { "cost": [ @@ -80260,7 +104605,10 @@ 0.075, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-09-18" }, "zai/glm-5v-turbo": { "cost": [ @@ -80269,7 +104617,9 @@ 0.24, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 131072, + "released": "2026-04-01" } }, "name": "Tempr Gateway" @@ -80284,6 +104634,9 @@ 0.0 ], "limit": 202752, + "max_output": 16384, + "open": true, + "released": "2026-02-12", "status": "deprecated" }, "hunyuan-2.0-instruct": { @@ -80294,6 +104647,8 @@ 0.0 ], "limit": 131072, + "max_output": 16384, + "released": "2026-03-08", "status": "deprecated" }, "hunyuan-2.0-thinking": { @@ -80304,6 +104659,8 @@ 0.0 ], "limit": 131072, + "max_output": 16384, + "released": "2026-03-08", "status": "deprecated" }, "hunyuan-t1": { @@ -80314,6 +104671,8 @@ 0.0 ], "limit": 131072, + "max_output": 16384, + "released": "2026-03-08", "status": "deprecated" }, "hunyuan-turbos": { @@ -80324,6 +104683,8 @@ 0.0 ], "limit": 131072, + "max_output": 16384, + "released": "2026-03-08", "status": "deprecated" }, "kimi-k2.5": { @@ -80333,7 +104694,11 @@ 0.0, 0.0 ], + "knowledge": "2025-01", "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-01-27", "status": "deprecated" }, "minimax-m2.5": { @@ -80344,6 +104709,9 @@ 0.0 ], "limit": 204800, + "max_output": 32768, + "open": true, + "released": "2026-02-12", "status": "deprecated" }, "tc-code-latest": { @@ -80353,7 +104721,9 @@ 0.0, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 16384, + "released": "2026-03-08" } }, "name": "Tencent Coding Plan (China)" @@ -80367,7 +104737,10 @@ 0.0, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 128000, + "open": true, + "released": "2026-07-06" }, "hy4-preview": { "cost": [ @@ -80376,7 +104749,10 @@ 0.042, 0.0 ], - "limit": 1024000 + "limit": 1024000, + "max_output": 64000, + "open": true, + "released": "2026-08-28" } }, "name": "Tencent Token Plan" @@ -80390,7 +104766,10 @@ 0.0, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 128000, + "open": true, + "released": "2026-07-06" }, "hy3-preview": { "cost": [ @@ -80399,7 +104778,10 @@ 0.0, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 64000, + "open": true, + "released": "2026-04-20" }, "hy4-preview": { "cost": [ @@ -80408,7 +104790,10 @@ 0.042, 0.0 ], - "limit": 1024000 + "limit": 1024000, + "max_output": 64000, + "open": true, + "released": "2026-08-28" } }, "name": "Tencent TokenHub" @@ -80422,7 +104807,11 @@ 0.165, 0.825 ], + "knowledge": "2024-07", "limit": 164000, + "max_output": 8192, + "open": true, + "released": "2025-05-28", "status": "deprecated" }, "deepseek/deepseek-v3.2": { @@ -80432,7 +104821,11 @@ 0.075, 0.375 ], + "knowledge": "2025-05", "limit": 163840, + "max_output": 163840, + "open": true, + "released": "2025-12-01", "status": "deprecated" }, "deepseek/deepseek-v4-flash-0731": { @@ -80442,7 +104835,11 @@ 0.06, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-07-31" }, "deepseek/deepseek-v4-pro": { "cost": [ @@ -80451,7 +104848,11 @@ 0.4375, 2.185 ], + "knowledge": "2025-05", "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-04-24", "status": "deprecated" }, "deepseek/deepseek-v4-pro-0813": { @@ -80461,7 +104862,10 @@ 0.5, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 64000, + "open": true, + "released": "2026-08-13" }, "deepseek/deepseek-v4.1-flash": { "cost": [ @@ -80470,7 +104874,11 @@ 0.13, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-09-10" }, "minimax/minimax-m2.5": { "cost": [ @@ -80480,6 +104888,9 @@ 0.375 ], "limit": 196608, + "max_output": 65536, + "open": true, + "released": "2026-02-12", "status": "deprecated" }, "minimax/minimax-m3": { @@ -80489,7 +104900,10 @@ 0.1, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-06-01" }, "moonshotai/kimi-k2.5": { "cost": [ @@ -80498,7 +104912,11 @@ 0.125, 0.625 ], + "knowledge": "2025-01", "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-01-27", "status": "deprecated" }, "moonshotai/kimi-k2.6": { @@ -80508,7 +104926,11 @@ 0.25, 1.25 ], + "knowledge": "2025-01", "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-20", "status": "deprecated" }, "moonshotai/kimi-k2.7-code": { @@ -80518,7 +104940,11 @@ 0.3125, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-06-12" }, "moonshotai/kimi-k3": { "cost": [ @@ -80527,7 +104953,10 @@ 0.75, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-16" }, "qwen/qwen3-235b-a22b-2507": { "cost": [ @@ -80536,7 +104965,11 @@ 0.018, 0.09 ], + "knowledge": "2025-06-30", "limit": 131000, + "max_output": 262144, + "open": true, + "released": "2025-07-21", "status": "deprecated" }, "qwen/qwen3.5-122b-a10b": { @@ -80547,6 +104980,9 @@ 0.625 ], "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-02-23", "status": "deprecated" }, "qwen/qwen3.5-9b": { @@ -80557,6 +104993,9 @@ 0.1875 ], "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-23", "status": "deprecated" }, "qwen/qwen3.8-2.4t-a95b": { @@ -80566,7 +105005,10 @@ 0.63, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 64000, + "open": true, + "released": "2026-08-12" }, "qwen/qwen3.8-27b": { "cost": [ @@ -80575,7 +105017,10 @@ 0.1, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-08-14" }, "qwen/qwen3.8-flash-next": { "cost": [ @@ -80584,7 +105029,10 @@ 0.05, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 64000, + "open": true, + "released": "2026-08-27" }, "z-ai/glm-5": { "cost": [ @@ -80594,6 +105042,9 @@ 1.25 ], "limit": 202752, + "max_output": 202752, + "open": true, + "released": "2026-02-12", "status": "deprecated" }, "z-ai/glm-5-turbo": { @@ -80604,6 +105055,8 @@ 1.5 ], "limit": 202752, + "max_output": 131072, + "released": "2026-03-16", "status": "deprecated" }, "z-ai/glm-5.1": { @@ -80614,6 +105067,9 @@ 1.75 ], "limit": 202752, + "max_output": 202752, + "open": true, + "released": "2026-04-07", "status": "deprecated" }, "z-ai/glm-5.2": { @@ -80623,7 +105079,10 @@ 0.375, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "z-ai/glm-5.3": { "cost": [ @@ -80632,7 +105091,10 @@ 0.44, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 64000, + "open": true, + "released": "2026-08-14" }, "z-ai/glm-5.3-flash": { "cost": [ @@ -80641,7 +105103,10 @@ 0.05, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 64000, + "open": true, + "released": "2026-08-26" }, "z-ai/glm-5v-turbo": { "cost": [ @@ -80651,6 +105116,8 @@ 1.5 ], "limit": 202752, + "max_output": 131072, + "released": "2026-04-01", "status": "deprecated" } }, @@ -80665,7 +105132,10 @@ 0.039, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 32768, + "open": true, + "released": "2025-04-29" }, "Qwen/Qwen3.5-35B-A3B-Base": { "cost": [ @@ -80674,7 +105144,10 @@ 0.108, 0.0 ], - "limit": 65536 + "limit": 65536, + "max_output": 65536, + "open": true, + "released": "2026-02-24" }, "Qwen/Qwen3.5-397B-A17B": { "cost": [ @@ -80683,7 +105156,10 @@ 0.33, 0.0 ], - "limit": 65536 + "limit": 65536, + "max_output": 65536, + "open": true, + "released": "2026-02-15" }, "Qwen/Qwen3.5-397B-A17B:peft:262144": { "cost": [ @@ -80692,7 +105168,10 @@ 0.33, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-02-15" }, "Qwen/Qwen3.5-4B": { "cost": [ @@ -80701,7 +105180,10 @@ 0.066, 0.0 ], - "limit": 65536 + "limit": 65536, + "max_output": 65536, + "open": true, + "released": "2026-03-02" }, "Qwen/Qwen3.5-4B:peft:262144": { "cost": [ @@ -80710,7 +105192,10 @@ 0.066, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-03-02" }, "Qwen/Qwen3.5-9B": { "cost": [ @@ -80719,7 +105204,10 @@ 0.06, 0.0 ], - "limit": 65536 + "limit": 65536, + "max_output": 65536, + "open": true, + "released": "2026-02-23" }, "Qwen/Qwen3.5-9B-Base": { "cost": [ @@ -80728,7 +105216,10 @@ 0.06, 0.0 ], - "limit": 65536 + "limit": 65536, + "max_output": 65536, + "open": true, + "released": "2026-02-26" }, "Qwen/Qwen3.6-27B": { "cost": [ @@ -80737,7 +105228,10 @@ 0.372, 0.0 ], - "limit": 65536 + "limit": 65536, + "max_output": 65536, + "open": true, + "released": "2026-04-22" }, "Qwen/Qwen3.6-35B-A3B": { "cost": [ @@ -80746,7 +105240,10 @@ 0.09, 0.0 ], - "limit": 65536 + "limit": 65536, + "max_output": 65536, + "open": true, + "released": "2026-04-17" }, "Qwen/Qwen3.6-35B-A3B:peft:262144": { "cost": [ @@ -80755,7 +105252,10 @@ 0.09, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-17" }, "Qwen/Qwen3.8-27B": { "cost": [ @@ -80764,7 +105264,10 @@ 0.1395, 0.0 ], - "limit": 65536 + "limit": 65536, + "max_output": 65536, + "open": true, + "released": "2026-08-14" }, "Qwen/Qwen3.8-27B:peft:262144": { "cost": [ @@ -80773,7 +105276,10 @@ 0.1395, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-08-14" }, "deepseek-ai/DeepSeek-V3.1": { "cost": [ @@ -80782,7 +105288,10 @@ 0.339, 0.0 ], - "limit": 32768 + "limit": 32768, + "max_output": 32768, + "open": true, + "released": "2025-08-21" }, "deepseek-ai/DeepSeek-V4.1-Flash-1017:peft:262144": { "cost": [ @@ -80791,7 +105300,11 @@ 0.12, 0.0 ], - "limit": 262144 + "knowledge": "2025-05", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-10-17" }, "deepseek-ai/DeepSeek-V4.1-Flash:peft:262144": { "cost": [ @@ -80800,7 +105313,11 @@ 0.12, 0.0 ], - "limit": 262144 + "knowledge": "2025-05", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-09-10" }, "moonshotai/Kimi-K2.6": { "cost": [ @@ -80809,7 +105326,11 @@ 0.441, 0.0 ], - "limit": 32768 + "knowledge": "2025-01", + "limit": 32768, + "max_output": 32768, + "open": true, + "released": "2026-04-20" }, "moonshotai/Kimi-K2.6:peft:131072": { "cost": [ @@ -80818,7 +105339,11 @@ 0.441, 0.0 ], - "limit": 131072 + "knowledge": "2025-01", + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2026-04-20" }, "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16": { "cost": [ @@ -80827,7 +105352,11 @@ 0.039, 0.0 ], - "limit": 65536 + "knowledge": "2025-06-25", + "limit": 65536, + "max_output": 65536, + "open": true, + "released": "2025-12-15" }, "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16": { "cost": [ @@ -80836,7 +105365,11 @@ 0.114, 0.0 ], - "limit": 65536 + "knowledge": "2025-06", + "limit": 65536, + "max_output": 65536, + "open": true, + "released": "2026-03-11" }, "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16:peft:262144": { "cost": [ @@ -80845,7 +105378,11 @@ 0.114, 0.0 ], - "limit": 262144 + "knowledge": "2025-06", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-03-11" }, "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16": { "cost": [ @@ -80854,7 +105391,11 @@ 0.36, 0.0 ], - "limit": 65536 + "knowledge": "2025-09", + "limit": 65536, + "max_output": 65536, + "open": true, + "released": "2026-06-04" }, "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16:peft:262144": { "cost": [ @@ -80863,7 +105404,11 @@ 0.36, 0.0 ], - "limit": 262144 + "knowledge": "2025-09", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-06-04" }, "nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16": { "cost": [ @@ -80872,7 +105417,11 @@ 0.0368, 0.0 ], - "limit": 65536 + "knowledge": "2025-09", + "limit": 65536, + "max_output": 65536, + "open": true, + "released": "2026-08-11" }, "nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16:peft:262144": { "cost": [ @@ -80881,7 +105430,11 @@ 0.0368, 0.0 ], - "limit": 262144 + "knowledge": "2025-09", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-08-11" }, "nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16": { "cost": [ @@ -80890,7 +105443,10 @@ 0.114, 0.0 ], - "limit": 65536 + "limit": 65536, + "max_output": 65536, + "open": true, + "released": "2026-10-15" }, "nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16:peft:262144": { "cost": [ @@ -80899,7 +105455,10 @@ 0.114, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-10-15" }, "openai/gpt-oss-120b": { "cost": [ @@ -80908,7 +105467,11 @@ 0.066, 0.0 ], - "limit": 32768 + "knowledge": "2024-06", + "limit": 32768, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "openai/gpt-oss-120b:peft:131072": { "cost": [ @@ -80917,7 +105480,11 @@ 0.066, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2025-08-05" }, "openai/gpt-oss-20b": { "cost": [ @@ -80926,7 +105493,11 @@ 0.036, 0.0 ], - "limit": 32768 + "knowledge": "2024-06", + "limit": 32768, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "thinkingmachines/Inkling": { "cost": [ @@ -80935,7 +105506,10 @@ 0.374, 0.0 ], - "limit": 65536 + "limit": 65536, + "max_output": 65536, + "open": true, + "released": "2026-07-15" }, "thinkingmachines/Inkling-Small": { "cost": [ @@ -80944,7 +105518,10 @@ 0.116, 0.0 ], - "limit": 65536 + "limit": 65536, + "max_output": 65536, + "open": true, + "released": "2026-07-30" }, "thinkingmachines/Inkling-Small:peft:262144": { "cost": [ @@ -80953,7 +105530,10 @@ 0.116, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-07-30" }, "thinkingmachines/Inkling-Small:peft:262144:sampling-nvfp4": { "cost": [ @@ -80962,7 +105542,10 @@ 0.06, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-07-30" }, "thinkingmachines/Inkling:peft:262144": { "cost": [ @@ -80971,7 +105554,10 @@ 0.374, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-07-15" }, "thinkingmachines/Inkling:peft:262144:sampling-nvfp4": { "cost": [ @@ -80980,7 +105566,10 @@ 0.17, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-07-15" }, "zai-org/GLM-5.3-Flash:peft:262144": { "cost": [ @@ -80989,7 +105578,10 @@ 0.168, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-08-26" }, "zai-org/GLM-5.3:peft:262144": { "cost": [ @@ -80998,7 +105590,10 @@ 0.756, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-08-14" } }, "name": "Thinking Machines" @@ -81012,7 +105607,11 @@ 0.13, 0.0 ], + "knowledge": "2025-05", "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-09-10", "status": "beta" }, "gemma4-31b": { @@ -81022,7 +105621,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-04-02" }, "glm-5-3": { "cost": [ @@ -81031,7 +105634,10 @@ 0.45, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "gpt-oss-120b": { "cost": [ @@ -81040,7 +105646,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05" }, "gpt-oss-safeguard-120b": { "cost": [ @@ -81049,7 +105659,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-10-29" }, "kimi-k3": { "cost": [ @@ -81058,7 +105672,10 @@ 0.8, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 131072, + "open": true, + "released": "2026-07-16" }, "llama3-3-70b": { "cost": [ @@ -81067,7 +105684,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2023-12", + "limit": 131072, + "max_output": 4096, + "open": true, + "released": "2024-12-06" }, "nomic-embed-text": { "cost": [ @@ -81076,7 +105697,10 @@ 0.0, 0.0 ], - "limit": 8192 + "limit": 8192, + "max_output": 768, + "open": true, + "released": "2024-02" } }, "name": "Tinfoil" @@ -81091,6 +105715,9 @@ 0.0 ], "limit": 32768, + "max_output": 32768, + "open": true, + "released": "2026-02-24", "status": "deprecated" }, "MiniMaxAI/MiniMax-M2.5": { @@ -81101,6 +105728,9 @@ 0.0 ], "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-02-12", "status": "deprecated" }, "MiniMaxAI/MiniMax-M2.7": { @@ -81111,6 +105741,9 @@ 0.0 ], "limit": 196608, + "max_output": 131072, + "open": true, + "released": "2026-03-18", "status": "deprecated" }, "MiniMaxAI/MiniMax-M3": { @@ -81120,7 +105753,10 @@ 0.06, 0.0 ], - "limit": 524288 + "limit": 524288, + "max_output": 524288, + "open": true, + "released": "2026-06-01" }, "Qwen/Qwen2.5-7B-Instruct-Turbo": { "cost": [ @@ -81130,6 +105766,9 @@ 0.0 ], "limit": 32768, + "max_output": 32768, + "open": true, + "released": "2024-09-19", "status": "deprecated" }, "Qwen/Qwen3-235B-A22B-Instruct-2507-tput": { @@ -81140,6 +105779,9 @@ 0.0 ], "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2025-07-21", "status": "deprecated" }, "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": { @@ -81149,7 +105791,11 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2025-07-22", "status": "deprecated" }, "Qwen/Qwen3-Coder-Next-FP8": { @@ -81159,7 +105805,11 @@ 0.0, 0.0 ], + "knowledge": "2025-09", "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-02-03", "status": "deprecated" }, "Qwen/Qwen3.5-397B-A17B": { @@ -81170,6 +105820,9 @@ 0.0 ], "limit": 262144, + "max_output": 130000, + "open": true, + "released": "2026-02-15", "status": "deprecated" }, "Qwen/Qwen3.5-9B": { @@ -81179,7 +105832,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-23" }, "Qwen/Qwen3.6-Plus": { "cost": [ @@ -81188,7 +105844,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-04", + "limit": 1000000, + "max_output": 65536, + "released": "2026-04-02" }, "Qwen/Qwen3.7-Max": { "cost": [ @@ -81197,7 +105856,9 @@ 0.5, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-05-21" }, "deepseek-ai/DeepSeek-R1": { "cost": [ @@ -81206,7 +105867,11 @@ 0.0, 0.0 ], + "knowledge": "2024-07", "limit": 163839, + "max_output": 163839, + "open": true, + "released": "2025-01-20", "status": "deprecated" }, "deepseek-ai/DeepSeek-V3": { @@ -81217,6 +105882,9 @@ 0.0 ], "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2024-12-26", "status": "deprecated" }, "deepseek-ai/DeepSeek-V3-1": { @@ -81227,6 +105895,9 @@ 0.0 ], "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2025-08-21", "status": "deprecated" }, "deepseek-ai/DeepSeek-V4-Flash-0731": { @@ -81236,7 +105907,11 @@ 0.03, 0.0 ], + "knowledge": "2025-05", "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-07-31", "status": "deprecated" }, "deepseek-ai/DeepSeek-V4-Pro-0813": { @@ -81246,7 +105921,10 @@ 0.13, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-08-13" }, "deepseek-ai/DeepSeek-V4.1-Flash": { "cost": [ @@ -81255,7 +105933,11 @@ 0.006, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-09-10" }, "essentialai/Rnj-1-Instruct": { "cost": [ @@ -81265,6 +105947,9 @@ 0.0 ], "limit": 32768, + "max_output": 32768, + "open": true, + "released": "2025-12-04", "status": "deprecated" }, "meta-llama/Llama-3.3-70B-Instruct-Turbo": { @@ -81274,7 +105959,11 @@ 0.0, 0.0 ], + "knowledge": "2023-12", "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2024-12-06", "status": "deprecated" }, "meta-models/Muse-Spark-Open-816B-A42B": { @@ -81284,7 +105973,11 @@ 0.15, 0.0 ], - "limit": 1048576 + "knowledge": "2026-01-04", + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-10-15" }, "moonshotai/Kimi-K3": { "cost": [ @@ -81293,7 +105986,10 @@ 0.3, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-16" }, "nvidia/NVIDIA-Nemotron-3.5-Super-VL": { "cost": [ @@ -81302,7 +105998,10 @@ 0.02, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-10-15" }, "nvidia/nemotron-3-ultra-550b-a55b": { "cost": [ @@ -81311,7 +106010,11 @@ 0.2, 0.0 ], + "knowledge": "2025-09", "limit": 512300, + "max_output": 512300, + "open": true, + "released": "2026-06-04", "status": "deprecated" }, "openai/gpt-oss-120b": { @@ -81321,7 +106024,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2025-08-05" }, "reflection/Beam-1.0-501B-A23B": { "cost": [ @@ -81330,7 +106037,11 @@ 0.04, 0.0 ], - "limit": 1048576 + "knowledge": "2026-06-30", + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-10-05" }, "thinkingmachines/Inkling": { "cost": [ @@ -81339,7 +106050,10 @@ 0.17, 0.0 ], - "limit": 524288 + "limit": 524288, + "max_output": 131072, + "open": true, + "released": "2026-07-15" }, "zai-org/GLM-5": { "cost": [ @@ -81349,6 +106063,9 @@ 0.0 ], "limit": 202752, + "max_output": 131072, + "open": true, + "released": "2026-02-12", "status": "deprecated" }, "zai-org/GLM-5.1": { @@ -81359,6 +106076,9 @@ 0.0 ], "limit": 202752, + "max_output": 131072, + "open": true, + "released": "2026-04-07", "status": "deprecated" }, "zai-org/GLM-5.2": { @@ -81368,7 +106088,10 @@ 0.26, 0.0 ], - "limit": 1048575 + "limit": 1048575, + "max_output": 164000, + "open": true, + "released": "2026-06-13" }, "zai-org/GLM-5.3": { "cost": [ @@ -81377,7 +106100,10 @@ 0.26, 0.0 ], - "limit": 1048575 + "limit": 1048575, + "max_output": 262144, + "open": true, + "released": "2026-08-14" }, "zai-org/GLM-5.3-Flash": { "cost": [ @@ -81386,7 +106112,10 @@ 0.03, 0.0 ], - "limit": 1048575 + "limit": 1048575, + "max_output": 400000, + "open": true, + "released": "2026-08-26" } }, "name": "Together AI" @@ -81400,7 +106129,10 @@ 0.06, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 8192, + "open": true, + "released": "2025-08-21" }, "deepseek/deepseek-v3.2": { "cost": [ @@ -81409,7 +106141,11 @@ 0.06, 0.0 ], - "limit": 128000 + "knowledge": "2024-07", + "limit": 128000, + "max_output": 64000, + "open": true, + "released": "2025-12-01" }, "deepseek/deepseek-v4-flash": { "cost": [ @@ -81418,7 +106154,11 @@ 0.028, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "deepseek/deepseek-v4-pro": { "cost": [ @@ -81427,7 +106167,11 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "minimax/minimax-m2.5": { "cost": [ @@ -81436,7 +106180,10 @@ 0.03, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-02-12" }, "moonshotai/kimi-k2.6": { "cost": [ @@ -81445,7 +106192,11 @@ 0.16, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-20" }, "moonshotai/kimi-k3": { "cost": [ @@ -81454,7 +106205,10 @@ 0.3, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-16" }, "qwen/qwen3.5-397b-a17b": { "cost": [ @@ -81463,7 +106217,10 @@ 0.2, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-15" }, "z-ai/glm-5": { "cost": [ @@ -81472,7 +106229,10 @@ 0.2226, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-02-12" }, "z-ai/glm-5.1": { "cost": [ @@ -81481,7 +106241,10 @@ 0.26, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 131072, + "open": true, + "released": "2026-04-07" }, "z-ai/glm-5.2": { "cost": [ @@ -81490,7 +106253,10 @@ 0.26, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "z-ai/glm-5.3": { "cost": [ @@ -81499,7 +106265,10 @@ 0.26, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "z-ai/glm-5.3-flash": { "cost": [ @@ -81508,7 +106277,10 @@ 0.03, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-26" } }, "name": "TokenGo" @@ -81522,7 +106294,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-14" } }, "name": "TokenRouter" @@ -81536,7 +106311,10 @@ 0.03, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131071, + "open": true, + "released": "2026-08-26" }, "umans-deepseek-v4-flash-0731": { "cost": [ @@ -81545,7 +106323,11 @@ 0.028, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 393215, + "open": true, + "released": "2026-07-31" }, "umans-deepseek-v4.1-flash": { "cost": [ @@ -81554,7 +106336,11 @@ 0.028, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 393215, + "open": true, + "released": "2026-10-17" }, "umans-deepseek-v4.1-flash-1017": { "cost": [ @@ -81563,7 +106349,11 @@ 0.028, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 393215, + "open": true, + "released": "2026-10-17" }, "umans-flash": { "cost": [ @@ -81572,7 +106362,10 @@ 0.05, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-04-17" }, "umans-glm-5.3": { "cost": [ @@ -81581,7 +106374,10 @@ 0.26, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131071, + "open": true, + "released": "2026-08-14" }, "umans-glm-5.3-flash": { "cost": [ @@ -81590,7 +106386,10 @@ 0.03, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131071, + "open": true, + "released": "2026-08-26" }, "umans-kimi-k3": { "cost": [ @@ -81599,7 +106398,10 @@ 0.3, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-16" } }, "name": "Umans AI" @@ -81613,7 +106415,10 @@ 0.0, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131071, + "open": true, + "released": "2026-08-26" }, "umans-deepseek-v4-flash-0731": { "cost": [ @@ -81622,7 +106427,11 @@ 0.0, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 393215, + "open": true, + "released": "2026-07-31" }, "umans-deepseek-v4.1-flash": { "cost": [ @@ -81631,7 +106440,11 @@ 0.0, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 393215, + "open": true, + "released": "2026-10-17" }, "umans-deepseek-v4.1-flash-1017": { "cost": [ @@ -81640,7 +106453,11 @@ 0.0, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 393215, + "open": true, + "released": "2026-10-17" }, "umans-flash": { "cost": [ @@ -81649,7 +106466,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-17" }, "umans-glm-5.3": { "cost": [ @@ -81658,7 +106478,10 @@ 0.0, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131071, + "open": true, + "released": "2026-08-14" }, "umans-glm-5.3-flash": { "cost": [ @@ -81667,7 +106490,10 @@ 0.0, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131071, + "open": true, + "released": "2026-08-26" }, "umans-kimi-k3": { "cost": [ @@ -81676,7 +106502,10 @@ 0.0, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-16" }, "umans-qwen3.6-35b-a3b": { "cost": [ @@ -81685,7 +106514,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-17" } }, "name": "Umans AI Coding Plan" @@ -81699,7 +106531,10 @@ 0.0, 0.0 ], - "limit": 200000 + "knowledge": "2025-02-28", + "limit": 200000, + "max_output": 64000, + "released": "2025-10-15" }, "claude-opus-4-8": { "cost": [ @@ -81708,7 +106543,10 @@ 0.0, 0.0 ], + "knowledge": "2026-01", "limit": 1000000, + "max_output": 128000, + "released": "2026-05-28", "status": "deprecated" }, "claude-sonnet-5": { @@ -81718,7 +106556,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-30" }, "deepseek-v4-flash": { "cost": [ @@ -81727,7 +106568,11 @@ 0.0, 0.0 ], + "knowledge": "2025-05", "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24", "status": "deprecated" }, "deepseek-v4-flash:free": { @@ -81737,7 +106582,11 @@ 0.0, 0.0 ], + "knowledge": "2025-05", "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24", "status": "deprecated" }, "deepseek-v4-pro": { @@ -81747,7 +106596,11 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "deepseek-v4-pro:free": { "cost": [ @@ -81756,7 +106609,11 @@ 0.0, 0.0 ], + "knowledge": "2025-05", "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24", "status": "deprecated" }, "gemini-3.5-flash": { @@ -81766,7 +106623,10 @@ 0.0, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-05-19" }, "gemma-4-31b-it:free": { "cost": [ @@ -81775,7 +106635,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-04-02" }, "glm-4.5-flash:free": { "cost": [ @@ -81784,7 +106648,10 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2025-04", + "limit": 131072, + "max_output": 98304, + "released": "2025-07-28" }, "glm-5.2": { "cost": [ @@ -81794,6 +106661,9 @@ 0.0 ], "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-13", "status": "deprecated" }, "glm-5.2:free": { @@ -81804,6 +106674,9 @@ 0.0 ], "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-13", "status": "deprecated" }, "gpt-5.2": { @@ -81813,7 +106686,10 @@ 0.0, 0.0 ], + "knowledge": "2025-08-31", "limit": 400000, + "max_output": 128000, + "released": "2025-12-11", "status": "deprecated" }, "gpt-5.4": { @@ -81823,7 +106699,10 @@ 0.0, 0.0 ], + "knowledge": "2025-08-31", "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05", "status": "deprecated" }, "gpt-5.4:free": { @@ -81833,7 +106712,10 @@ 0.0, 0.0 ], + "knowledge": "2025-08-31", "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05", "status": "deprecated" }, "gpt-5.5": { @@ -81843,7 +106725,10 @@ 0.0, 0.0 ], - "limit": 1050000 + "knowledge": "2025-12-01", + "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23" }, "gpt-5.5:free": { "cost": [ @@ -81852,7 +106737,10 @@ 0.0, 0.0 ], + "knowledge": "2025-12-01", "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23", "status": "deprecated" }, "kimi-k2.6": { @@ -81862,7 +106750,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-20" }, "minimax-m2.7": { "cost": [ @@ -81872,6 +106764,9 @@ 0.0 ], "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-03-18", "status": "deprecated" }, "minimax-m2.7:free": { @@ -81881,7 +106776,10 @@ 0.0, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-03-18" }, "nemotron-3-ultra-550b-a55b:free": { "cost": [ @@ -81890,7 +106788,11 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-09", + "limit": 1000000, + "max_output": 128000, + "open": true, + "released": "2026-06-04" }, "qwen3.5-397b-a17b:free": { "cost": [ @@ -81900,6 +106802,9 @@ 0.0 ], "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-02-15", "status": "deprecated" }, "step-3.7-flash:free": { @@ -81909,7 +106814,11 @@ 0.0, 0.0 ], + "knowledge": "2026-03-01", "limit": 256000, + "max_output": 256000, + "open": true, + "released": "2026-05-29", "status": "deprecated" } }, @@ -81924,7 +106833,10 @@ 0.0, 0.0 ], - "limit": 32768 + "knowledge": "2024-09", + "limit": 32768, + "max_output": 4096, + "released": "2024-06-12" }, "solar-mini4": { "cost": [ @@ -81933,7 +106845,10 @@ 0.01, 0.0 ], - "limit": 524288 + "knowledge": "2026-02", + "limit": 524288, + "max_output": 131072, + "released": "2026-09-22" }, "solar-pro2": { "cost": [ @@ -81942,7 +106857,10 @@ 0.0, 0.0 ], - "limit": 65536 + "knowledge": "2025-03", + "limit": 65536, + "max_output": 8192, + "released": "2025-05-20" }, "solar-pro3": { "cost": [ @@ -81951,7 +106869,10 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2025-03", + "limit": 131072, + "max_output": 8192, + "released": "2026-01-26" }, "solar-pro4": { "cost": [ @@ -81960,7 +106881,10 @@ 0.06, 0.0 ], - "limit": 524288 + "knowledge": "2026-02", + "limit": 524288, + "max_output": 131072, + "released": "2026-08-06" } }, "name": "Upstage" @@ -81975,6 +106899,9 @@ 0.0 ], "limit": 1048576, + "max_output": 512000, + "open": true, + "released": "2026-06-01", "status": "deprecated" }, "deepseek-v4.1-flash": { @@ -81984,7 +106911,11 @@ 0.0048, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-09-10" }, "glm-5.3": { "cost": [ @@ -81993,7 +106924,10 @@ 0.208, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "glm-5.3-flash": { "cost": [ @@ -82002,7 +106936,10 @@ 0.024, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-26" }, "hy4-preview": { "cost": [ @@ -82011,7 +106948,10 @@ 0.034, 0.0 ], - "limit": 1024000 + "limit": 1024000, + "max_output": 64000, + "open": true, + "released": "2026-08-28" }, "kimi-k3": { "cost": [ @@ -82020,7 +106960,10 @@ 0.24, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-16" }, "qwen3.8-flash": { "cost": [ @@ -82029,7 +106972,9 @@ 0.013, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-08-26" }, "qwen3.8-max": { "cost": [ @@ -82038,13 +106983,26 @@ 0.2, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-08-03" } }, "name": "Vancine" }, "venice": { "models": { + "abliteration-abliterated-model-large-flash": { + "cost": [ + 1.25, + 2.5, + 0.125, + 0.0 + ], + "limit": 1000000, + "max_output": 131072, + "released": "2026-10-23" + }, "abliteration-abliterated-model-large-v2": { "cost": [ 3.0, @@ -82052,7 +107010,9 @@ 0.3, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 32768, + "released": "2026-10-01" }, "aion-labs-aion-3-0": { "cost": [ @@ -82061,7 +107021,9 @@ 0.9375, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 32768, + "released": "2026-05-05" }, "aion-labs-aion-3-0-mini": { "cost": [ @@ -82070,7 +107032,9 @@ 0.225, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 32768, + "released": "2026-05-14" }, "aion-labs-aion-3-5": { "cost": [ @@ -82079,7 +107043,9 @@ 0.9375, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "released": "2026-09-23" }, "aion-labs-aion-3-5-mini": { "cost": [ @@ -82088,7 +107054,9 @@ 0.225, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "released": "2026-09-23" }, "claude-fable-5": { "cost": [ @@ -82097,7 +107065,10 @@ 1.0, 12.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-09" }, "claude-fable-5-1": { "cost": [ @@ -82106,7 +107077,10 @@ 0.25, 12.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-01" }, "claude-haiku-5-5": { "cost": [ @@ -82115,7 +107089,10 @@ 0.01, 0.125 ], + "knowledge": "2026-06", "limit": 1000000, + "max_output": 128000, + "released": "2026-10-07", "tiers": [ { "cost": [ @@ -82138,7 +107115,10 @@ 0.5, 6.25 ], - "limit": 198000 + "knowledge": "2025-05", + "limit": 198000, + "max_output": 32768, + "released": "2025-11-24" }, "claude-opus-4-6": { "cost": [ @@ -82147,7 +107127,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2025-05-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-05" }, "claude-opus-4-7": { "cost": [ @@ -82156,7 +107139,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-16" }, "claude-opus-4-8": { "cost": [ @@ -82165,7 +107151,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-28" }, "claude-opus-4-8-fast": { "cost": [ @@ -82174,7 +107163,10 @@ 1.0, 12.5 ], - "limit": 1000000 + "knowledge": "2026-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-28" }, "claude-opus-5": { "cost": [ @@ -82183,7 +107175,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-05", + "limit": 1000000, + "max_output": 128000, + "released": "2026-07-24" }, "claude-opus-5-5": { "cost": [ @@ -82192,7 +107187,10 @@ 0.2, 5.0 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-22" }, "claude-opus-5-5-fast": { "cost": [ @@ -82201,7 +107199,10 @@ 0.4, 10.0 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-22" }, "claude-opus-5-fast": { "cost": [ @@ -82210,7 +107211,10 @@ 1.0, 12.5 ], - "limit": 1000000 + "knowledge": "2026-05", + "limit": 1000000, + "max_output": 128000, + "released": "2026-07-24" }, "claude-sonnet-4-5": { "cost": [ @@ -82219,7 +107223,10 @@ 0.3, 3.75 ], + "knowledge": "2025-07-31", "limit": 198000, + "max_output": 64000, + "released": "2025-09-29", "status": "deprecated" }, "claude-sonnet-4-6": { @@ -82229,7 +107236,10 @@ 0.3, 3.75 ], - "limit": 1000000 + "knowledge": "2025-08-31", + "limit": 1000000, + "max_output": 64000, + "released": "2026-02-17" }, "claude-sonnet-5": { "cost": [ @@ -82238,7 +107248,10 @@ 0.2, 2.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 64000, + "released": "2026-06-30" }, "claude-sonnet-5-5": { "cost": [ @@ -82247,7 +107260,10 @@ 0.1, 2.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-28" }, "deepseek-v3.2": { "cost": [ @@ -82256,7 +107272,11 @@ 0.16, 0.0 ], + "knowledge": "2024-07", "limit": 160000, + "max_output": 32768, + "open": true, + "released": "2025-12-01", "status": "deprecated" }, "deepseek-v4-1-flash": { @@ -82266,7 +107286,11 @@ 0.0075, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-09-10" }, "deepseek-v4-1-flash-1017": { "cost": [ @@ -82275,7 +107299,35 @@ 0.0075, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-10-17" + }, + "deepseek-v4-1-flash-1017-uncensored": { + "cost": [ + 0.33, + 1.32, + 0.00825, + 0.0 + ], + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-10-27" + }, + "deepseek-v4-1-flash-uncensored": { + "cost": [ + 0.33, + 1.32, + 0.00825, + 0.0 + ], + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-10-23" }, "deepseek-v4-flash": { "cost": [ @@ -82284,7 +107336,11 @@ 0.028, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 32768, + "open": true, + "released": "2026-04-24" }, "deepseek-v4-flash-0731": { "cost": [ @@ -82293,7 +107349,11 @@ 0.028, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 32768, + "open": true, + "released": "2026-07-31" }, "deepseek-v4-flash-0731-fast": { "cost": [ @@ -82302,7 +107362,11 @@ 0.0875, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 32768, + "open": true, + "released": "2026-07-31" }, "deepseek-v4-pro": { "cost": [ @@ -82311,7 +107375,11 @@ 0.33, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 32768, + "open": true, + "released": "2026-04-24" }, "deepseek-v4-pro-0813": { "cost": [ @@ -82320,7 +107388,10 @@ 0.165, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 32768, + "open": true, + "released": "2026-08-13" }, "gemini-3-1-pro-preview": { "cost": [ @@ -82329,7 +107400,10 @@ 0.5, 0.5 ], + "knowledge": "2025-01", "limit": 1000000, + "max_output": 32768, + "released": "2026-02-19", "tiers": [ { "cost": [ @@ -82352,7 +107426,10 @@ 0.155, 0.086 ], - "limit": 1000000 + "knowledge": "2025-01", + "limit": 1000000, + "max_output": 65536, + "released": "2026-05-19" }, "gemini-3-5-flash-lite": { "cost": [ @@ -82361,7 +107438,10 @@ 0.0375, 0.0 ], - "limit": 1000000 + "knowledge": "2026-03", + "limit": 1000000, + "max_output": 65536, + "released": "2026-07-21" }, "gemini-3-6-flash": { "cost": [ @@ -82370,7 +107450,10 @@ 0.09375, 0.0 ], - "limit": 1000000 + "knowledge": "2026-03", + "limit": 1000000, + "max_output": 65536, + "released": "2026-07-21" }, "gemini-3-7-flash": { "cost": [ @@ -82379,7 +107462,10 @@ 0.09375, 0.0 ], - "limit": 1000000 + "knowledge": "2026-03", + "limit": 1000000, + "max_output": 65536, + "released": "2026-08-13" }, "gemini-3-8-flash": { "cost": [ @@ -82388,7 +107474,9 @@ 0.09375, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 65536, + "released": "2026-09-02" }, "gemini-3-flash-preview": { "cost": [ @@ -82397,7 +107485,10 @@ 0.07, 0.0 ], - "limit": 256000 + "knowledge": "2025-01", + "limit": 256000, + "max_output": 65536, + "released": "2025-12-17" }, "gemini-4-argon": { "cost": [ @@ -82406,7 +107497,10 @@ 0.125, 0.0 ], - "limit": 1000000 + "knowledge": "2026-03", + "limit": 1000000, + "max_output": 65536, + "released": "2026-10-13" }, "gemma-4-uncensored": { "cost": [ @@ -82415,7 +107509,10 @@ 0.0, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 8192, + "open": true, + "released": "2026-04-13" }, "google-gemma-3-27b-it": { "cost": [ @@ -82424,7 +107521,11 @@ 0.0, 0.0 ], - "limit": 198000 + "knowledge": "2024-08", + "limit": 198000, + "max_output": 16384, + "open": true, + "released": "2025-03-12" }, "google-gemma-4-26b-a4b-it": { "cost": [ @@ -82433,7 +107534,10 @@ 0.05, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 8192, + "open": true, + "released": "2026-04-02" }, "google-gemma-4-31b-it": { "cost": [ @@ -82442,7 +107546,11 @@ 0.09, 0.0 ], - "limit": 256000 + "knowledge": "2025-01", + "limit": 256000, + "max_output": 8192, + "open": true, + "released": "2026-04-02" }, "grok-4-20": { "cost": [ @@ -82452,6 +107560,8 @@ 0.0 ], "limit": 2000000, + "max_output": 128000, + "released": "2026-03-12", "tiers": [ { "cost": [ @@ -82475,6 +107585,8 @@ 0.0 ], "limit": 2000000, + "max_output": 128000, + "released": "2026-03-12", "tiers": [ { "cost": [ @@ -82498,6 +107610,8 @@ 0.0 ], "limit": 1000000, + "max_output": 32000, + "released": "2026-04-17", "tiers": [ { "cost": [ @@ -82521,6 +107635,8 @@ 0.0 ], "limit": 500000, + "max_output": 32000, + "released": "2026-07-08", "tiers": [ { "cost": [ @@ -82543,7 +107659,10 @@ 0.57, 0.0 ], + "knowledge": "2026-02-01", "limit": 500000, + "max_output": 200000, + "released": "2026-08-12", "tiers": [ { "cost": [ @@ -82566,7 +107685,10 @@ 0.57, 0.0 ], + "knowledge": "2026-05", "limit": 500000, + "max_output": 200000, + "released": "2026-09-21", "tiers": [ { "cost": [ @@ -82590,6 +107712,8 @@ 0.0 ], "limit": 256000, + "max_output": 65536, + "released": "2026-04-16", "tiers": [ { "cost": [ @@ -82612,7 +107736,12 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2023-12-31", + "limit": 128000, + "max_output": 16384, + "open": true, + "released": "2024-08-16", + "status": "deprecated" }, "hy4-preview": { "cost": [ @@ -82621,7 +107750,10 @@ 0.0525, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 64000, + "open": true, + "released": "2026-08-28" }, "inkling": { "cost": [ @@ -82631,6 +107763,9 @@ 0.0 ], "limit": 524288, + "max_output": 65536, + "open": true, + "released": "2026-07-15", "status": "deprecated" }, "kimi-k2-5": { @@ -82640,7 +107775,11 @@ 0.22, 0.0 ], - "limit": 256000 + "knowledge": "2025-01", + "limit": 256000, + "max_output": 65536, + "open": true, + "released": "2026-01-27" }, "kimi-k2-6": { "cost": [ @@ -82649,7 +107788,11 @@ 0.16, 0.0 ], - "limit": 256000 + "knowledge": "2025-01", + "limit": 256000, + "max_output": 65536, + "open": true, + "released": "2026-04-20" }, "kimi-k2-7-code": { "cost": [ @@ -82658,7 +107801,11 @@ 0.16, 0.0 ], - "limit": 256000 + "knowledge": "2025-01", + "limit": 256000, + "max_output": 65536, + "open": true, + "released": "2026-06-12" }, "kimi-k3": { "cost": [ @@ -82667,7 +107814,32 @@ 0.375, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-07-16" + }, + "kimi-k3-1-pro": { + "cost": [ + 3.0, + 15.0, + 0.30000000000000004, + 0.0 + ], + "limit": 1000000, + "max_output": 131072, + "released": "2026-10-23" + }, + "kimi-k3-1-pro-highspeed": { + "cost": [ + 6.0, + 30.0, + 0.6000000000000001, + 0.0 + ], + "limit": 1000000, + "max_output": 131072, + "released": "2026-10-23" }, "kimi-k3-fast-api": { "cost": [ @@ -82676,7 +107848,10 @@ 0.45, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-07-16" }, "llama-3.2-3b": { "cost": [ @@ -82685,7 +107860,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2023-12", + "limit": 128000, + "max_output": 4096, + "open": true, + "released": "2024-09-25" }, "llama-3.3-70b": { "cost": [ @@ -82694,7 +107873,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2023-12", + "limit": 128000, + "max_output": 4096, + "open": true, + "released": "2024-12-06" }, "mercury-2": { "cost": [ @@ -82703,7 +107886,9 @@ 0.03125, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 50000, + "released": "2026-02-24" }, "mercury-2-5": { "cost": [ @@ -82712,7 +107897,9 @@ 0.025, 0.0 ], - "limit": 260000 + "limit": 260000, + "max_output": 65536, + "released": "2026-09-08" }, "mercury-3": { "cost": [ @@ -82721,7 +107908,9 @@ 0.01, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-10-16" }, "minimax-m25": { "cost": [ @@ -82730,7 +107919,10 @@ 0.03, 0.0 ], - "limit": 198000 + "limit": 198000, + "max_output": 32768, + "open": true, + "released": "2026-02-12" }, "minimax-m27": { "cost": [ @@ -82739,7 +107931,10 @@ 0.06875, 0.0 ], - "limit": 198000 + "limit": 198000, + "max_output": 32768, + "open": true, + "released": "2026-03-18" }, "minimax-m3-1-flash": { "cost": [ @@ -82748,7 +107943,9 @@ 0.01875, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-10-19" }, "minimax-m3-preview": { "cost": [ @@ -82757,7 +107954,10 @@ 0.06, 0.0 ], - "limit": 524288 + "limit": 524288, + "max_output": 65536, + "open": true, + "released": "2026-06-12" }, "mistral-small-3-2-24b-instruct": { "cost": [ @@ -82766,7 +107966,11 @@ 0.0, 0.0 ], - "limit": 256000 + "knowledge": "2023-10-31", + "limit": 256000, + "max_output": 16384, + "open": true, + "released": "2025-06-20" }, "muse-spark-open": { "cost": [ @@ -82775,7 +107979,11 @@ 0.1875, 0.0 ], - "limit": 1048576 + "knowledge": "2026-01-04", + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-10-15" }, "muse-wonder": { "cost": [ @@ -82784,16 +107992,21 @@ 0.25, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-10-12" }, "nvidia-nemotron-3-5-super-vl-120b-a12b": { "cost": [ - 0.25, - 1.25, - 0.125, + 0.2, + 0.5, + 0.04, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-10-15" }, "nvidia-nemotron-3-nano-30b-a3b": { "cost": [ @@ -82802,7 +108015,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2025-06-25", + "limit": 128000, + "max_output": 16384, + "open": true, + "released": "2025-12-15" }, "nvidia-nemotron-3-ultra-550b-a55b": { "cost": [ @@ -82811,7 +108028,11 @@ 0.1875, 0.0 ], - "limit": 256000 + "knowledge": "2025-09", + "limit": 256000, + "max_output": 32768, + "open": true, + "released": "2026-06-04" }, "olafangensan-glm-4.7-flash-heretic": { "cost": [ @@ -82820,7 +108041,10 @@ 0.035, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 24000, + "open": true, + "released": "2026-02-04" }, "openai-gpt-4o-2024-11-20": { "cost": [ @@ -82829,7 +108053,10 @@ 1.25, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-11-20" }, "openai-gpt-4o-mini-2024-07-18": { "cost": [ @@ -82838,7 +108065,10 @@ 0.075, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-07-18" }, "openai-gpt-52": { "cost": [ @@ -82847,7 +108077,10 @@ 0.175, 0.0 ], - "limit": 256000 + "knowledge": "2025-08-31", + "limit": 256000, + "max_output": 65536, + "released": "2025-12-11" }, "openai-gpt-53-codex": { "cost": [ @@ -82856,7 +108089,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-02-05" }, "openai-gpt-54": { "cost": [ @@ -82865,7 +108101,10 @@ 0.25, 0.0 ], + "knowledge": "2025-08-31", "limit": 1000000, + "max_output": 131072, + "released": "2026-03-05", "tiers": [ { "cost": [ @@ -82888,7 +108127,10 @@ 0.075, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "openai-gpt-54-pro": { "cost": [ @@ -82897,7 +108139,10 @@ 0.0, 0.0 ], + "knowledge": "2025-08-31", "limit": 1000000, + "max_output": 128000, + "released": "2026-03-05", "tiers": [ { "cost": [ @@ -82920,7 +108165,10 @@ 0.5, 0.0 ], + "knowledge": "2025-12-01", "limit": 1000000, + "max_output": 131072, + "released": "2026-04-23", "tiers": [ { "cost": [ @@ -82943,7 +108191,10 @@ 0.0, 0.0 ], + "knowledge": "2025-12-01", "limit": 1000000, + "max_output": 128000, + "released": "2026-04-23", "tiers": [ { "cost": [ @@ -82966,7 +108217,10 @@ 0.02, 0.25 ], + "knowledge": "2026-02-16", "limit": 1000000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -82989,7 +108243,10 @@ 0.02, 0.25 ], + "knowledge": "2026-02-16", "limit": 1000000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -83012,7 +108269,10 @@ 0.4, 5.0 ], + "knowledge": "2026-02-16", "limit": 1000000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -83035,7 +108295,10 @@ 0.4, 5.0 ], + "knowledge": "2026-02-16", "limit": 1000000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -83058,7 +108321,10 @@ 0.2, 2.5 ], + "knowledge": "2026-02-16", "limit": 1000000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -83081,7 +108347,10 @@ 0.2, 2.5 ], + "knowledge": "2026-02-16", "limit": 1000000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -83104,7 +108373,10 @@ 1.0, 12.5 ], + "knowledge": "2026-04-30", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-04", "tiers": [ { "cost": [ @@ -83127,7 +108399,10 @@ 1.0, 12.5 ], + "knowledge": "2026-04-30", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-04", "tiers": [ { "cost": [ @@ -83150,7 +108425,10 @@ 0.01, 0.125 ], + "knowledge": "2026-05-18", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -83173,7 +108451,10 @@ 0.2, 2.5 ], + "knowledge": "2026-04-20", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -83196,7 +108477,10 @@ 0.1, 2.5 ], + "knowledge": "2026-04-30", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-29", "tiers": [ { "cost": [ @@ -83219,7 +108503,10 @@ 0.6, 15.0 ], + "knowledge": "2026-04-30", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-29", "tiers": [ { "cost": [ @@ -83235,6 +108522,32 @@ } ] }, + "openai-gpt-61-terra": { + "cost": [ + 1.0, + 5.0, + 0.05, + 1.25 + ], + "knowledge": "2026-06-01", + "limit": 1050000, + "max_output": 128000, + "released": "2026-10-26", + "tiers": [ + { + "cost": [ + 2.0, + 7.5, + 0.1, + 2.5 + ], + "tier": { + "size": 272000, + "type": "context" + } + } + ] + }, "openai-gpt-oss-120b": { "cost": [ 0.07, @@ -83242,7 +108555,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-06", + "limit": 128000, + "max_output": 16384, + "open": true, + "released": "2025-08-05" }, "qwen-3-6-plus": { "cost": [ @@ -83251,7 +108568,10 @@ 0.0625, 0.78 ], + "knowledge": "2025-04", "limit": 1000000, + "max_output": 65536, + "released": "2026-04-02", "tiers": [ { "cost": [ @@ -83274,7 +108594,9 @@ 0.27, 3.35 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 65536, + "released": "2026-05-21" }, "qwen-3-7-plus": { "cost": [ @@ -83283,7 +108605,10 @@ 0.05, 0.625 ], + "knowledge": "2025-04", "limit": 1000000, + "max_output": 65536, + "released": "2026-06-02", "tiers": [ { "cost": [ @@ -83306,7 +108631,10 @@ 0.3125, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-08-12" }, "qwen-3-8-27b": { "cost": [ @@ -83315,7 +108643,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-08-14" }, "qwen-3-8-flash": { "cost": [ @@ -83324,7 +108655,9 @@ 0.014, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-08-26" }, "qwen-3-8-max": { "cost": [ @@ -83333,7 +108666,9 @@ 0.3125, 3.125 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-07-19" }, "qwen3-235b-a22b-instruct-2507": { "cost": [ @@ -83342,7 +108677,10 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 16384, + "open": true, + "released": "2025-07-21" }, "qwen3-235b-a22b-thinking-2507": { "cost": [ @@ -83351,7 +108689,10 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 16384, + "open": true, + "released": "2025-07-25" }, "qwen3-5-35b-a3b": { "cost": [ @@ -83360,7 +108701,10 @@ 0.05, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 16384, + "open": true, + "released": "2026-02-23" }, "qwen3-5-397b-a17b": { "cost": [ @@ -83369,7 +108713,10 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 32768, + "open": true, + "released": "2026-02-15" }, "qwen3-6-27b": { "cost": [ @@ -83378,7 +108725,10 @@ 0.0, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 65536, + "open": true, + "released": "2026-04-22" }, "qwen3-6-35b-a3b": { "cost": [ @@ -83387,7 +108737,10 @@ 0.0, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 65536, + "open": true, + "released": "2026-04-17" }, "qwen3-coder-480b-a35b-instruct-turbo": { "cost": [ @@ -83396,7 +108749,10 @@ 0.04, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 65536, + "open": true, + "released": "2026-01-27" }, "qwen3-next-80b": { "cost": [ @@ -83405,7 +108761,11 @@ 0.0, 0.0 ], - "limit": 256000 + "knowledge": "2025-04", + "limit": 256000, + "max_output": 16384, + "open": true, + "released": "2025-09" }, "qwen3-vl-235b-a22b": { "cost": [ @@ -83414,7 +108774,10 @@ 0.1, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 16384, + "open": true, + "released": "2026-01-16" }, "seed-2-1-turbo": { "cost": [ @@ -83423,7 +108786,9 @@ 0.125, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 65536, + "released": "2026-06-23" }, "venice-uncensored-1-2": { "cost": [ @@ -83432,7 +108797,10 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 8192, + "open": true, + "released": "2026-04-01" }, "venice-uncensored-role-play": { "cost": [ @@ -83441,7 +108809,10 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 4096, + "open": true, + "released": "2026-02-20" }, "xiaomi-mimo-v2-5": { "cost": [ @@ -83450,7 +108821,11 @@ 0.08, 0.0 ], - "limit": 1000000 + "knowledge": "2024-12", + "limit": 1000000, + "max_output": 65536, + "open": true, + "released": "2026-04-22" }, "xiaomi-mimo-v2-6-flash": { "cost": [ @@ -83459,7 +108834,10 @@ 0.00375, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-09-22" }, "z-ai-glm-5-3": { "cost": [ @@ -83468,7 +108846,10 @@ 0.325, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "z-ai-glm-5-3-flash": { "cost": [ @@ -83477,7 +108858,10 @@ 0.03, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-08-26" }, "z-ai-glm-5-turbo": { "cost": [ @@ -83486,7 +108870,9 @@ 0.24, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 32768, + "released": "2026-03-16" }, "z-ai-glm-5v-turbo": { "cost": [ @@ -83495,7 +108881,9 @@ 0.3, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 32768, + "released": "2026-04-01" }, "zai-org-glm-4.6": { "cost": [ @@ -83504,7 +108892,11 @@ 0.08, 0.0 ], - "limit": 198000 + "knowledge": "2025-04", + "limit": 198000, + "max_output": 16384, + "open": true, + "released": "2025-09-30" }, "zai-org-glm-4.7": { "cost": [ @@ -83513,7 +108905,11 @@ 0.11, 0.0 ], - "limit": 198000 + "knowledge": "2025-04", + "limit": 198000, + "max_output": 16384, + "open": true, + "released": "2025-12-22" }, "zai-org-glm-5": { "cost": [ @@ -83522,7 +108918,10 @@ 0.2, 0.0 ], - "limit": 198000 + "limit": 198000, + "max_output": 32000, + "open": true, + "released": "2026-02-12" }, "zai-org-glm-5-1": { "cost": [ @@ -83531,7 +108930,10 @@ 0.286, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 80000, + "open": true, + "released": "2026-04-07" }, "zai-org-glm-5-2": { "cost": [ @@ -83540,7 +108942,10 @@ 0.26, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-13" } }, "name": "Venice AI" @@ -83554,7 +108959,10 @@ 0.0, 0.0 ], - "limit": 40960 + "knowledge": "2025-04", + "limit": 40960, + "max_output": 16384, + "released": "2025-04-28" }, "alibaba/qwen-3-235b": { "cost": [ @@ -83563,7 +108971,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 16384, + "open": true, + "released": "2025-07-21" }, "alibaba/qwen-3-30b": { "cost": [ @@ -83572,7 +108983,10 @@ 0.0, 0.0 ], - "limit": 40960 + "limit": 40960, + "max_output": 16384, + "open": true, + "released": "2025-04-28" }, "alibaba/qwen-3-32b": { "cost": [ @@ -83581,7 +108995,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2025-04", + "limit": 128000, + "max_output": 8192, + "open": true, + "released": "2025-04-28" }, "alibaba/qwen3-coder": { "cost": [ @@ -83590,7 +109008,11 @@ 0.022, 0.0 ], + "knowledge": "2025-04", "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2025-07-22", "tiers": [ { "cost": [ @@ -83625,7 +109047,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-04", + "limit": 262144, + "max_output": 8192, + "open": true, + "released": "2025-07-31" }, "alibaba/qwen3-coder-next": { "cost": [ @@ -83634,7 +109060,11 @@ 0.0, 0.0 ], - "limit": 256000 + "knowledge": "2025-09", + "limit": 256000, + "max_output": 256000, + "open": true, + "released": "2026-02-03" }, "alibaba/qwen3-max-thinking": { "cost": [ @@ -83643,7 +109073,11 @@ 0.24, 0.0 ], + "knowledge": "2025-01", "limit": 256000, + "max_output": 65536, + "open": true, + "released": "2026-01-23", "tiers": [ { "cost": [ @@ -83678,7 +109112,11 @@ 0.0, 0.0 ], - "limit": 262114 + "knowledge": "2025-04", + "limit": 262114, + "max_output": 262114, + "open": true, + "released": "2025-09" }, "alibaba/qwen3-next-80b-a3b-thinking": { "cost": [ @@ -83687,7 +109125,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-04", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2025-09" }, "alibaba/qwen3-vl-instruct": { "cost": [ @@ -83696,7 +109138,11 @@ 0.11, 0.0 ], - "limit": 262144 + "knowledge": "2025-04", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2025-09-23" }, "alibaba/qwen3.5-flash": { "cost": [ @@ -83705,7 +109151,9 @@ 0.01, 0.125 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 64000, + "released": "2026-02-23" }, "alibaba/qwen3.5-plus": { "cost": [ @@ -83714,7 +109162,10 @@ 0.04, 0.5 ], + "knowledge": "2025-04", "limit": 1000000, + "max_output": 64000, + "released": "2026-02-16", "tiers": [ { "cost": [ @@ -83737,7 +109188,10 @@ 0.0, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 65536, + "open": true, + "released": "2026-04-22" }, "alibaba/qwen3.6-plus": { "cost": [ @@ -83746,7 +109200,10 @@ 0.05, 0.625 ], + "knowledge": "2025-04", "limit": 1000000, + "max_output": 64000, + "released": "2026-04-02", "tiers": [ { "cost": [ @@ -83770,6 +109227,8 @@ 0.038 ], "limit": 991000, + "max_output": 64000, + "released": "2026-07-15", "tiers": [ { "cost": [ @@ -83804,7 +109263,9 @@ 0.5, 3.125 ], - "limit": 991000 + "limit": 991000, + "max_output": 64000, + "released": "2026-05-21" }, "alibaba/qwen3.7-plus": { "cost": [ @@ -83813,7 +109274,10 @@ 0.08, 0.5 ], + "knowledge": "2025-04", "limit": 1000000, + "max_output": 64000, + "released": "2026-06-02", "tiers": [ { "cost": [ @@ -83836,7 +109300,10 @@ 0.25, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 128000, + "open": true, + "released": "2026-08-12" }, "alibaba/qwen3.8-27b": { "cost": [ @@ -83845,7 +109312,10 @@ 0.1, 0.625 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "alibaba/qwen3.8-flash": { "cost": [ @@ -83854,7 +109324,9 @@ 0.016, 0.2 ], - "limit": 991000 + "limit": 991000, + "max_output": 128000, + "released": "2026-08-26" }, "alibaba/qwen3.8-max": { "cost": [ @@ -83863,7 +109335,9 @@ 0.25, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 128000, + "released": "2026-07-19" }, "alibaba/qwen3.8-max-0902": { "cost": [ @@ -83872,7 +109346,9 @@ 0.25, 2.5 ], - "limit": 991000 + "limit": 991000, + "max_output": 128000, + "released": "2026-09-02" }, "alibaba/qwen3.8-max-prime": { "cost": [ @@ -83881,7 +109357,9 @@ 0.5, 5.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-09-23" }, "alibaba/qwen3.8-omni-flash": { "cost": [ @@ -83890,7 +109368,9 @@ 0.016, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-09-17" }, "amazon/nova-2-lite": { "cost": [ @@ -83899,7 +109379,10 @@ 0.0825, 0.0 ], - "limit": 1000000 + "knowledge": "2025-10", + "limit": 1000000, + "max_output": 65535, + "released": "2025-12-02" }, "amazon/nova-lite": { "cost": [ @@ -83908,7 +109391,10 @@ 0.015, 0.06 ], - "limit": 300000 + "knowledge": "2024-10", + "limit": 300000, + "max_output": 10000, + "released": "2024-12-03" }, "amazon/nova-micro": { "cost": [ @@ -83917,7 +109403,10 @@ 0.00875, 0.035 ], - "limit": 128000 + "knowledge": "2024-10", + "limit": 128000, + "max_output": 10000, + "released": "2024-12-03" }, "amazon/nova-pro": { "cost": [ @@ -83926,7 +109415,10 @@ 0.2, 0.8 ], - "limit": 300000 + "knowledge": "2024-10", + "limit": 300000, + "max_output": 10000, + "released": "2024-12-03" }, "anthropic/claude-fable-5": { "cost": [ @@ -83935,7 +109427,10 @@ 1.0, 12.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-09" }, "anthropic/claude-fable-5.1": { "cost": [ @@ -83944,7 +109439,10 @@ 0.25, 12.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-01" }, "anthropic/claude-haiku-4.5": { "cost": [ @@ -83953,7 +109451,10 @@ 0.1, 1.25 ], - "limit": 200000 + "knowledge": "2025-02-28", + "limit": 200000, + "max_output": 64000, + "released": "2025-10-15" }, "anthropic/claude-haiku-5.5": { "cost": [ @@ -83962,7 +109463,10 @@ 0.01, 0.125 ], + "knowledge": "2026-06", "limit": 1000000, + "max_output": 128000, + "released": "2026-10-07", "tiers": [ { "cost": [ @@ -83985,7 +109489,10 @@ 0.5, 6.25 ], - "limit": 200000 + "knowledge": "2025-05", + "limit": 200000, + "max_output": 64000, + "released": "2025-11-24" }, "anthropic/claude-opus-4.6": { "cost": [ @@ -83994,7 +109501,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2025-05-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-05" }, "anthropic/claude-opus-4.7": { "cost": [ @@ -84003,7 +109513,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-16" }, "anthropic/claude-opus-4.8": { "cost": [ @@ -84012,7 +109525,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-28" }, "anthropic/claude-opus-4.8-fast": { "cost": [ @@ -84021,7 +109537,10 @@ 1.0, 12.5 ], - "limit": 1000000 + "knowledge": "2026-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-28" }, "anthropic/claude-opus-5": { "cost": [ @@ -84030,7 +109549,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-05", + "limit": 1000000, + "max_output": 128000, + "released": "2026-07-24" }, "anthropic/claude-opus-5-fast": { "cost": [ @@ -84039,7 +109561,10 @@ 1.0, 12.5 ], - "limit": 1000000 + "knowledge": "2026-05", + "limit": 1000000, + "max_output": 128000, + "released": "2026-07-24" }, "anthropic/claude-opus-5.5": { "cost": [ @@ -84048,7 +109573,10 @@ 0.2, 5.0 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-22" }, "anthropic/claude-opus-5.5-fast": { "cost": [ @@ -84057,7 +109585,10 @@ 0.4, 10.0 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-22" }, "anthropic/claude-sonnet-4.5": { "cost": [ @@ -84066,7 +109597,10 @@ 0.3, 3.75 ], + "knowledge": "2025-07-31", "limit": 1000000, + "max_output": 64000, + "released": "2025-09-29", "tiers": [ { "cost": [ @@ -84089,7 +109623,10 @@ 0.3, 3.75 ], + "knowledge": "2025-08-31", "limit": 1000000, + "max_output": 128000, + "released": "2026-02-17", "tiers": [ { "cost": [ @@ -84112,7 +109649,10 @@ 0.2, 2.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-30" }, "anthropic/claude-sonnet-5.5": { "cost": [ @@ -84121,7 +109661,10 @@ 0.1, 2.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-28" }, "arcee-ai/trinity-large-thinking": { "cost": [ @@ -84130,7 +109673,10 @@ 0.06, 0.0 ], - "limit": 262100 + "limit": 262100, + "max_output": 80000, + "open": true, + "released": "2026-04-01" }, "bytedance/seed-1.6": { "cost": [ @@ -84140,6 +109686,8 @@ 0.0 ], "limit": 256000, + "max_output": 32000, + "released": "2025-10-15", "tiers": [ { "cost": [ @@ -84163,6 +109711,8 @@ 0.0 ], "limit": 256000, + "max_output": 32768, + "released": "2025-12-28", "tiers": [ { "cost": [ @@ -84185,7 +109735,9 @@ 0.1, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "released": "2026-06-23" }, "callstack/apex": { "cost": [ @@ -84194,7 +109746,9 @@ 0.2, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 131072, + "released": "2026-10-08" }, "cohere/command-a": { "cost": [ @@ -84203,7 +109757,11 @@ 0.0, 0.0 ], - "limit": 256000 + "knowledge": "2024-08-31", + "limit": 256000, + "max_output": 8000, + "open": true, + "released": "2025-03-13" }, "deepseek/deepseek-r1": { "cost": [ @@ -84212,7 +109770,11 @@ 0.0, 0.0 ], + "knowledge": "2024-07", "limit": 128000, + "max_output": 32768, + "open": true, + "released": "2025-01-20", "status": "deprecated" }, "deepseek/deepseek-v3.1": { @@ -84222,7 +109784,10 @@ 0.13, 0.0 ], - "limit": 163840 + "limit": 163840, + "max_output": 128000, + "open": true, + "released": "2025-08-21" }, "deepseek/deepseek-v3.2": { "cost": [ @@ -84231,7 +109796,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-07", + "limit": 128000, + "max_output": 8000, + "open": true, + "released": "2025-12-01" }, "deepseek/deepseek-v3.2-thinking": { "cost": [ @@ -84240,7 +109809,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-07", + "limit": 128000, + "max_output": 8000, + "open": true, + "released": "2025-12-01" }, "deepseek/deepseek-v4-flash": { "cost": [ @@ -84249,7 +109822,11 @@ 0.028, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "deepseek/deepseek-v4-flash-0731": { "cost": [ @@ -84258,7 +109835,11 @@ 0.014, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-07-31" }, "deepseek/deepseek-v4-flash-vision-exp": { "cost": [ @@ -84267,7 +109848,10 @@ 0.0068, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-08-21" }, "deepseek/deepseek-v4-pro": { "cost": [ @@ -84276,7 +109860,11 @@ 0.022, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "deepseek/deepseek-v4-pro-0813": { "cost": [ @@ -84285,7 +109873,10 @@ 0.066, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-08-13" }, "deepseek/deepseek-v4.1-flash": { "cost": [ @@ -84294,7 +109885,11 @@ 0.0015, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 32768, + "open": true, + "released": "2026-09-10" }, "deepseek/deepseek-v4.1-flash-1017": { "cost": [ @@ -84303,7 +109898,11 @@ 0.0015, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-10-17" }, "deepseek/deepseek-v4.1-flash-1017-fast": { "cost": [ @@ -84312,7 +109911,11 @@ 0.014, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 262144, + "open": true, + "released": "2026-10-17" }, "deepseek/deepseek-v4.1-flash-fast": { "cost": [ @@ -84321,7 +109924,11 @@ 0.014, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 32768, + "open": true, + "released": "2026-09-10" }, "elorian/glimpse": { "cost": [ @@ -84330,7 +109937,9 @@ 0.06, 0.0 ], - "limit": 220000 + "limit": 220000, + "max_output": 4096, + "released": "2026-10-16" }, "fireworks/ember-1": { "cost": [ @@ -84339,7 +109948,9 @@ 0.3, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "released": "2026-09-22" }, "google/gemini-2.5-flash": { "cost": [ @@ -84348,7 +109959,10 @@ 0.03, 0.0 ], - "limit": 1000000 + "knowledge": "2025-01", + "limit": 1000000, + "max_output": 65535, + "released": "2025-06-17" }, "google/gemini-2.5-flash-image": { "cost": [ @@ -84357,7 +109971,11 @@ 0.03, 0.0 ], - "limit": 32768 + "knowledge": "2024-06", + "limit": 32768, + "max_output": 65535, + "released": "2025-08-26", + "type": "image" }, "google/gemini-2.5-flash-lite": { "cost": [ @@ -84366,7 +109984,10 @@ 0.01, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65535, + "released": "2025-06-17" }, "google/gemini-2.5-pro": { "cost": [ @@ -84375,7 +109996,10 @@ 0.125, 0.0 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65535, + "released": "2025-06-17", "tiers": [ { "cost": [ @@ -84398,7 +110022,10 @@ 0.05, 0.0 ], - "limit": 1000000 + "knowledge": "2025-03", + "limit": 1000000, + "max_output": 65000, + "released": "2025-12-17" }, "google/gemini-3-pro-image": { "cost": [ @@ -84407,7 +110034,11 @@ 0.2, 0.0 ], - "limit": 65536 + "knowledge": "2025-01", + "limit": 65536, + "max_output": 32768, + "released": "2026-05-28", + "type": "image" }, "google/gemini-3.1-flash-image": { "cost": [ @@ -84416,7 +110047,11 @@ 0.05, 0.0 ], - "limit": 131072 + "knowledge": "2025-01", + "limit": 131072, + "max_output": 32768, + "released": "2026-05-28", + "type": "image" }, "google/gemini-3.1-flash-image-preview": { "cost": [ @@ -84425,7 +110060,11 @@ 0.05, 0.0 ], - "limit": 131072 + "knowledge": "2025-01", + "limit": 131072, + "max_output": 32768, + "released": "2026-02-26", + "type": "image" }, "google/gemini-3.1-flash-lite": { "cost": [ @@ -84434,7 +110073,10 @@ 0.03, 0.0 ], - "limit": 1000000 + "knowledge": "2025-01", + "limit": 1000000, + "max_output": 65000, + "released": "2026-05-07" }, "google/gemini-3.1-flash-lite-image": { "cost": [ @@ -84443,7 +110085,11 @@ 0.03, 0.0 ], - "limit": 65536 + "knowledge": "2025-01", + "limit": 65536, + "max_output": 4096, + "released": "2026-06-30", + "type": "image" }, "google/gemini-3.1-pro-preview": { "cost": [ @@ -84452,7 +110098,10 @@ 0.2, 0.0 ], + "knowledge": "2025-01", "limit": 1000000, + "max_output": 64000, + "released": "2026-02-19", "tiers": [ { "cost": [ @@ -84475,7 +110124,10 @@ 0.15, 0.0 ], - "limit": 1000000 + "knowledge": "2025-01", + "limit": 1000000, + "max_output": 64000, + "released": "2026-05-19" }, "google/gemini-3.5-flash-lite": { "cost": [ @@ -84484,7 +110136,10 @@ 0.03, 0.0 ], - "limit": 1000000 + "knowledge": "2026-03", + "limit": 1000000, + "max_output": 65000, + "released": "2026-07-21" }, "google/gemini-3.5-transcribe": { "cost": [ @@ -84493,7 +110148,10 @@ 0.0, 0.0 ], - "limit": 98304 + "limit": 98304, + "max_output": 32768, + "released": "2026-08-26", + "type": "transcription" }, "google/gemini-3.6-flash": { "cost": [ @@ -84502,7 +110160,10 @@ 0.075, 0.0 ], - "limit": 1000000 + "knowledge": "2026-03", + "limit": 1000000, + "max_output": 64000, + "released": "2026-07-21" }, "google/gemini-3.7-flash": { "cost": [ @@ -84511,7 +110172,10 @@ 0.075, 0.0 ], - "limit": 1000000 + "knowledge": "2026-03", + "limit": 1000000, + "max_output": 65535, + "released": "2026-08-13" }, "google/gemini-3.8-flash": { "cost": [ @@ -84520,7 +110184,9 @@ 0.075, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 65535, + "released": "2026-09-02" }, "google/gemini-3.8-flash-lite-tts": { "cost": [ @@ -84529,7 +110195,10 @@ 0.0, 0.0 ], - "limit": 8192 + "limit": 8192, + "max_output": 16384, + "released": "2026-09-22", + "type": "speech" }, "google/gemini-3.8-flash-tts": { "cost": [ @@ -84538,7 +110207,10 @@ 0.0, 0.0 ], - "limit": 8192 + "limit": 8192, + "max_output": 16384, + "released": "2026-09-22", + "type": "speech" }, "google/gemini-3.8-live": { "cost": [ @@ -84547,7 +110219,10 @@ 0.0, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 65536, + "released": "2026-09-15", + "type": "realtime" }, "google/gemini-3.8-live-extended-thinking": { "cost": [ @@ -84556,7 +110231,10 @@ 0.0, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 65536, + "released": "2026-09-15", + "type": "realtime" }, "google/gemini-4-argon": { "cost": [ @@ -84565,7 +110243,10 @@ 0.1, 0.0 ], - "limit": 1000000 + "knowledge": "2026-03", + "limit": 1000000, + "max_output": 1000000, + "released": "2026-10-13" }, "google/gemini-nano-banana-2.1": { "cost": [ @@ -84574,7 +110255,10 @@ 0.15, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 32768, + "released": "2026-10-06", + "type": "image" }, "google/gemini-omni-flash-preview": { "cost": [ @@ -84583,7 +110267,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 57920, + "released": "2026-06-30", + "type": "video" }, "google/gemma-4-26b-a4b-it": { "cost": [ @@ -84592,7 +110279,10 @@ 0.015, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 131072, + "open": true, + "released": "2026-04-02" }, "google/gemma-4-31b-it": { "cost": [ @@ -84601,7 +110291,11 @@ 0.0, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 131072, + "open": true, + "released": "2026-04-02" }, "inception/mercury-2": { "cost": [ @@ -84610,7 +110304,9 @@ 0.025, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 50000, + "released": "2026-02-24" }, "inception/mercury-2.5": { "cost": [ @@ -84619,7 +110315,9 @@ 0.004, 0.0 ], - "limit": 260000 + "limit": 260000, + "max_output": 65536, + "released": "2026-09-08" }, "inception/mercury-3": { "cost": [ @@ -84628,7 +110326,9 @@ 0.01, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-10-19" }, "inception/mercury-coder-small": { "cost": [ @@ -84637,7 +110337,9 @@ 0.0, 0.0 ], - "limit": 32000 + "limit": 32000, + "max_output": 16384, + "released": "2025-02-26" }, "inclusionai/ling-3.0-flash": { "cost": [ @@ -84646,7 +110348,10 @@ 0.0042, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 32000, + "open": true, + "released": "2026-07-23" }, "inclusionai/ling-3.0-flash-fin": { "cost": [ @@ -84655,7 +110360,10 @@ 0.015, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 32000, + "open": true, + "released": "2026-08-27" }, "inclusionai/ling-3.0-flash-sante": { "cost": [ @@ -84664,7 +110372,9 @@ 0.015, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 32000, + "released": "2026-09-04" }, "inclusionai/ling-3.0-flash-vl": { "cost": [ @@ -84673,7 +110383,10 @@ 0.015, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 32000, + "open": true, + "released": "2026-09-10" }, "inclusionai/ling-3.1-flash": { "cost": [ @@ -84682,7 +110395,10 @@ 0.06, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-09-29" }, "inference-net/schematron-v2-small": { "cost": [ @@ -84691,7 +110407,9 @@ 0.05, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 4096, + "released": "2026-04-16" }, "inference-net/schematron-v2-turbo": { "cost": [ @@ -84700,7 +110418,9 @@ 0.03, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 8192, + "released": "2026-04-16" }, "interfaze/interfaze-beta": { "cost": [ @@ -84709,7 +110429,9 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 32000, + "released": "2025-10-07" }, "liquid/lfm2.5-24b-a2b": { "cost": [ @@ -84718,7 +110440,9 @@ 0.025, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 8200, + "released": "2026-10-13" }, "meituan/longcat-2.5-preview": { "cost": [ @@ -84727,7 +110451,9 @@ 0.006, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "released": "2026-09-25" }, "meta/llama-3.1-70b": { "cost": [ @@ -84736,7 +110462,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2023-12", + "limit": 128000, + "max_output": 8192, + "open": true, + "released": "2024-07-23" }, "meta/llama-3.1-8b": { "cost": [ @@ -84745,7 +110475,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2023-12", + "limit": 128000, + "max_output": 8192, + "open": true, + "released": "2024-07-23" }, "meta/llama-3.3-70b": { "cost": [ @@ -84754,7 +110488,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2023-12", + "limit": 128000, + "max_output": 8192, + "open": true, + "released": "2024-12-06" }, "meta/llama-4-maverick": { "cost": [ @@ -84763,7 +110501,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-08", + "limit": 128000, + "max_output": 8192, + "open": true, + "released": "2025-04-05" }, "meta/llama-4-scout": { "cost": [ @@ -84772,7 +110514,11 @@ 0.0, 0.0 ], - "limit": 128000 + "knowledge": "2024-08", + "limit": 128000, + "max_output": 8192, + "open": true, + "released": "2025-04-05" }, "meta/muse-glimmer-30b": { "cost": [ @@ -84781,7 +110527,11 @@ 0.04, 0.0 ], - "limit": 131072 + "knowledge": "2026-01-04", + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2026-08-10" }, "meta/muse-spark-1.1": { "cost": [ @@ -84790,7 +110540,9 @@ 0.15, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "released": "2026-04-08" }, "meta/muse-spark-1.2": { "cost": [ @@ -84799,7 +110551,9 @@ 0.15, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "released": "2026-08-05" }, "meta/muse-spark-1.2-contributor": { "cost": [ @@ -84808,7 +110562,9 @@ 0.002, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "released": "2026-08-05" }, "meta/muse-spark-1.3": { "cost": [ @@ -84817,7 +110573,9 @@ 0.15, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "released": "2026-09-02" }, "meta/muse-spark-1.3-contributor": { "cost": [ @@ -84826,7 +110584,9 @@ 0.002, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "released": "2026-09-02" }, "meta/muse-spark-open": { "cost": [ @@ -84835,7 +110595,11 @@ 0.15, 0.0 ], - "limit": 1048576 + "knowledge": "2026-01-04", + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-10-15" }, "meta/muse-wonder-1.0": { "cost": [ @@ -84844,7 +110608,9 @@ 0.2, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "released": "2026-10-12" }, "microsoft/mai-image-2.6": { "cost": [ @@ -84852,7 +110618,9 @@ 38.0, 0.0, 0.0 - ] + ], + "released": "2026-10-13", + "type": "image" }, "microsoft/mai-image-2.6-flash": { "cost": [ @@ -84860,7 +110628,9 @@ 19.0, 0.0, 0.0 - ] + ], + "released": "2026-10-13", + "type": "image" }, "minimax/minimax-m2": { "cost": [ @@ -84869,7 +110639,10 @@ 0.03, 0.375 ], - "limit": 205000 + "limit": 205000, + "max_output": 196608, + "open": true, + "released": "2025-10-27" }, "minimax/minimax-m2.1": { "cost": [ @@ -84878,7 +110651,10 @@ 0.03, 0.375 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-12-23" }, "minimax/minimax-m2.1-lightning": { "cost": [ @@ -84887,7 +110663,10 @@ 0.03, 0.375 ], - "limit": 204800 + "knowledge": "2024-10", + "limit": 204800, + "max_output": 131072, + "released": "2025-12-23" }, "minimax/minimax-m2.5": { "cost": [ @@ -84896,7 +110675,10 @@ 0.03, 0.375 ], - "limit": 204800 + "limit": 204800, + "max_output": 131000, + "open": true, + "released": "2026-02-12" }, "minimax/minimax-m2.5-highspeed": { "cost": [ @@ -84905,7 +110687,10 @@ 0.03, 0.375 ], - "limit": 204800 + "limit": 204800, + "max_output": 131000, + "open": true, + "released": "2026-02-13" }, "minimax/minimax-m2.7": { "cost": [ @@ -84914,7 +110699,10 @@ 0.06, 0.375 ], - "limit": 204800 + "limit": 204800, + "max_output": 131000, + "open": true, + "released": "2026-03-18" }, "minimax/minimax-m2.7-highspeed": { "cost": [ @@ -84923,7 +110711,10 @@ 0.06, 0.375 ], - "limit": 204800 + "limit": 204800, + "max_output": 131100, + "open": true, + "released": "2026-03-18" }, "minimax/minimax-m3": { "cost": [ @@ -84932,7 +110723,10 @@ 0.06, 0.0 ], - "limit": 512000 + "limit": 512000, + "max_output": 512000, + "open": true, + "released": "2026-06-01" }, "minimax/minimax-m3.1-flash": { "cost": [ @@ -84941,7 +110735,9 @@ 0.015, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "released": "2026-10-19" }, "mistral/codestral": { "cost": [ @@ -84950,7 +110746,11 @@ 0.03, 0.0 ], - "limit": 128000 + "knowledge": "2024-10", + "limit": 128000, + "max_output": 4000, + "open": true, + "released": "2024-05-29" }, "mistral/ministral-14b": { "cost": [ @@ -84959,7 +110759,10 @@ 0.02, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 256000, + "open": true, + "released": "2025-12-02" }, "mistral/ministral-3b": { "cost": [ @@ -84968,7 +110771,11 @@ 0.01, 0.0 ], - "limit": 131072 + "knowledge": "2024-10", + "limit": 131072, + "max_output": 4000, + "open": true, + "released": "2024-10-16" }, "mistral/ministral-8b": { "cost": [ @@ -84977,7 +110784,11 @@ 0.015, 0.0 ], - "limit": 262144 + "knowledge": "2024-10", + "limit": 262144, + "max_output": 4000, + "open": true, + "released": "2024-10-16" }, "mistral/mistral-large-3": { "cost": [ @@ -84986,7 +110797,11 @@ 0.05, 0.0 ], - "limit": 262144 + "knowledge": "2024-11", + "limit": 262144, + "max_output": 256000, + "open": true, + "released": "2025-12-02" }, "mistral/mistral-large-4": { "cost": [ @@ -84995,7 +110810,9 @@ 0.14, 0.0 ], - "limit": 524288 + "limit": 524288, + "max_output": 262144, + "released": "2026-10-06" }, "mistral/mistral-medium-3.5": { "cost": [ @@ -85004,7 +110821,9 @@ 0.15, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 256000, + "released": "2026-04-30" }, "mistral/mistral-nemo": { "cost": [ @@ -85013,7 +110832,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-07", + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2024-07-18" }, "mistral/mistral-small": { "cost": [ @@ -85022,7 +110845,11 @@ 0.015, 0.0 ], - "limit": 262144 + "knowledge": "2025-06", + "limit": 262144, + "max_output": 4000, + "open": true, + "released": "2026-03-16" }, "mixedbread/toast-1": { "cost": [ @@ -85031,7 +110858,9 @@ 0.036, 0.0 ], - "limit": 131000 + "limit": 131000, + "max_output": 4000, + "released": "2026-08-13" }, "moonshotai/kimi-k2": { "cost": [ @@ -85040,7 +110869,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-12-31", + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2025-07-11" }, "moonshotai/kimi-k2.5": { "cost": [ @@ -85049,7 +110882,11 @@ 0.0, 0.0 ], - "limit": 256000 + "knowledge": "2025-01", + "limit": 256000, + "max_output": 256000, + "open": true, + "released": "2026-01-27" }, "moonshotai/kimi-k2.6": { "cost": [ @@ -85058,7 +110895,11 @@ 0.16, 0.0 ], - "limit": 262000 + "knowledge": "2025-01", + "limit": 262000, + "max_output": 262000, + "open": true, + "released": "2026-04-20" }, "moonshotai/kimi-k2.7-code": { "cost": [ @@ -85067,7 +110908,11 @@ 0.19, 0.0 ], - "limit": 256000 + "knowledge": "2025-01", + "limit": 256000, + "max_output": 32768, + "open": true, + "released": "2026-06-12" }, "moonshotai/kimi-k2.7-code-highspeed": { "cost": [ @@ -85076,7 +110921,11 @@ 0.38, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-06-12" }, "moonshotai/kimi-k3": { "cost": [ @@ -85085,7 +110934,10 @@ 0.3, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-07-16" }, "moonshotai/kimi-k3-fast": { "cost": [ @@ -85094,7 +110946,32 @@ 0.45, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-07-16" + }, + "moonshotai/kimi-k3.1-pro": { + "cost": [ + 2.0, + 10.0, + 0.2, + 2.0 + ], + "limit": 1048576, + "max_output": 1048576, + "released": "2026-10-23" + }, + "moonshotai/kimi-k3.1-pro-highspeed": { + "cost": [ + 4.0, + 20.0, + 0.2, + 4.0 + ], + "limit": 1048576, + "max_output": 1048576, + "released": "2026-10-23" }, "morph/morph-v3-fast": { "cost": [ @@ -85103,7 +110980,9 @@ 0.0, 0.0 ], - "limit": 16000 + "limit": 262144, + "max_output": 131072, + "released": "2025-07-07" }, "morph/morph-v3-large": { "cost": [ @@ -85112,7 +110991,9 @@ 0.0, 0.0 ], - "limit": 32000 + "limit": 262144, + "max_output": 131072, + "released": "2025-07-07" }, "nvidia/nemotron-3-nano-30b-a3b": { "cost": [ @@ -85121,7 +111002,11 @@ 0.025, 0.0 ], - "limit": 262144 + "knowledge": "2025-06-25", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2025-12-15" }, "nvidia/nemotron-3-super-120b-a12b": { "cost": [ @@ -85130,7 +111015,11 @@ 0.0, 0.0 ], - "limit": 256000 + "knowledge": "2025-06", + "limit": 256000, + "max_output": 32000, + "open": true, + "released": "2026-03-11" }, "nvidia/nemotron-3-ultra-550b-a55b": { "cost": [ @@ -85139,7 +111028,11 @@ 0.12, 0.0 ], - "limit": 1000000 + "knowledge": "2025-09", + "limit": 1000000, + "max_output": 65000, + "open": true, + "released": "2026-06-04" }, "nvidia/nemotron-3.5-lightning": { "cost": [ @@ -85148,7 +111041,11 @@ 0.01, 0.0 ], - "limit": 262144 + "knowledge": "2025-09", + "limit": 262144, + "max_output": 131072, + "open": true, + "released": "2026-08-11" }, "nvidia/nemotron-3.5-lightning-free": { "cost": [ @@ -85157,7 +111054,11 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-09", + "limit": 1000000, + "max_output": 65000, + "open": true, + "released": "2026-08-11" }, "nvidia/nemotron-3.5-super-vl": { "cost": [ @@ -85166,7 +111067,10 @@ 0.04, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-10-15" }, "nvidia/nemotron-nano-12b-v2-vl": { "cost": [ @@ -85175,7 +111079,10 @@ 0.0, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2025-10-28" }, "nvidia/nemotron-nano-9b-v2": { "cost": [ @@ -85184,7 +111091,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-09", + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2025-08-18" }, "openai/gpt-4.1": { "cost": [ @@ -85193,7 +111104,10 @@ 0.5, 0.0 ], - "limit": 1047576 + "knowledge": "2024-04", + "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14" }, "openai/gpt-4.1-fast": { "cost": [ @@ -85202,7 +111116,10 @@ 0.875, 0.0 ], - "limit": 1047576 + "knowledge": "2024-04", + "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14" }, "openai/gpt-4.1-mini": { "cost": [ @@ -85211,7 +111128,10 @@ 0.1, 0.0 ], - "limit": 1047576 + "knowledge": "2024-04", + "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14" }, "openai/gpt-4.1-mini-fast": { "cost": [ @@ -85220,7 +111140,10 @@ 0.175, 0.0 ], - "limit": 1047576 + "knowledge": "2024-04", + "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14" }, "openai/gpt-4.1-nano": { "cost": [ @@ -85229,7 +111152,10 @@ 0.03, 0.0 ], + "knowledge": "2024-04", "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14", "status": "deprecated" }, "openai/gpt-4.1-nano-fast": { @@ -85239,7 +111165,10 @@ 0.06, 0.0 ], + "knowledge": "2024-04", "limit": 1047576, + "max_output": 32768, + "released": "2025-04-14", "status": "deprecated" }, "openai/gpt-4o": { @@ -85249,7 +111178,10 @@ 1.25, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-05-13" }, "openai/gpt-4o-fast": { "cost": [ @@ -85258,7 +111190,10 @@ 2.125, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-05-13" }, "openai/gpt-4o-mini": { "cost": [ @@ -85267,7 +111202,10 @@ 0.075, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-07-18" }, "openai/gpt-4o-mini-fast": { "cost": [ @@ -85276,7 +111214,10 @@ 0.125, 0.0 ], - "limit": 128000 + "knowledge": "2023-09", + "limit": 128000, + "max_output": 16384, + "released": "2024-07-18" }, "openai/gpt-4o-mini-transcribe": { "cost": [ @@ -85285,7 +111226,11 @@ 0.0, 0.0 ], - "limit": 16000 + "knowledge": "2024-06-01", + "limit": 16000, + "max_output": 2000, + "released": "2025-03-20", + "type": "transcription" }, "openai/gpt-4o-transcribe": { "cost": [ @@ -85294,7 +111239,11 @@ 0.0, 0.0 ], - "limit": 16000 + "knowledge": "2024-06-01", + "limit": 16000, + "max_output": 2000, + "released": "2025-03-20", + "type": "transcription" }, "openai/gpt-5": { "cost": [ @@ -85303,7 +111252,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "openai/gpt-5-codex": { "cost": [ @@ -85312,7 +111264,10 @@ 0.13, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-09-15" }, "openai/gpt-5-fast": { "cost": [ @@ -85321,7 +111276,10 @@ 0.25, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "openai/gpt-5-flex": { "cost": [ @@ -85330,7 +111288,10 @@ 0.0625, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "openai/gpt-5-mini": { "cost": [ @@ -85339,7 +111300,10 @@ 0.025, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "openai/gpt-5-mini-fast": { "cost": [ @@ -85348,7 +111312,10 @@ 0.045, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "openai/gpt-5-mini-flex": { "cost": [ @@ -85357,7 +111324,10 @@ 0.0125, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "openai/gpt-5-nano": { "cost": [ @@ -85366,7 +111336,10 @@ 0.005, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "openai/gpt-5-nano-flex": { "cost": [ @@ -85375,7 +111348,10 @@ 0.0025, 0.0 ], - "limit": 400000 + "knowledge": "2024-05-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "openai/gpt-5-pro": { "cost": [ @@ -85384,7 +111360,10 @@ 0.0, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 272000, + "released": "2025-10-06" }, "openai/gpt-5.1-codex": { "cost": [ @@ -85393,7 +111372,10 @@ 0.13, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "openai/gpt-5.1-codex-max": { "cost": [ @@ -85402,7 +111384,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "openai/gpt-5.1-codex-mini": { "cost": [ @@ -85411,7 +111396,10 @@ 0.03, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "openai/gpt-5.1-thinking": { "cost": [ @@ -85420,7 +111408,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-10", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-12" }, "openai/gpt-5.1-thinking-fast": { "cost": [ @@ -85429,7 +111420,9 @@ 0.25, 0.0 ], - "limit": 400000 + "limit": 400000, + "max_output": 128000, + "released": "2025-11-12" }, "openai/gpt-5.2": { "cost": [ @@ -85438,7 +111431,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "openai/gpt-5.2-codex": { "cost": [ @@ -85447,7 +111443,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "openai/gpt-5.2-fast": { "cost": [ @@ -85456,7 +111455,10 @@ 0.35, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "openai/gpt-5.2-pro": { "cost": [ @@ -85465,7 +111467,10 @@ 0.0, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "openai/gpt-5.3-codex": { "cost": [ @@ -85474,7 +111479,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-02-05" }, "openai/gpt-5.3-codex-fast": { "cost": [ @@ -85483,7 +111491,10 @@ 0.35, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-02-05" }, "openai/gpt-5.4": { "cost": [ @@ -85492,7 +111503,10 @@ 0.25, 0.0 ], + "knowledge": "2025-08-31", "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05", "tiers": [ { "cost": [ @@ -85515,7 +111529,10 @@ 0.5, 0.0 ], - "limit": 1050000 + "knowledge": "2025-08-31", + "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05" }, "openai/gpt-5.4-mini": { "cost": [ @@ -85524,7 +111541,10 @@ 0.075, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "openai/gpt-5.4-mini-fast": { "cost": [ @@ -85533,7 +111553,10 @@ 0.15, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "openai/gpt-5.4-nano": { "cost": [ @@ -85542,7 +111565,10 @@ 0.02, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "openai/gpt-5.4-pro": { "cost": [ @@ -85551,7 +111577,10 @@ 0.0, 0.0 ], + "knowledge": "2025-08-31", "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05", "tiers": [ { "cost": [ @@ -85574,7 +111603,10 @@ 0.5, 0.0 ], + "knowledge": "2025-12-01", "limit": 1000000, + "max_output": 128000, + "released": "2026-04-23", "tiers": [ { "cost": [ @@ -85597,7 +111629,10 @@ 1.25, 0.0 ], - "limit": 1000000 + "knowledge": "2025-12-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-23" }, "openai/gpt-5.5-pro": { "cost": [ @@ -85606,7 +111641,10 @@ 0.0, 0.0 ], + "knowledge": "2025-12-01", "limit": 1000000, + "max_output": 128000, + "released": "2026-04-23", "tiers": [ { "cost": [ @@ -85629,7 +111667,10 @@ 0.02, 0.25 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -85652,7 +111693,10 @@ 0.04, 0.5 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -85675,7 +111719,10 @@ 0.4, 5.0 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -85698,7 +111745,10 @@ 0.8, 10.0 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -85721,7 +111771,10 @@ 0.2, 2.5 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -85744,7 +111797,10 @@ 0.4, 5.0 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -85767,7 +111823,10 @@ 1.0, 12.5 ], + "knowledge": "2026-04-30", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-04", "tiers": [ { "cost": [ @@ -85791,6 +111850,8 @@ 25.0 ], "limit": 1050000, + "max_output": 128000, + "released": "2026-09-04", "tiers": [ { "cost": [ @@ -85813,7 +111874,10 @@ 0.01, 0.125 ], + "knowledge": "2026-05-18", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -85836,7 +111900,10 @@ 0.02, 0.25 ], + "knowledge": "2026-05-18", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -85859,7 +111926,10 @@ 0.2, 2.5 ], + "knowledge": "2026-04-20", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -85882,7 +111952,10 @@ 0.4, 5.0 ], + "knowledge": "2026-04-20", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -85905,7 +111978,10 @@ 0.1, 2.5 ], + "knowledge": "2026-04-30", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-29", "tiers": [ { "cost": [ @@ -85928,7 +112004,10 @@ 0.2, 5.0 ], + "knowledge": "2026-04-30", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-29", "tiers": [ { "cost": [ @@ -85944,13 +112023,67 @@ } ] }, + "openai/gpt-6.1-terra": { + "cost": [ + 1.0, + 5.0, + 0.05, + 1.25 + ], + "knowledge": "2026-06-01", + "limit": 1050000, + "max_output": 128000, + "released": "2026-10-26", + "tiers": [ + { + "cost": [ + 2.0, + 7.5, + 0.1, + 2.5 + ], + "tier": { + "size": 272001, + "type": "context" + } + } + ] + }, + "openai/gpt-6.1-terra-fast": { + "cost": [ + 2.0, + 10.0, + 0.1, + 2.5 + ], + "knowledge": "2026-06-01", + "limit": 1050000, + "max_output": 128000, + "released": "2026-10-26", + "tiers": [ + { + "cost": [ + 4.0, + 15.0, + 0.2, + 5.0 + ], + "tier": { + "size": 272001, + "type": "context" + } + } + ] + }, "openai/gpt-image-1-mini": { "cost": [ 2.0, 8.0, 0.2, 0.0 - ] + ], + "released": "2025-10-06", + "type": "image" }, "openai/gpt-image-1.5": { "cost": [ @@ -85958,7 +112091,9 @@ 32.0, 1.25, 0.0 - ] + ], + "released": "2025-11-25", + "type": "image" }, "openai/gpt-image-2": { "cost": [ @@ -85966,7 +112101,9 @@ 30.0, 1.25, 0.0 - ] + ], + "released": "2026-04-21", + "type": "image" }, "openai/gpt-image-2.5-flare": { "cost": [ @@ -85974,7 +112111,9 @@ 30.0, 1.25, 0.0 - ] + ], + "released": "2026-09-08", + "type": "image" }, "openai/gpt-image-2.5-sunburst": { "cost": [ @@ -85982,7 +112121,9 @@ 30.0, 1.25, 0.0 - ] + ], + "released": "2026-09-08", + "type": "image" }, "openai/gpt-oss-120b": { "cost": [ @@ -85991,7 +112132,11 @@ 0.1, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2025-08-05" }, "openai/gpt-oss-20b": { "cost": [ @@ -86000,7 +112145,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 8192, + "open": true, + "released": "2025-08-05" }, "openai/gpt-oss-safeguard-120b": { "cost": [ @@ -86009,7 +112158,10 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 16000, + "open": true, + "released": "2025-10-29" }, "openai/gpt-oss-safeguard-20b": { "cost": [ @@ -86018,7 +112170,10 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 16000, + "open": true, + "released": "2025-10-29" }, "openai/gpt-realtime-1.5": { "cost": [ @@ -86027,7 +112182,11 @@ 0.4, 0.0 ], - "limit": 32000 + "knowledge": "2024-09-30", + "limit": 32000, + "max_output": 4096, + "released": "2026-02-23", + "type": "realtime" }, "openai/gpt-realtime-2": { "cost": [ @@ -86036,7 +112195,11 @@ 0.4, 0.0 ], - "limit": 128000 + "knowledge": "2024-09-30", + "limit": 128000, + "max_output": 32000, + "released": "2026-05-07", + "type": "realtime" }, "openai/gpt-realtime-2.1": { "cost": [ @@ -86045,7 +112208,11 @@ 0.4, 0.0 ], - "limit": 128000 + "knowledge": "2024-09-30", + "limit": 128000, + "max_output": 32000, + "released": "2026-07-06", + "type": "realtime" }, "openai/gpt-realtime-mini": { "cost": [ @@ -86054,7 +112221,11 @@ 0.06, 0.0 ], - "limit": 32000 + "knowledge": "2023-10-01", + "limit": 32000, + "max_output": 4096, + "released": "2025-10-06", + "type": "realtime" }, "openai/o1": { "cost": [ @@ -86063,7 +112234,10 @@ 7.5, 0.0 ], + "knowledge": "2023-09", "limit": 200000, + "max_output": 100000, + "released": "2024-12-05", "status": "deprecated" }, "openai/o3": { @@ -86073,7 +112247,10 @@ 0.5, 0.0 ], - "limit": 200000 + "knowledge": "2024-05", + "limit": 200000, + "max_output": 100000, + "released": "2025-04-16" }, "openai/o3-fast": { "cost": [ @@ -86082,7 +112259,10 @@ 0.875, 0.0 ], - "limit": 200000 + "knowledge": "2024-05", + "limit": 200000, + "max_output": 100000, + "released": "2025-04-16" }, "openai/o3-flex": { "cost": [ @@ -86091,7 +112271,10 @@ 0.25, 0.0 ], - "limit": 200000 + "knowledge": "2024-05", + "limit": 200000, + "max_output": 100000, + "released": "2025-04-16" }, "openai/o3-mini": { "cost": [ @@ -86100,7 +112283,10 @@ 0.55, 0.0 ], + "knowledge": "2024-05", "limit": 200000, + "max_output": 100000, + "released": "2024-12-20", "status": "deprecated" }, "openai/o3-pro": { @@ -86110,7 +112296,10 @@ 0.0, 0.0 ], - "limit": 200000 + "knowledge": "2024-05", + "limit": 200000, + "max_output": 100000, + "released": "2025-06-10" }, "openai/o4-mini": { "cost": [ @@ -86119,7 +112308,10 @@ 0.275, 0.0 ], + "knowledge": "2024-05", "limit": 200000, + "max_output": 100000, + "released": "2025-04-16", "status": "deprecated" }, "openai/o4-mini-fast": { @@ -86129,7 +112321,10 @@ 0.5, 0.0 ], + "knowledge": "2024-05", "limit": 200000, + "max_output": 100000, + "released": "2025-04-16", "status": "deprecated" }, "openai/o4-mini-flex": { @@ -86139,7 +112334,10 @@ 0.1375, 0.0 ], + "knowledge": "2024-05", "limit": 200000, + "max_output": 100000, + "released": "2025-04-16", "status": "deprecated" }, "perplexity/sonar": { @@ -86149,7 +112347,10 @@ 0.0, 0.0625 ], - "limit": 127000 + "knowledge": "2025-02", + "limit": 127000, + "max_output": 8000, + "released": "2025-02-19" }, "poolside/laguna-s-2.1": { "cost": [ @@ -86158,7 +112359,10 @@ 0.009, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-07-21" }, "poolside/laguna-s-2.1-free": { "cost": [ @@ -86167,7 +112371,10 @@ 0.0, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 32768, + "open": true, + "released": "2026-07-21" }, "quiverai/arrow-2": { "cost": [ @@ -86176,7 +112383,9 @@ 0.4, 5.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 65536, + "released": "2026-09-16" }, "quiverai/arrow-2-telos": { "cost": [ @@ -86185,7 +112394,9 @@ 0.6, 7.5 ], - "limit": 131072 + "limit": 131072, + "max_output": 65536, + "released": "2026-09-16" }, "reflection/beam": { "cost": [ @@ -86194,7 +112405,11 @@ 0.0, 0.0 ], - "limit": 1048576 + "knowledge": "2026-06-30", + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-10-05" }, "reflection/beam-free": { "cost": [ @@ -86203,7 +112418,11 @@ 0.0, 0.0 ], - "limit": 1048576 + "knowledge": "2026-06-30", + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-10-05" }, "sakana/fugu-max": { "cost": [ @@ -86212,7 +112431,9 @@ 0.25, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 1000000, + "released": "2026-09-11" }, "sakana/fugu-ultra": { "cost": [ @@ -86222,6 +112443,8 @@ 0.0 ], "limit": 1000000, + "max_output": 1000000, + "released": "2026-06-15", "tiers": [ { "cost": [ @@ -86244,7 +112467,10 @@ 0.5, 0.0 ], + "knowledge": "2026-08-28", "limit": 1000000, + "max_output": 1000000, + "released": "2026-09-11", "tiers": [ { "cost": [ @@ -86267,7 +112493,9 @@ 0.15, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 256000, + "released": "2026-08-03" }, "scaledown/scaledown-extract-1": { "cost": [ @@ -86276,7 +112504,9 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 1000000, + "released": "2026-10-20" }, "scaledown/scaledown-summarize-1": { "cost": [ @@ -86285,7 +112515,9 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 1000, + "released": "2026-10-20" }, "spacexai/grok-4.20-multi-agent": { "cost": [ @@ -86295,6 +112527,8 @@ 0.0 ], "limit": 2000000, + "max_output": 2000000, + "released": "2026-03-10", "tiers": [ { "cost": [ @@ -86318,6 +112552,8 @@ 0.0 ], "limit": 2000000, + "max_output": 2000000, + "released": "2026-03-11", "tiers": [ { "cost": [ @@ -86341,6 +112577,8 @@ 0.0 ], "limit": 2000000, + "max_output": 2000000, + "released": "2026-03-09", "tiers": [ { "cost": [ @@ -86364,6 +112602,8 @@ 0.0 ], "limit": 2000000, + "max_output": 2000000, + "released": "2026-03-11", "tiers": [ { "cost": [ @@ -86387,6 +112627,8 @@ 0.0 ], "limit": 2000000, + "max_output": 2000000, + "released": "2026-03-09", "tiers": [ { "cost": [ @@ -86410,6 +112652,8 @@ 0.0 ], "limit": 2000000, + "max_output": 2000000, + "released": "2026-03-11", "tiers": [ { "cost": [ @@ -86433,6 +112677,8 @@ 0.0 ], "limit": 1000000, + "max_output": 1000000, + "released": "2026-04-17", "tiers": [ { "cost": [ @@ -86456,6 +112702,8 @@ 0.0 ], "limit": 500000, + "max_output": 500000, + "released": "2026-07-08", "tiers": [ { "cost": [ @@ -86478,7 +112726,10 @@ 0.5, 0.0 ], + "knowledge": "2026-02-01", "limit": 500000, + "max_output": 500000, + "released": "2026-08-12", "tiers": [ { "cost": [ @@ -86501,7 +112752,10 @@ 0.5, 0.0 ], + "knowledge": "2026-05", "limit": 500000, + "max_output": 500000, + "released": "2026-09-21", "tiers": [ { "cost": [ @@ -86525,6 +112779,8 @@ 0.0 ], "limit": 256000, + "max_output": 256000, + "released": "2026-04-16", "tiers": [ { "cost": [ @@ -86547,7 +112803,9 @@ 0.0, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 256000, + "released": "2026-10-07" }, "stepfun/step-3.7-flash": { "cost": [ @@ -86556,7 +112814,11 @@ 0.04, 0.0 ], - "limit": 256000 + "knowledge": "2026-03-01", + "limit": 256000, + "max_output": 256000, + "open": true, + "released": "2026-05-29" }, "stepfun/step-5-preview": { "cost": [ @@ -86565,7 +112827,10 @@ 0.1, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-09-16" }, "tencent/hy-mt2-lite": { "cost": [ @@ -86574,7 +112839,9 @@ 0.0, 0.0 ], - "limit": 8000 + "limit": 8000, + "max_output": 4000, + "released": "2026-06-12" }, "tencent/hy-mt2-plus": { "cost": [ @@ -86583,7 +112850,9 @@ 0.0, 0.0 ], - "limit": 8000 + "limit": 8000, + "max_output": 4000, + "released": "2026-06-12" }, "tencent/hy-mt2-pro": { "cost": [ @@ -86592,7 +112861,9 @@ 0.0, 0.0 ], - "limit": 8000 + "limit": 8000, + "max_output": 4000, + "released": "2026-05-21" }, "tencent/hy3": { "cost": [ @@ -86601,7 +112872,10 @@ 0.035, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-07-06" }, "tencent/hy4-preview": { "cost": [ @@ -86610,7 +112884,10 @@ 0.042, 0.0 ], - "limit": 1024000 + "limit": 1024000, + "max_output": 64000, + "open": true, + "released": "2026-08-28" }, "thinkingmachines/inkling": { "cost": [ @@ -86619,7 +112896,10 @@ 0.17, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 256000, + "open": true, + "released": "2026-07-15" }, "thinkingmachines/inkling-small": { "cost": [ @@ -86628,7 +112908,10 @@ 0.1, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 1000000, + "open": true, + "released": "2026-07-30" }, "xiaomi/mimo-v2.5": { "cost": [ @@ -86637,7 +112920,11 @@ 0.0025, 0.0 ], - "limit": 1050000 + "knowledge": "2024-12", + "limit": 1050000, + "max_output": 131100, + "open": true, + "released": "2026-04-22" }, "xiaomi/mimo-v2.5-pro": { "cost": [ @@ -86646,7 +112933,11 @@ 0.0028, 0.0 ], - "limit": 1050000 + "knowledge": "2024-12", + "limit": 1050000, + "max_output": 131000, + "open": true, + "released": "2026-04-22" }, "xiaomi/mimo-v2.6-flash": { "cost": [ @@ -86655,7 +112946,10 @@ 0.0028, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-09-22" }, "xiaomi/mimo-v2.6-pro": { "cost": [ @@ -86664,7 +112958,10 @@ 0.0036, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-09-22" }, "xiaomi/mimo-v2.6-pro-ultraspeed": { "cost": [ @@ -86673,7 +112970,10 @@ 0.036, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-09-21" }, "zai/glm-4.5": { "cost": [ @@ -86682,7 +112982,11 @@ 0.11, 0.0 ], - "limit": 128000 + "knowledge": "2025-04", + "limit": 128000, + "max_output": 96000, + "open": true, + "released": "2025-07-28" }, "zai/glm-4.5-air": { "cost": [ @@ -86691,7 +112995,11 @@ 0.03, 0.0 ], - "limit": 128000 + "knowledge": "2025-04", + "limit": 128000, + "max_output": 96000, + "open": true, + "released": "2025-07-28" }, "zai/glm-4.5v": { "cost": [ @@ -86700,7 +113008,11 @@ 0.11, 0.0 ], - "limit": 66000 + "knowledge": "2025-04", + "limit": 66000, + "max_output": 16000, + "open": true, + "released": "2025-08-11" }, "zai/glm-4.6": { "cost": [ @@ -86709,7 +113021,11 @@ 0.11, 0.0 ], - "limit": 200000 + "knowledge": "2025-04", + "limit": 200000, + "max_output": 96000, + "open": true, + "released": "2025-09-30" }, "zai/glm-4.7": { "cost": [ @@ -86718,7 +113034,11 @@ 0.0, 0.0 ], - "limit": 200000 + "knowledge": "2025-04", + "limit": 200000, + "max_output": 120000, + "open": true, + "released": "2025-12-22" }, "zai/glm-4.7-flash": { "cost": [ @@ -86727,7 +113047,11 @@ 0.0, 0.0 ], - "limit": 200000 + "knowledge": "2025-04", + "limit": 200000, + "max_output": 131000, + "open": true, + "released": "2026-01-19" }, "zai/glm-4.7-flashx": { "cost": [ @@ -86736,7 +113060,11 @@ 0.01, 0.0 ], - "limit": 200000 + "knowledge": "2025-04", + "limit": 200000, + "max_output": 128000, + "open": true, + "released": "2026-01-19" }, "zai/glm-5": { "cost": [ @@ -86745,7 +113073,10 @@ 0.0, 0.0 ], - "limit": 202800 + "limit": 202800, + "max_output": 131100, + "open": true, + "released": "2026-02-12" }, "zai/glm-5-turbo": { "cost": [ @@ -86754,7 +113085,9 @@ 0.24, 0.0 ], - "limit": 202800 + "limit": 202800, + "max_output": 131072, + "released": "2026-03-16" }, "zai/glm-5.1": { "cost": [ @@ -86763,7 +113096,10 @@ 0.26, 0.0 ], - "limit": 202800 + "limit": 202800, + "max_output": 64000, + "open": true, + "released": "2026-04-07" }, "zai/glm-5.2": { "cost": [ @@ -86772,7 +113108,10 @@ 0.16, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 128000, + "open": true, + "released": "2026-06-13" }, "zai/glm-5.2-fast": { "cost": [ @@ -86781,7 +113120,10 @@ 0.56, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 128000, + "open": true, + "released": "2026-06-13" }, "zai/glm-5.3": { "cost": [ @@ -86790,7 +113132,10 @@ 0.2, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 262144, + "open": true, + "released": "2026-08-14" }, "zai/glm-5.3-fast": { "cost": [ @@ -86799,7 +113144,10 @@ 0.21, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 262144, + "open": true, + "released": "2026-08-14" }, "zai/glm-5.3-flash": { "cost": [ @@ -86808,7 +113156,10 @@ 0.03, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131000, + "open": true, + "released": "2026-08-26" }, "zai/glm-5.3-flashx": { "cost": [ @@ -86817,7 +113168,10 @@ 0.075, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-26" }, "zai/glm-5v-turbo": { "cost": [ @@ -86826,7 +113180,9 @@ 0.24, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 128000, + "released": "2026-04-01" } }, "name": "Vercel AI Gateway" @@ -86840,7 +113196,9 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 65536, + "released": "2024-05-15" }, "vispark/vision-medium": { "cost": [ @@ -86849,7 +113207,9 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 65536, + "released": "2024-05-15" }, "vispark/vision-small": { "cost": [ @@ -86858,7 +113218,9 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 65536, + "released": "2024-05-15" } }, "name": "Vispark" @@ -86872,7 +113234,10 @@ 1.25, 12.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-09" }, "claude-fable-5-1": { "cost": [ @@ -86881,7 +113246,10 @@ 0.5, 12.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-01" }, "claude-haiku-5-5": { "cost": [ @@ -86890,7 +113258,10 @@ 0.01, 0.125 ], + "knowledge": "2026-06", "limit": 1000000, + "max_output": 128000, + "released": "2026-10-07", "tiers": [ { "cost": [ @@ -86913,7 +113284,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-05", + "limit": 1000000, + "max_output": 128000, + "released": "2026-07-24" }, "claude-opus-5-5": { "cost": [ @@ -86922,7 +113296,10 @@ 0.2, 5.0 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-22" }, "claude-sonnet-5": { "cost": [ @@ -86931,7 +113308,10 @@ 0.2, 2.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-30" }, "claude-sonnet-5-5": { "cost": [ @@ -86940,7 +113320,10 @@ 0.2, 2.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-28" }, "deepseek-v3.2": { "cost": [ @@ -86949,7 +113332,12 @@ 0.03, 0.0 ], - "limit": 128000 + "knowledge": "2024-07", + "limit": 128000, + "max_output": 128000, + "open": true, + "released": "2025-12-01", + "status": "deprecated" }, "deepseek-v4-flash": { "cost": [ @@ -86958,7 +113346,11 @@ 0.044, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-07-31" }, "deepseek-v4-pro": { "cost": [ @@ -86967,7 +113359,11 @@ 0.14, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "deepseek-v4-pro-0813": { "cost": [ @@ -86976,7 +113372,10 @@ 0.05, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-08-13" }, "deepseek-v4.1-flash": { "cost": [ @@ -86985,7 +113384,11 @@ 0.01, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-09-10" }, "gemini-3.1-flash-lite-preview": { "cost": [ @@ -86994,7 +113397,11 @@ 0.025, 1.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-03-03", + "status": "deprecated" }, "gemini-3.1-pro-preview": { "cost": [ @@ -87003,7 +113410,11 @@ 0.3, 0.0 ], + "knowledge": "2025-01", "limit": 1048576, + "max_output": 65536, + "released": "2026-02-19", + "status": "deprecated", "tiers": [ { "cost": [ @@ -87026,7 +113437,10 @@ 0.075, 0.0 ], - "limit": 1048576 + "knowledge": "2026-03", + "limit": 1048576, + "max_output": 65536, + "released": "2026-08-13" }, "gemini-3.8-flash": { "cost": [ @@ -87035,7 +113449,9 @@ 0.15, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 128000, + "released": "2026-09-02" }, "glm-5.2": { "cost": [ @@ -87044,7 +113460,11 @@ 0.3, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 128000, + "open": true, + "released": "2026-06-13", + "status": "deprecated" }, "glm-5.3": { "cost": [ @@ -87053,7 +113473,10 @@ 0.3, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "glm-5.3-flash": { "cost": [ @@ -87062,7 +113485,10 @@ 0.04, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-26" }, "gpt-5-mini": { "cost": [ @@ -87071,7 +113497,11 @@ 0.03, 0.0 ], - "limit": 272000 + "knowledge": "2024-05-30", + "limit": 272000, + "max_output": 128000, + "released": "2025-08-07", + "status": "deprecated" }, "gpt-5.1-codex": { "cost": [ @@ -87080,7 +113510,11 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13", + "status": "deprecated" }, "gpt-5.1-codex-max": { "cost": [ @@ -87089,7 +113523,11 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13", + "status": "deprecated" }, "gpt-5.2-codex": { "cost": [ @@ -87098,7 +113536,11 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11", + "status": "deprecated" }, "gpt-5.3-codex": { "cost": [ @@ -87107,7 +113549,11 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-02-05", + "status": "deprecated" }, "gpt-5.4": { "cost": [ @@ -87116,7 +113562,11 @@ 0.25, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-05", + "status": "deprecated" }, "gpt-5.4-mini": { "cost": [ @@ -87125,7 +113575,11 @@ 0.075, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17", + "status": "deprecated" }, "gpt-5.4-nano": { "cost": [ @@ -87134,7 +113588,11 @@ 0.02, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17", + "status": "deprecated" }, "gpt-5.5": { "cost": [ @@ -87143,7 +113601,11 @@ 0.5, 0.0 ], + "knowledge": "2025-12-01", "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23", + "status": "deprecated", "tiers": [ { "cost": [ @@ -87166,7 +113628,10 @@ 0.1, 1.25 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "gpt-5.6-sol": { "cost": [ @@ -87175,7 +113640,10 @@ 0.5, 6.25 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "gpt-5.6-terra": { "cost": [ @@ -87184,7 +113652,10 @@ 0.25, 3.125 ], - "limit": 1050000 + "knowledge": "2026-02-16", + "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09" }, "gpt-6-astra": { "cost": [ @@ -87193,7 +113664,10 @@ 1.0, 12.5 ], + "knowledge": "2026-04-30", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-04", "tiers": [ { "cost": [ @@ -87216,7 +113690,10 @@ 0.01, 0.125 ], + "knowledge": "2026-05-18", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -87239,7 +113716,10 @@ 0.2, 2.5 ], + "knowledge": "2026-04-20", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -87262,7 +113742,10 @@ 0.2, 2.5 ], + "knowledge": "2026-04-30", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-29", "tiers": [ { "cost": [ @@ -87278,6 +113761,32 @@ } ] }, + "gpt-6.1-terra": { + "cost": [ + 1.1, + 5.5, + 0.055, + 1.375 + ], + "knowledge": "2026-06-01", + "limit": 1050000, + "max_output": 128000, + "released": "2026-10-26", + "tiers": [ + { + "cost": [ + 2.2, + 8.25, + 0.11, + 2.75 + ], + "tier": { + "size": 272000, + "type": "context" + } + } + ] + }, "kimi-k3": { "cost": [ 3.0, @@ -87285,7 +113794,10 @@ 0.3, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-07-16" }, "viv-fast": { "cost": [ @@ -87294,7 +113806,10 @@ 0.05, 0.0 ], - "limit": 1000000 + "knowledge": "2026-09", + "limit": 1000000, + "max_output": 256000, + "released": "2026-09-21" } }, "name": "Vivgrid" @@ -87308,7 +113823,11 @@ 0.01484, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-07-31" }, "deepseek-v4-pro-ga-260813": { "cost": [ @@ -87317,7 +113836,10 @@ 0.04453, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-08-13" }, "doubao-seed-1-6-251015": { "cost": [ @@ -87327,6 +113849,8 @@ 0.0 ], "limit": 256000, + "max_output": 64000, + "released": "2025-10-15", "status": "deprecated", "tiers": [ { @@ -87363,6 +113887,8 @@ 0.0 ], "limit": 256000, + "max_output": 32000, + "released": "2025-08-28", "status": "deprecated", "tiers": [ { @@ -87399,6 +113925,8 @@ 0.0 ], "limit": 256000, + "max_output": 32000, + "released": "2025-08-15", "status": "deprecated", "tiers": [ { @@ -87435,6 +113963,8 @@ 0.0 ], "limit": 256000, + "max_output": 64000, + "released": "2025-12-28", "status": "deprecated", "tiers": [ { @@ -87471,6 +114001,8 @@ 0.0 ], "limit": 262144, + "max_output": 131072, + "released": "2026-02-14", "status": "deprecated", "tiers": [ { @@ -87507,6 +114039,8 @@ 0.0 ], "limit": 256000, + "max_output": 131072, + "released": "2026-02-14", "tiers": [ { "cost": [ @@ -87542,6 +114076,8 @@ 0.0 ], "limit": 256000, + "max_output": 131072, + "released": "2026-02-14", "tiers": [ { "cost": [ @@ -87577,6 +114113,8 @@ 0.0 ], "limit": 256000, + "max_output": 128000, + "released": "2026-02-14", "status": "deprecated", "tiers": [ { @@ -87612,7 +114150,9 @@ 0.17812, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 256000, + "released": "2026-06-23" }, "doubao-seed-2-1-turbo-260628": { "cost": [ @@ -87621,7 +114161,9 @@ 0.08906, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 256000, + "released": "2026-06-23" }, "doubao-seed-character-260628": { "cost": [ @@ -87631,6 +114173,8 @@ 0.0 ], "limit": 256000, + "max_output": 256000, + "released": "2026-06-23", "tiers": [ { "cost": [ @@ -87653,7 +114197,9 @@ 0.17812, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 256000, + "released": "2026-06-23" }, "glm-5-2-260617": { "cost": [ @@ -87662,7 +114208,10 @@ 0.29687, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "glm-5-3-flash-260828": { "cost": [ @@ -87671,7 +114220,10 @@ 0.03414, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-26" } }, "name": "Volcengine Ark" @@ -87685,7 +114237,11 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "deepseek-v4-pro": { "cost": [ @@ -87694,7 +114250,11 @@ 0.0, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "doubao-seed-2.0-lite": { "cost": [ @@ -87704,6 +114264,8 @@ 0.0 ], "limit": 256000, + "max_output": 32000, + "released": "2026-02-14", "status": "deprecated" }, "doubao-seed-2.1-turbo": { @@ -87714,6 +114276,8 @@ 0.0 ], "limit": 256000, + "max_output": 256000, + "released": "2026-06-23", "status": "deprecated" }, "doubao-seed-evolving": { @@ -87723,7 +114287,9 @@ 0.0, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 256000, + "released": "2026-06-23" }, "glm-5.3": { "cost": [ @@ -87732,7 +114298,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "glm-5.3-flash": { "cost": [ @@ -87741,7 +114310,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-26" }, "kimi-k2.7-code": { "cost": [ @@ -87750,7 +114322,11 @@ 0.0, 0.0 ], + "knowledge": "2025-01", "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-06-12", "status": "deprecated" }, "kimi-k3": { @@ -87760,7 +114336,10 @@ 0.0, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-16" }, "minimax-m3": { "cost": [ @@ -87770,6 +114349,9 @@ 0.0 ], "limit": 1048576, + "max_output": 512000, + "open": true, + "released": "2026-06-01", "status": "deprecated" } }, @@ -87784,7 +114366,11 @@ 0.0, 0.0 ], + "knowledge": "2025-05", "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-07-31", "status": "deprecated" }, "deepseek-v4.1-flash": { @@ -87794,7 +114380,11 @@ 0.0, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 384000, + "open": true, + "released": "2026-09-10" }, "glm-5.2": { "cost": [ @@ -87803,7 +114393,10 @@ 0.0, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "glm-5.3": { "cost": [ @@ -87812,7 +114405,10 @@ 0.0, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "glm-5.3-flash": { "cost": [ @@ -87821,7 +114417,10 @@ 0.0, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-08-26" }, "glm-5.x-menthol": { "cost": [ @@ -87830,7 +114429,10 @@ 0.0, 0.0 ], - "limit": 202752 + "limit": 202752, + "max_output": 131072, + "open": true, + "released": "2026-02-12" }, "laguna-s-2.1": { "cost": [ @@ -87840,6 +114442,9 @@ 0.0 ], "limit": 1048576, + "max_output": 32768, + "open": true, + "released": "2026-07-21", "status": "deprecated" }, "mimo-v2.6-flash-rl": { @@ -87849,7 +114454,10 @@ 0.0, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-09-22" }, "mimo-v2.6-pro-rl": { "cost": [ @@ -87858,7 +114466,10 @@ 0.0, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-09-22" }, "minimax-m3": { "cost": [ @@ -87867,7 +114478,10 @@ 0.0, 0.0 ], - "limit": 524288 + "limit": 524288, + "max_output": 512000, + "open": true, + "released": "2026-06-01" }, "muse-glimmer-30b": { "cost": [ @@ -87876,7 +114490,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2026-01-04", + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2026-08-10" }, "nemotron-3-nano-omni-30b-a3b-reasoning": { "cost": [ @@ -87885,7 +114503,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-04-28" }, "nemotron-3.5-content-safety": { "cost": [ @@ -87894,7 +114515,10 @@ 0.0, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 8192, + "open": true, + "released": "2026-06-02" }, "qwen3.8-27b": { "cost": [ @@ -87903,7 +114527,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 32768, + "open": true, + "released": "2026-08-14" }, "qwen3.8-flash-next": { "cost": [ @@ -87912,7 +114539,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 131072, + "open": true, + "released": "2026-08-27" } }, "name": "Vultr" @@ -87926,7 +114556,11 @@ 0.1, 0.0 ], + "knowledge": "2025-04", "limit": 202752, + "max_output": 131072, + "open": true, + "released": "2026-04-07", "status": "deprecated" }, "GLM-5.2": { @@ -87936,7 +114570,10 @@ 0.26, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "Kimi-K2.6": { "cost": [ @@ -87945,7 +114582,11 @@ 0.19, 0.0 ], + "knowledge": "2025-01", "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-04-20", "status": "deprecated" }, "MiniMax-M3": { @@ -87956,6 +114597,9 @@ 0.0 ], "limit": 1048576, + "max_output": 512000, + "open": true, + "released": "2026-06-01", "status": "deprecated", "tiers": [ { @@ -87980,6 +114624,9 @@ 0.0 ], "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-06-13", "status": "deprecated" } }, @@ -87994,7 +114641,10 @@ 0.27, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-16" } }, "name": "Wallaby" @@ -88008,16 +114658,22 @@ 0.05, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-06-01" }, "Qwen/Qwen3.6-35B-A3B": { "cost": [ - 0.25, - 1.25, - 0.25, + 0.1, + 0.95, + 0.05, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-17" }, "Qwen/Qwen3.8-27B": { "cost": [ @@ -88026,7 +114682,10 @@ 0.15, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-08-14" }, "deepseek-ai/DeepSeek-V3.1": { "cost": [ @@ -88035,7 +114694,10 @@ 0.55, 0.0 ], - "limit": 161000 + "limit": 161000, + "max_output": 161000, + "open": true, + "released": "2025-08-21" }, "deepseek-ai/DeepSeek-V4-Flash-0731": { "cost": [ @@ -88044,7 +114706,11 @@ 0.07, 0.0 ], - "limit": 262144 + "knowledge": "2025-05", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-07-31" }, "deepseek-ai/DeepSeek-V4-Pro-0813": { "cost": [ @@ -88053,16 +114719,23 @@ 0.044, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-08-13" }, "deepseek-ai/DeepSeek-V4.1-Flash": { "cost": [ - 0.15, + 0.13, 0.65, 0.002, 0.0 ], - "limit": 1048576 + "knowledge": "2025-05", + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-09-10" }, "google/gemma-4-26B-A4B-it": { "cost": [ @@ -88071,7 +114744,10 @@ 0.05, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-02" }, "google/gemma-4-31B-it": { "cost": [ @@ -88080,16 +114756,23 @@ 0.1, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-02" }, "ibm-granite/granite-4.2-8b": { "cost": [ - 0.1, + 0.06, 0.15, - 0.05, + 0.015, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2026-08-25" }, "meta-llama/Llama-3.1-8B-Instruct": { "cost": [ @@ -88098,7 +114781,11 @@ 0.22, 0.0 ], - "limit": 131072 + "knowledge": "2023-12", + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2024-07-23" }, "meta-llama/Llama-3.3-70B-Instruct": { "cost": [ @@ -88107,7 +114794,11 @@ 0.71, 0.0 ], - "limit": 128000 + "knowledge": "2023-12", + "limit": 128000, + "max_output": 128000, + "open": true, + "released": "2024-12-06" }, "moonshotai/Kimi-K2.6": { "cost": [ @@ -88116,16 +114807,24 @@ 0.15, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-04-20" }, "moonshotai/Kimi-K2.7-Code": { "cost": [ - 0.71, - 3.5, - 0.15, + 0.6, + 3.0, + 0.12, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-06-12" }, "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B": { "cost": [ @@ -88134,7 +114833,11 @@ 0.1, 0.0 ], - "limit": 262144 + "knowledge": "2025-09", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-06-04" }, "nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B": { "cost": [ @@ -88143,7 +114846,11 @@ 0.04, 0.0 ], - "limit": 262144 + "knowledge": "2025-09", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-08-11" }, "nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B": { "cost": [ @@ -88152,7 +114859,10 @@ 0.02, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-10-15" }, "openai/gpt-oss-120b": { "cost": [ @@ -88161,7 +114871,11 @@ 0.03, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2025-08-05" }, "openai/gpt-oss-20b": { "cost": [ @@ -88170,7 +114884,11 @@ 0.03, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2025-08-05" }, "reflection/Beam-1.0-501B-A23B": { "cost": [ @@ -88179,7 +114897,11 @@ 0.04, 0.0 ], - "limit": 1048576 + "knowledge": "2026-06-30", + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-10-05" }, "zai-org/GLM-5.2": { "cost": [ @@ -88188,7 +114910,10 @@ 0.14, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-06-13" }, "zai-org/GLM-5.3": { "cost": [ @@ -88197,16 +114922,22 @@ 0.19, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-08-14" }, "zai-org/GLM-5.3-Flash": { "cost": [ - 0.15, - 0.5, + 0.12, + 0.38, 0.02, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 1048576, + "open": true, + "released": "2026-08-26" } }, "name": "CoreWeave" @@ -88220,7 +114951,10 @@ 0.0, 0.0 ], - "limit": 131072 + "limit": 131072, + "max_output": 131072, + "open": true, + "released": "2025-10-02" }, "meta-llama/llama-3-3-70b-instruct": { "cost": [ @@ -88229,7 +114963,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2023-12", + "limit": 131072, + "max_output": 4096, + "open": true, + "released": "2024-12-06" }, "meta-llama/llama-4-maverick-17b-128e-instruct-fp8": { "cost": [ @@ -88238,7 +114976,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-08", + "limit": 131072, + "max_output": 8192, + "open": true, + "released": "2025-04-05" }, "mistralai/mistral-small-3-1-24b-instruct-2503": { "cost": [ @@ -88247,7 +114989,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 16384, + "open": true, + "released": "2025-03-17" }, "openai/gpt-oss-120b": { "cost": [ @@ -88256,7 +115002,11 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2024-06", + "limit": 131072, + "max_output": 32768, + "open": true, + "released": "2025-08-05" } }, "name": "watsonx.ai" @@ -88271,6 +115021,8 @@ 0.0 ], "limit": 1000000, + "max_output": 30000, + "released": "2026-03-09", "tiers": [ { "cost": [ @@ -88294,6 +115046,8 @@ 0.0 ], "limit": 1000000, + "max_output": 30000, + "released": "2026-03-09", "tiers": [ { "cost": [ @@ -88317,6 +115071,8 @@ 0.0 ], "limit": 1000000, + "max_output": 30000, + "released": "2026-03-09", "tiers": [ { "cost": [ @@ -88340,6 +115096,8 @@ 0.0 ], "limit": 1000000, + "max_output": 30000, + "released": "2026-04-17", "tiers": [ { "cost": [ @@ -88363,6 +115121,8 @@ 0.0 ], "limit": 500000, + "max_output": 500000, + "released": "2026-07-08", "tiers": [ { "cost": [ @@ -88385,7 +115145,10 @@ 0.5, 0.0 ], + "knowledge": "2026-02-01", "limit": 500000, + "max_output": 500000, + "released": "2026-08-12", "tiers": [ { "cost": [ @@ -88408,7 +115171,10 @@ 0.5, 0.0 ], + "knowledge": "2026-05", "limit": 500000, + "max_output": 500000, + "released": "2026-09-21", "tiers": [ { "cost": [ @@ -88432,6 +115198,8 @@ 0.0 ], "limit": 256000, + "max_output": 256000, + "released": "2026-04-16", "tiers": [ { "cost": [ @@ -88459,7 +115227,11 @@ 0.0028, 0.0 ], + "knowledge": "2024-12", "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-04-22", "status": "deprecated" }, "mimo-v2.5-pro": { @@ -88469,7 +115241,11 @@ 0.0036, 0.0 ], + "knowledge": "2024-12", "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-04-22", "status": "deprecated" }, "mimo-v2.5-pro-ultraspeed": { @@ -88479,7 +115255,11 @@ 0.0108, 0.0 ], + "knowledge": "2024-12", "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-06-08", "status": "deprecated" }, "mimo-v2.6-flash": { @@ -88489,7 +115269,10 @@ 0.0028, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-09-22" }, "mimo-v2.6-pro": { "cost": [ @@ -88498,7 +115281,10 @@ 0.0036, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-09-22" }, "mimo-v2.6-pro-ultraspeed": { "cost": [ @@ -88507,7 +115293,10 @@ 0.036, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-09-21" } }, "name": "Xiaomi" @@ -88521,7 +115310,11 @@ 0.0, 0.0 ], + "knowledge": "2024-12", "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-04-22", "status": "deprecated" }, "mimo-v2.5-pro": { @@ -88531,7 +115324,11 @@ 0.0, 0.0 ], + "knowledge": "2024-12", "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-04-22", "status": "deprecated" }, "mimo-v2.5-tts": { @@ -88541,7 +115338,10 @@ 0.0, 0.0 ], - "limit": 8192 + "limit": 8192, + "max_output": 8192, + "released": "2026-04-22", + "type": "speech" }, "mimo-v2.5-tts-voiceclone": { "cost": [ @@ -88550,7 +115350,10 @@ 0.0, 0.0 ], - "limit": 8192 + "limit": 8192, + "max_output": 8192, + "released": "2026-04-22", + "type": "speech" }, "mimo-v2.5-tts-voicedesign": { "cost": [ @@ -88559,7 +115362,10 @@ 0.0, 0.0 ], - "limit": 8192 + "limit": 8192, + "max_output": 8192, + "released": "2026-04-22", + "type": "speech" }, "mimo-v2.6-flash": { "cost": [ @@ -88568,7 +115374,10 @@ 0.0, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-09-22" }, "mimo-v2.6-pro": { "cost": [ @@ -88577,7 +115386,10 @@ 0.0, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-09-22" } }, "name": "Xiaomi Token Plan (Europe)" @@ -88591,7 +115403,11 @@ 0.0, 0.0 ], + "knowledge": "2024-12", "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-04-22", "status": "deprecated" }, "mimo-v2.5-pro": { @@ -88601,7 +115417,11 @@ 0.0, 0.0 ], + "knowledge": "2024-12", "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-04-22", "status": "deprecated" }, "mimo-v2.5-tts": { @@ -88611,7 +115431,10 @@ 0.0, 0.0 ], - "limit": 8192 + "limit": 8192, + "max_output": 8192, + "released": "2026-04-22", + "type": "speech" }, "mimo-v2.5-tts-voiceclone": { "cost": [ @@ -88620,7 +115443,10 @@ 0.0, 0.0 ], - "limit": 8192 + "limit": 8192, + "max_output": 8192, + "released": "2026-04-22", + "type": "speech" }, "mimo-v2.5-tts-voicedesign": { "cost": [ @@ -88629,7 +115455,10 @@ 0.0, 0.0 ], - "limit": 8192 + "limit": 8192, + "max_output": 8192, + "released": "2026-04-22", + "type": "speech" }, "mimo-v2.6-flash": { "cost": [ @@ -88638,7 +115467,10 @@ 0.0, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-09-22" }, "mimo-v2.6-pro": { "cost": [ @@ -88647,7 +115479,10 @@ 0.0, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-09-22" } }, "name": "Xiaomi Token Plan (China)" @@ -88661,7 +115496,11 @@ 0.0, 0.0 ], + "knowledge": "2024-12", "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-04-22", "status": "deprecated" }, "mimo-v2.5-pro": { @@ -88671,7 +115510,11 @@ 0.0, 0.0 ], + "knowledge": "2024-12", "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-04-22", "status": "deprecated" }, "mimo-v2.5-tts": { @@ -88681,7 +115524,10 @@ 0.0, 0.0 ], - "limit": 8192 + "limit": 8192, + "max_output": 8192, + "released": "2026-04-22", + "type": "speech" }, "mimo-v2.5-tts-voiceclone": { "cost": [ @@ -88690,7 +115536,10 @@ 0.0, 0.0 ], - "limit": 8192 + "limit": 8192, + "max_output": 8192, + "released": "2026-04-22", + "type": "speech" }, "mimo-v2.5-tts-voicedesign": { "cost": [ @@ -88699,7 +115548,10 @@ 0.0, 0.0 ], - "limit": 8192 + "limit": 8192, + "max_output": 8192, + "released": "2026-04-22", + "type": "speech" }, "mimo-v2.6-flash": { "cost": [ @@ -88708,7 +115560,10 @@ 0.0, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-09-22" }, "mimo-v2.6-pro": { "cost": [ @@ -88717,7 +115572,10 @@ 0.0, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-09-22" } }, "name": "Xiaomi Token Plan (Singapore)" @@ -88731,7 +115589,10 @@ 0.3, 0.0 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-09" }, "claude-haiku-4-5": { "cost": [ @@ -88740,7 +115601,10 @@ 0.06, 0.0 ], - "limit": 200000 + "knowledge": "2025-02-28", + "limit": 200000, + "max_output": 128000, + "released": "2025-10-15" }, "claude-opus-4-8": { "cost": [ @@ -88749,7 +115613,10 @@ 0.15, 0.0 ], - "limit": 200000 + "knowledge": "2026-01", + "limit": 200000, + "max_output": 128000, + "released": "2026-05-28" }, "claude-sonnet-4-6": { "cost": [ @@ -88758,7 +115625,10 @@ 0.09, 0.0 ], - "limit": 200000 + "knowledge": "2025-08-31", + "limit": 200000, + "max_output": 128000, + "released": "2026-02-17" }, "gemini-3.5-flash": { "cost": [ @@ -88767,7 +115637,10 @@ 0.155, 0.0 ], - "limit": 1000000 + "knowledge": "2025-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-19" }, "gpt-5.4": { "cost": [ @@ -88776,7 +115649,10 @@ 0.075, 0.0 ], - "limit": 1050000 + "knowledge": "2025-08-31", + "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05" }, "gpt-5.4-mini": { "cost": [ @@ -88785,7 +115661,10 @@ 0.0375, 0.0 ], - "limit": 272000 + "knowledge": "2025-08-31", + "limit": 272000, + "max_output": 128000, + "released": "2026-03-17" }, "gpt-5.5": { "cost": [ @@ -88794,7 +115673,10 @@ 0.15, 0.0 ], - "limit": 1050000 + "knowledge": "2025-12-01", + "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23" }, "gpt-5.6": { "cost": [ @@ -88803,7 +115685,10 @@ 0.15, 0.0 ], - "limit": 372000 + "knowledge": "2026-02-16", + "limit": 372000, + "max_output": 128000, + "released": "2026-07-09" }, "gpt-5.6-sol": { "cost": [ @@ -88812,7 +115697,10 @@ 0.15, 0.0 ], - "limit": 372000 + "knowledge": "2026-02-16", + "limit": 372000, + "max_output": 128000, + "released": "2026-07-09" }, "gpt-5.6-terra": { "cost": [ @@ -88821,7 +115709,10 @@ 0.15, 0.0 ], - "limit": 372000 + "knowledge": "2026-02-16", + "limit": 372000, + "max_output": 128000, + "released": "2026-07-09" }, "xpersona-frieren-coder": { "cost": [ @@ -88830,7 +115721,10 @@ 0.15, 0.0 ], - "limit": 1000000 + "knowledge": "2025-12-30", + "limit": 1000000, + "max_output": 384000, + "released": "2026-05-01" }, "xpersona-gpt-5.5": { "cost": [ @@ -88839,7 +115733,10 @@ 0.3, 0.0 ], + "knowledge": "2025-12-30", "limit": 1000000, + "max_output": 128000, + "released": "2026-04-23", "status": "deprecated" } }, @@ -88854,7 +115751,11 @@ 0.11, 0.0 ], - "limit": 131072 + "knowledge": "2025-04", + "limit": 131072, + "max_output": 98304, + "open": true, + "released": "2025-07-28" }, "glm-4.5-air": { "cost": [ @@ -88863,7 +115764,11 @@ 0.03, 0.0 ], - "limit": 131072 + "knowledge": "2025-04", + "limit": 131072, + "max_output": 98304, + "open": true, + "released": "2025-07-28" }, "glm-4.5-flash": { "cost": [ @@ -88872,7 +115777,10 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2025-04", + "limit": 131072, + "max_output": 98304, + "released": "2025-07-28" }, "glm-4.5v": { "cost": [ @@ -88881,7 +115789,11 @@ 0.11, 0.0 ], - "limit": 64000 + "knowledge": "2025-04", + "limit": 64000, + "max_output": 16384, + "open": true, + "released": "2025-08-11" }, "glm-4.6": { "cost": [ @@ -88890,7 +115802,11 @@ 0.11, 0.0 ], - "limit": 204800 + "knowledge": "2025-04", + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-09-30" }, "glm-4.6v": { "cost": [ @@ -88899,7 +115815,11 @@ 0.05, 0.0 ], - "limit": 128000 + "knowledge": "2025-04", + "limit": 128000, + "max_output": 32768, + "open": true, + "released": "2025-12-08" }, "glm-4.6v-flash": { "cost": [ @@ -88908,7 +115828,10 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 32768, + "open": true, + "released": "2025-12-08" }, "glm-4.7": { "cost": [ @@ -88917,7 +115840,11 @@ 0.11, 0.0 ], - "limit": 204800 + "knowledge": "2025-04", + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-12-22" }, "glm-4.7-flash": { "cost": [ @@ -88926,7 +115853,11 @@ 0.0, 0.0 ], - "limit": 200000 + "knowledge": "2025-04", + "limit": 200000, + "max_output": 131072, + "open": true, + "released": "2026-01-19" }, "glm-4.7-flashx": { "cost": [ @@ -88935,7 +115866,11 @@ 0.01, 0.0 ], - "limit": 200000 + "knowledge": "2025-04", + "limit": 200000, + "max_output": 131072, + "open": true, + "released": "2026-01-19" }, "glm-5": { "cost": [ @@ -88944,7 +115879,10 @@ 0.2, 0.0 ], - "limit": 204800 + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-02-12" }, "glm-5-turbo": { "cost": [ @@ -88953,7 +115891,9 @@ 0.24, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 131072, + "released": "2026-03-16" }, "glm-5.1": { "cost": [ @@ -88962,7 +115902,10 @@ 0.26, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 131072, + "open": true, + "released": "2026-04-07" }, "glm-5.2": { "cost": [ @@ -88971,7 +115914,10 @@ 0.26, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "glm-5.3": { "cost": [ @@ -88980,7 +115926,10 @@ 0.26, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "glm-5.3-flash": { "cost": [ @@ -88989,7 +115938,10 @@ 0.03, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-26" }, "glm-5.3-flashx": { "cost": [ @@ -88998,7 +115950,10 @@ 0.075, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-09-18" }, "glm-5v-turbo": { "cost": [ @@ -89007,7 +115962,9 @@ 0.24, 0.0 ], - "limit": 200000 + "limit": 200000, + "max_output": 131072, + "released": "2026-04-01" } }, "name": "Z.AI" @@ -89021,7 +115978,11 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-12-22", "status": "deprecated" }, "glm-5-turbo": { @@ -89032,6 +115993,8 @@ 0.0 ], "limit": 200000, + "max_output": 131072, + "released": "2026-03-16", "status": "deprecated" }, "glm-5.2": { @@ -89042,6 +116005,9 @@ 0.0 ], "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-13", "status": "deprecated" }, "glm-5.2-highspeed": { @@ -89052,6 +116018,9 @@ 0.0 ], "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-13", "status": "deprecated" }, "glm-5.3": { @@ -89061,7 +116030,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "glm-5.3-flash": { "cost": [ @@ -89070,7 +116042,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-26" }, "glm-5.3-highspeed": { "cost": [ @@ -89079,7 +116054,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-14" } }, "name": "Z.AI Coding Plan" @@ -89093,7 +116071,9 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "released": "2026-08-26" } }, "name": "Zeldoc" @@ -89107,7 +116087,10 @@ 0.0, 0.0 ], - "limit": 262144 + "limit": 262144, + "max_output": 65536, + "open": true, + "released": "2026-04-17" } }, "name": "Zenifra" @@ -89121,7 +116104,10 @@ 1.0, 12.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-06-09" }, "anthropic/claude-fable-5.1": { "cost": [ @@ -89130,7 +116116,10 @@ 0.25, 12.5 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-01" }, "anthropic/claude-haiku-4.5": { "cost": [ @@ -89139,7 +116128,10 @@ 0.1, 1.25 ], - "limit": 200000 + "knowledge": "2025-02-28", + "limit": 200000, + "max_output": 64000, + "released": "2025-10-15" }, "anthropic/claude-opus-4.1": { "cost": [ @@ -89148,7 +116140,10 @@ 1.5, 18.75 ], - "limit": 200000 + "knowledge": "2025-03-31", + "limit": 200000, + "max_output": 32000, + "released": "2025-08-05" }, "anthropic/claude-opus-4.5": { "cost": [ @@ -89157,7 +116152,10 @@ 0.5, 6.25 ], - "limit": 200000 + "knowledge": "2025-05", + "limit": 200000, + "max_output": 32000, + "released": "2025-11-24" }, "anthropic/claude-opus-4.6": { "cost": [ @@ -89166,7 +116164,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2025-05-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-02-05" }, "anthropic/claude-opus-4.7": { "cost": [ @@ -89175,7 +116176,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 128000, + "released": "2026-04-16" }, "anthropic/claude-opus-4.8": { "cost": [ @@ -89184,7 +116188,10 @@ 0.5, 6.25 ], - "limit": 1000000 + "knowledge": "2026-01", + "limit": 1000000, + "max_output": 128000, + "released": "2026-05-28" }, "anthropic/claude-opus-5.5": { "cost": [ @@ -89193,7 +116200,10 @@ 0.2, 5.0 ], - "limit": 1000000 + "knowledge": "2026-06", + "limit": 1000000, + "max_output": 128000, + "released": "2026-09-22" }, "anthropic/claude-sonnet-4.5": { "cost": [ @@ -89202,7 +116212,10 @@ 0.3, 3.75 ], + "knowledge": "2025-07-31", "limit": 1000000, + "max_output": 64000, + "released": "2025-09-29", "tiers": [ { "cost": [ @@ -89225,7 +116238,10 @@ 0.3, 3.75 ], - "limit": 1000000 + "knowledge": "2025-08-31", + "limit": 1000000, + "max_output": 64000, + "released": "2026-02-17" }, "anthropic/claude-sonnet-5": { "cost": [ @@ -89234,7 +116250,10 @@ 0.2, 2.5 ], - "limit": 1000000 + "knowledge": "2026-01-31", + "limit": 1000000, + "max_output": 64000, + "released": "2026-06-30" }, "baidu/ernie-5.0-thinking-preview": { "cost": [ @@ -89243,7 +116262,10 @@ 0.0, 0.0 ], + "knowledge": "2025-01-01", "limit": 128000, + "max_output": 64000, + "released": "2026-01-22", "tiers": [ { "cost": [ @@ -89267,6 +116289,8 @@ 0.0 ], "limit": 256000, + "max_output": 32000, + "released": "2025-12-28", "tiers": [ { "cost": [ @@ -89302,6 +116326,8 @@ 0.0 ], "limit": 256000, + "max_output": 32000, + "released": "2026-02-14", "tiers": [ { "cost": [ @@ -89337,6 +116363,8 @@ 0.0 ], "limit": 256000, + "max_output": 32000, + "released": "2026-02-14", "tiers": [ { "cost": [ @@ -89372,6 +116400,8 @@ 0.0 ], "limit": 256000, + "max_output": 32000, + "released": "2026-02-14", "tiers": [ { "cost": [ @@ -89407,6 +116437,8 @@ 0.0 ], "limit": 256000, + "max_output": 32000, + "released": "2026-02-14", "tiers": [ { "cost": [ @@ -89442,6 +116474,8 @@ 0.0 ], "limit": 256000, + "max_output": 32000, + "released": "2025-11-11", "tiers": [ { "cost": [ @@ -89476,7 +116510,11 @@ 0.0293, 0.0 ], - "limit": 128000 + "knowledge": "2024-07", + "limit": 128000, + "max_output": 8000, + "open": true, + "released": "2025-12-01" }, "deepseek/deepseek-v3.2-exp": { "cost": [ @@ -89485,7 +116523,10 @@ 0.0, 0.0 ], + "knowledge": "2025-01-01", "limit": 163000, + "max_output": 64000, + "released": "2025-09-29", "status": "deprecated" }, "deepseek/deepseek-v4-flash": { @@ -89495,7 +116536,11 @@ 0.007, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "deepseek/deepseek-v4-pro": { "cost": [ @@ -89504,7 +116549,11 @@ 0.022, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-04-24" }, "deepseek/deepseek-v4.1-flash": { "cost": [ @@ -89513,7 +116562,11 @@ 0.0015, 0.0 ], - "limit": 1000000 + "knowledge": "2025-05", + "limit": 1000000, + "max_output": 384000, + "open": true, + "released": "2026-09-10" }, "google/gemini-2.5-flash": { "cost": [ @@ -89522,7 +116575,10 @@ 0.03, 0.0 ], - "limit": 1048000 + "knowledge": "2025-01", + "limit": 1048000, + "max_output": 65535, + "released": "2025-06-17" }, "google/gemini-2.5-flash-lite": { "cost": [ @@ -89531,7 +116587,10 @@ 0.01, 0.0 ], - "limit": 1048000 + "knowledge": "2025-01", + "limit": 1048000, + "max_output": 65535, + "released": "2025-06-17" }, "google/gemini-2.5-pro": { "cost": [ @@ -89540,7 +116599,10 @@ 0.13, 0.0 ], + "knowledge": "2025-01", "limit": 1048000, + "max_output": 65535, + "released": "2025-06-17", "tiers": [ { "cost": [ @@ -89563,7 +116625,10 @@ 0.05, 1.0 ], - "limit": 1048000 + "knowledge": "2025-01", + "limit": 1048000, + "max_output": 65535, + "released": "2025-12-17" }, "google/gemini-3.1-flash-lite": { "cost": [ @@ -89572,7 +116637,10 @@ 0.025, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-05-07" }, "google/gemini-3.1-pro-preview": { "cost": [ @@ -89581,7 +116649,10 @@ 0.2, 0.0 ], + "knowledge": "2025-01", "limit": 1048000, + "max_output": 65535, + "released": "2026-02-19", "tiers": [ { "cost": [ @@ -89604,7 +116675,10 @@ 0.15, 0.0 ], - "limit": 1048576 + "knowledge": "2025-01", + "limit": 1048576, + "max_output": 65536, + "released": "2026-05-19" }, "inclusionai/ring-2.6-1t": { "cost": [ @@ -89613,7 +116687,11 @@ 0.0263631, 0.0 ], - "limit": 262000 + "knowledge": "2025-12-31", + "limit": 262000, + "max_output": 65000, + "open": true, + "released": "2026-05-07" }, "minimax/minimax-m2": { "cost": [ @@ -89622,7 +116700,11 @@ 0.03, 0.375 ], - "limit": 204000 + "knowledge": "2025-01-01", + "limit": 204000, + "max_output": 128000, + "open": true, + "released": "2025-10-27" }, "minimax/minimax-m2.1": { "cost": [ @@ -89631,7 +116713,11 @@ 0.03, 0.375 ], - "limit": 204000 + "knowledge": "2025-01-01", + "limit": 204000, + "max_output": 131072, + "open": true, + "released": "2025-12-23" }, "minimax/minimax-m2.5": { "cost": [ @@ -89640,7 +116726,11 @@ 0.03, 0.375 ], - "limit": 204800 + "knowledge": "2025-01-01", + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-02-12" }, "minimax/minimax-m2.5-lightning": { "cost": [ @@ -89649,7 +116739,11 @@ 0.03, 0.375 ], - "limit": 204800 + "knowledge": "2025-01-01", + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-02-13" }, "minimax/minimax-m2.7": { "cost": [ @@ -89658,7 +116752,11 @@ 0.06, 0.375 ], - "limit": 204800 + "knowledge": "2025-01-01", + "limit": 204800, + "max_output": 131070, + "open": true, + "released": "2026-03-18" }, "minimax/minimax-m2.7-highspeed": { "cost": [ @@ -89667,7 +116765,11 @@ 0.0611, 0.3819 ], - "limit": 204800 + "knowledge": "2025-01-01", + "limit": 204800, + "max_output": 131070, + "open": true, + "released": "2026-03-18" }, "minimax/minimax-m3": { "cost": [ @@ -89677,6 +116779,9 @@ 0.0 ], "limit": 1000000, + "max_output": 512000, + "open": true, + "released": "2026-06-01", "tiers": [ { "cost": [ @@ -89699,7 +116804,9 @@ 0.015, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 512000, + "released": "2026-10-19" }, "moonshotai/kimi-k2.6": { "cost": [ @@ -89708,7 +116815,11 @@ 0.16, 0.0 ], - "limit": 262140 + "knowledge": "2025-01", + "limit": 262140, + "max_output": 262140, + "open": true, + "released": "2026-04-20" }, "moonshotai/kimi-k2.7-code": { "cost": [ @@ -89717,7 +116828,11 @@ 0.19, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-06-12" }, "moonshotai/kimi-k2.7-code-highspeed": { "cost": [ @@ -89726,7 +116841,11 @@ 0.38, 0.0 ], - "limit": 262144 + "knowledge": "2025-01", + "limit": 262144, + "max_output": 262144, + "open": true, + "released": "2026-06-12" }, "moonshotai/kimi-k3": { "cost": [ @@ -89735,7 +116854,10 @@ 0.3, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-07-16" }, "openai/chat-latest": { "cost": [ @@ -89744,7 +116866,10 @@ 0.5, 0.0 ], - "limit": 400000 + "knowledge": "2025-12-01", + "limit": 400000, + "max_output": 128000, + "released": "2026-05-05" }, "openai/gpt-5": { "cost": [ @@ -89753,7 +116878,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-08-07" }, "openai/gpt-5-codex": { "cost": [ @@ -89762,7 +116890,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-09-15" }, "openai/gpt-5.1": { "cost": [ @@ -89771,7 +116902,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "openai/gpt-5.1-codex": { "cost": [ @@ -89780,7 +116914,10 @@ 0.125, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 128000, + "released": "2025-11-13" }, "openai/gpt-5.1-codex-mini": { "cost": [ @@ -89789,7 +116926,10 @@ 0.025, 0.0 ], - "limit": 400000 + "knowledge": "2024-09-30", + "limit": 400000, + "max_output": 100000, + "released": "2025-11-13" }, "openai/gpt-5.2": { "cost": [ @@ -89798,7 +116938,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "openai/gpt-5.2-codex": { "cost": [ @@ -89807,7 +116950,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "openai/gpt-5.2-pro": { "cost": [ @@ -89816,7 +116962,10 @@ 0.0, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2025-12-11" }, "openai/gpt-5.3-codex": { "cost": [ @@ -89825,7 +116974,10 @@ 0.175, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-02-05" }, "openai/gpt-5.4": { "cost": [ @@ -89834,7 +116986,10 @@ 0.25, 0.0 ], + "knowledge": "2025-08-31", "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05", "tiers": [ { "cost": [ @@ -89857,7 +117012,10 @@ 0.075, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "openai/gpt-5.4-nano": { "cost": [ @@ -89866,7 +117024,10 @@ 0.02, 0.0 ], - "limit": 400000 + "knowledge": "2025-08-31", + "limit": 400000, + "max_output": 128000, + "released": "2026-03-17" }, "openai/gpt-5.4-pro": { "cost": [ @@ -89875,7 +117036,10 @@ 0.0, 0.0 ], + "knowledge": "2025-08-31", "limit": 1050000, + "max_output": 128000, + "released": "2026-03-05", "tiers": [ { "cost": [ @@ -89898,7 +117062,10 @@ 0.5, 0.0 ], + "knowledge": "2025-12-01", "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23", "tiers": [ { "cost": [ @@ -89921,7 +117088,10 @@ 1.25, 0.0 ], - "limit": 1050000 + "knowledge": "2025-12-01", + "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23" }, "openai/gpt-5.5-pro": { "cost": [ @@ -89930,7 +117100,10 @@ 0.0, 0.0 ], + "knowledge": "2025-12-01", "limit": 1050000, + "max_output": 128000, + "released": "2026-04-23", "tiers": [ { "cost": [ @@ -89953,7 +117126,10 @@ 0.02, 0.25 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -89976,7 +117152,10 @@ 0.4, 5.0 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -89999,7 +117178,10 @@ 0.2, 2.5 ], + "knowledge": "2026-02-16", "limit": 1050000, + "max_output": 128000, + "released": "2026-07-09", "tiers": [ { "cost": [ @@ -90022,7 +117204,10 @@ 1.0, 12.5 ], + "knowledge": "2026-04-30", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-04", "tiers": [ { "cost": [ @@ -90045,7 +117230,10 @@ 0.2, 2.5 ], + "knowledge": "2026-04-20", "limit": 1050000, + "max_output": 128000, + "released": "2026-09-22", "tiers": [ { "cost": [ @@ -90068,7 +117256,10 @@ 0.1, 1.25 ], + "knowledge": "2025-04", "limit": 1000000, + "max_output": 64000, + "released": "2025-07-23", "status": "deprecated" }, "qwen/qwen3-max": { @@ -90078,7 +117269,10 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 256000, + "max_output": 64000, + "released": "2025-09-23", "status": "deprecated" }, "qwen/qwen3.5-flash": { @@ -90088,7 +117282,10 @@ 0.02, 0.125 ], - "limit": 1020000 + "knowledge": "2025-01-01", + "limit": 1020000, + "max_output": 1020000, + "released": "2026-02-23" }, "qwen/qwen3.5-plus": { "cost": [ @@ -90097,7 +117294,10 @@ 0.08, 0.5 ], + "knowledge": "2025-04", "limit": 1000000, + "max_output": 64000, + "released": "2026-02-16", "tiers": [ { "cost": [ @@ -90120,7 +117320,10 @@ 0.1, 0.625 ], + "knowledge": "2025-04", "limit": 1000000, + "max_output": 64000, + "released": "2026-04-02", "tiers": [ { "cost": [ @@ -90143,7 +117346,9 @@ 0.25, 1.5625 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 64000, + "released": "2026-05-21" }, "qwen/qwen3.7-plus": { "cost": [ @@ -90152,7 +117357,10 @@ 0.08, 0.5 ], + "knowledge": "2025-04", "limit": 1000000, + "max_output": 64000, + "released": "2026-06-02", "tiers": [ { "cost": [ @@ -90175,7 +117383,11 @@ 0.0, 0.0 ], - "limit": 256000 + "knowledge": "2025-01", + "limit": 256000, + "max_output": 256000, + "open": true, + "released": "2026-01-29" }, "stepfun/step-3.7-flash": { "cost": [ @@ -90184,7 +117396,11 @@ 0.04, 0.0 ], - "limit": 256000 + "knowledge": "2026-03-01", + "limit": 256000, + "max_output": 256000, + "open": true, + "released": "2026-05-29" }, "volcengine/doubao-seed-1.8": { "cost": [ @@ -90193,7 +117409,10 @@ 0.02, 0.0024 ], + "knowledge": "2025-01-01", "limit": 256000, + "max_output": 64000, + "released": "2025-12-28", "status": "deprecated" }, "volcengine/doubao-seed-2.0-code": { @@ -90203,7 +117422,10 @@ 0.0, 0.0 ], + "knowledge": "2025-01-01", "limit": 256000, + "max_output": 32000, + "released": "2026-02-14", "status": "deprecated" }, "volcengine/doubao-seed-2.0-lite": { @@ -90213,7 +117435,10 @@ 0.02, 0.0024 ], + "knowledge": "2026-02-14", "limit": 256000, + "max_output": 64000, + "released": "2026-02-14", "status": "deprecated" }, "volcengine/doubao-seed-2.0-mini": { @@ -90223,7 +117448,10 @@ 0.01, 0.0024 ], + "knowledge": "2026-02-14", "limit": 256000, + "max_output": 64000, + "released": "2026-02-14", "status": "deprecated" }, "volcengine/doubao-seed-2.0-pro": { @@ -90233,7 +117461,10 @@ 0.09, 0.0024 ], + "knowledge": "2026-02-14", "limit": 256000, + "max_output": 64000, + "released": "2026-02-14", "status": "deprecated" }, "volcengine/doubao-seed-code": { @@ -90243,7 +117474,10 @@ 0.03, 0.0 ], + "knowledge": "2025-01-01", "limit": 256000, + "max_output": 64000, + "released": "2025-11-11", "status": "deprecated" }, "x-ai/grok-4.2-fast": { @@ -90254,6 +117488,8 @@ 0.0 ], "limit": 2000000, + "max_output": 30000, + "released": "2026-03-09", "tiers": [ { "cost": [ @@ -90277,6 +117513,8 @@ 0.0 ], "limit": 2000000, + "max_output": 30000, + "released": "2026-03-09", "tiers": [ { "cost": [ @@ -90300,6 +117538,8 @@ 0.0 ], "limit": 1000000, + "max_output": 1000000, + "released": "2026-04-17", "tiers": [ { "cost": [ @@ -90323,6 +117563,8 @@ 0.0 ], "limit": 500000, + "max_output": 500000, + "released": "2026-07-08", "tiers": [ { "cost": [ @@ -90345,7 +117587,10 @@ 0.5, 0.0 ], + "knowledge": "2026-02-01", "limit": 500000, + "max_output": 500000, + "released": "2026-08-12", "tiers": [ { "cost": [ @@ -90368,7 +117613,9 @@ 0.2, 0.0 ], - "limit": 256000 + "limit": 256000, + "max_output": 256000, + "released": "2026-04-16" }, "xiaomi/mimo-v2.5": { "cost": [ @@ -90377,7 +117624,11 @@ 0.08, 0.0 ], + "knowledge": "2024-12", "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-04-22", "status": "deprecated", "tiers": [ { @@ -90401,7 +117652,11 @@ 0.2, 0.0 ], + "knowledge": "2024-12", "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-04-22", "status": "deprecated", "tiers": [ { @@ -90425,7 +117680,10 @@ 0.0036, 0.0 ], - "limit": 1048576 + "limit": 1048576, + "max_output": 131072, + "open": true, + "released": "2026-09-22" }, "z-ai/glm-4.5": { "cost": [ @@ -90434,7 +117692,11 @@ 0.0582, 0.0 ], + "knowledge": "2025-04", "limit": 128000, + "max_output": 96000, + "open": true, + "released": "2025-07-28", "tiers": [ { "cost": [ @@ -90457,7 +117719,11 @@ 0.0233, 0.0 ], + "knowledge": "2025-04", "limit": 128000, + "max_output": 96000, + "open": true, + "released": "2025-07-28", "tiers": [ { "cost": [ @@ -90480,7 +117746,11 @@ 0.0582, 0.0 ], + "knowledge": "2025-04", "limit": 200000, + "max_output": 128000, + "open": true, + "released": "2025-09-30", "tiers": [ { "cost": [ @@ -90503,7 +117773,11 @@ 0.0291, 0.0 ], + "knowledge": "2025-04", "limit": 200000, + "max_output": 128000, + "open": true, + "released": "2025-12-08", "tiers": [ { "cost": [ @@ -90527,6 +117801,9 @@ 0.0 ], "limit": 200000, + "max_output": 128000, + "open": true, + "released": "2025-12-08", "tiers": [ { "cost": [ @@ -90550,6 +117827,9 @@ 0.0 ], "limit": 200000, + "max_output": 128000, + "open": true, + "released": "2025-12-08", "tiers": [ { "cost": [ @@ -90572,7 +117852,11 @@ 0.0582, 0.0 ], + "knowledge": "2025-04", "limit": 200000, + "max_output": 128000, + "open": true, + "released": "2025-12-22", "tiers": [ { "cost": [ @@ -90595,7 +117879,11 @@ 0.0, 0.0 ], - "limit": 200000 + "knowledge": "2025-04", + "limit": 200000, + "max_output": 128000, + "open": true, + "released": "2026-01-19" }, "z-ai/glm-4.7-flashx": { "cost": [ @@ -90604,7 +117892,11 @@ 0.0146, 0.0 ], - "limit": 200000 + "knowledge": "2025-04", + "limit": 200000, + "max_output": 128000, + "open": true, + "released": "2026-01-19" }, "z-ai/glm-5": { "cost": [ @@ -90614,6 +117906,9 @@ 0.0 ], "limit": 200000, + "max_output": 128000, + "open": true, + "released": "2026-02-12", "tiers": [ { "cost": [ @@ -90637,6 +117932,8 @@ 0.0 ], "limit": 200000, + "max_output": 128000, + "released": "2026-03-16", "tiers": [ { "cost": [ @@ -90660,6 +117957,9 @@ 0.0 ], "limit": 200000, + "max_output": 128000, + "open": true, + "released": "2026-04-07", "tiers": [ { "cost": [ @@ -90682,7 +117982,10 @@ 0.26, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 128000, + "open": true, + "released": "2026-06-13" }, "z-ai/glm-5.3": { "cost": [ @@ -90691,7 +117994,10 @@ 0.26, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 128000, + "open": true, + "released": "2026-08-14" }, "z-ai/glm-5.3-flash": { "cost": [ @@ -90700,7 +118006,10 @@ 0.015, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 128000, + "open": true, + "released": "2026-08-26" }, "z-ai/glm-5.3-flashx": { "cost": [ @@ -90709,7 +118018,10 @@ 0.075, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 128000, + "open": true, + "released": "2026-08-26" }, "z-ai/glm-5v-turbo": { "cost": [ @@ -90719,6 +118031,8 @@ 0.0 ], "limit": 200000, + "max_output": 128000, + "released": "2026-04-01", "tiers": [ { "cost": [ @@ -90746,7 +118060,11 @@ 0.11, 0.0 ], - "limit": 131072 + "knowledge": "2025-04", + "limit": 131072, + "max_output": 98304, + "open": true, + "released": "2025-07-28" }, "glm-4.5-air": { "cost": [ @@ -90755,7 +118073,11 @@ 0.0239, 0.0 ], + "knowledge": "2025-04", "limit": 131072, + "max_output": 98304, + "open": true, + "released": "2025-07-28", "tiers": [ { "cost": [ @@ -90778,7 +118100,10 @@ 0.0, 0.0 ], - "limit": 131072 + "knowledge": "2025-04", + "limit": 131072, + "max_output": 98304, + "released": "2025-07-28" }, "glm-4.5v": { "cost": [ @@ -90787,7 +118112,11 @@ 0.05976, 0.0 ], + "knowledge": "2025-04", "limit": 64000, + "max_output": 16384, + "open": true, + "released": "2025-08-11", "tiers": [ { "cost": [ @@ -90810,7 +118139,11 @@ 0.11, 0.0 ], - "limit": 204800 + "knowledge": "2025-04", + "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-09-30" }, "glm-4.6v": { "cost": [ @@ -90819,7 +118152,11 @@ 0.02988, 0.0 ], + "knowledge": "2025-04", "limit": 128000, + "max_output": 32768, + "open": true, + "released": "2025-12-08", "tiers": [ { "cost": [ @@ -90842,7 +118179,10 @@ 0.0, 0.0 ], - "limit": 128000 + "limit": 128000, + "max_output": 32768, + "open": true, + "released": "2025-12-08" }, "glm-4.7": { "cost": [ @@ -90851,7 +118191,11 @@ 0.08964, 0.0 ], + "knowledge": "2025-04", "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2025-12-22", "tiers": [ { "cost": [ @@ -90874,7 +118218,11 @@ 0.0, 0.0 ], - "limit": 200000 + "knowledge": "2025-04", + "limit": 200000, + "max_output": 131072, + "open": true, + "released": "2026-01-19" }, "glm-4.7-flashx": { "cost": [ @@ -90883,7 +118231,11 @@ 0.01494, 0.0 ], - "limit": 200000 + "knowledge": "2025-04", + "limit": 200000, + "max_output": 131072, + "open": true, + "released": "2026-01-19" }, "glm-5": { "cost": [ @@ -90893,6 +118245,9 @@ 0.0 ], "limit": 204800, + "max_output": 131072, + "open": true, + "released": "2026-02-12", "tiers": [ { "cost": [ @@ -90916,6 +118271,9 @@ 0.0 ], "limit": 200000, + "max_output": 131072, + "open": true, + "released": "2026-04-07", "tiers": [ { "cost": [ @@ -90938,7 +118296,10 @@ 0.29879, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-06-13" }, "glm-5.3": { "cost": [ @@ -90947,7 +118308,10 @@ 0.29879, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "glm-5.3-flash": { "cost": [ @@ -90956,7 +118320,10 @@ 0.03436, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-26" }, "glm-5.3-flashx": { "cost": [ @@ -90965,7 +118332,10 @@ 0.08516, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-09-18" }, "glm-5v-turbo": { "cost": [ @@ -90975,6 +118345,8 @@ 0.0 ], "limit": 200000, + "max_output": 131072, + "released": "2026-04-01", "tiers": [ { "cost": [ @@ -91002,7 +118374,11 @@ 0.0, 0.0 ], + "knowledge": "2025-04", "limit": 128000, + "max_output": 32768, + "open": true, + "released": "2025-12-08", "status": "deprecated" }, "glm-5.3": { @@ -91012,7 +118388,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-14" }, "glm-5.3-flash": { "cost": [ @@ -91021,7 +118400,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-26" }, "glm-5.3-highspeed": { "cost": [ @@ -91030,7 +118412,10 @@ 0.0, 0.0 ], - "limit": 1000000 + "limit": 1000000, + "max_output": 131072, + "open": true, + "released": "2026-08-14" } }, "name": "Zhipu AI Coding Plan" From b8391e7c32a7ae0200bc3d89f245aeb956a3d003 Mon Sep 17 00:00:00 2001 From: Mohamed Hamidi Date: Wed, 28 Oct 2026 21:33:32 +0100 Subject: [PATCH 2/4] feat(pricing): show context tiers, model cards and reasoning rates in P --- docs/backends.md | 8 ++ docs/pricing.md | 33 ++++- docs/programmatic.md | 6 + src/opentab/__init__.py | 3 + src/opentab/accounting/pricing.py | 209 +++++++++++++++++++++++++----- src/opentab/accounting/tiers.py | 56 ++++++-- src/opentab/api/service.py | 30 +++++ src/opentab/tui/app.py | 131 +++++++++++++++++-- src/opentab/tui/renderer.py | 37 +++++- src/opentab/tui/views/prices.py | 112 +++++++++++++++- src/opentab/web/page.py | 79 +++++++++-- src/opentab/web/report.py | 71 ++++++++-- tests/_support.py | 78 +++++++++++ tests/test_pricing.py | 92 +++++++++++++ tests/test_service.py | 8 ++ tests/test_tui_prices.py | 88 ++++++++++++- tests/test_tui_views_prices.py | 75 +++++++++++ tests/test_web.py | 30 +++-- 18 files changed, 1040 insertions(+), 106 deletions(-) diff --git a/docs/backends.md b/docs/backends.md index 3b39435..fd0b773 100644 --- a/docs/backends.md +++ b/docs/backends.md @@ -629,6 +629,14 @@ rankings and cache-penalty analysis substitute the input rate for a missing cach rate so absent metadata cannot make a model look free; API-equivalent totals and token economics keep the catalog's zero rate and flag it. +Snapshot rows keep card facts beside the rates (`CARD_INFO_KEYS`): a `reasoning` rate +only where it differs from output (tiers carry their own), release date, knowledge +cutoff, maximum output, open weights, and `type` only for non-chat models. +`reasoning_price()` follows the same card selection as `model_price()`, so per-request +costs, token economics and `w` (both frontends) bill reasoning at it; a tier without its +own reasoning rate uses the tier's output. `model_card_info()` and `catalog_card()` +expose the facts for `P` and the programmatic model listings. + Explicit context-tier tables win over legacy `context_over_200k`, which alone implies a 200,000-token boundary. Numeric request-context buckets, not dollars, survive rollups, warm caches and machine exports, so a rate refresh reprices without rereading diff --git a/docs/pricing.md b/docs/pricing.md index f1d7274..6f3ab98 100644 --- a/docs/pricing.md +++ b/docs/pricing.md @@ -80,7 +80,8 @@ session's recorded tokens cost if one model had produced them all? | `Enter` | Select the target | Your used models are ranked by token usage. Catalog models are ranked by effective -price at your overall token mix. If none of your models has a price, the catalog opens +price at your overall token mix; embedding, image, speech and other non-chat models +are left out. If none of your models has a price, the catalog opens directly. `w` works in demo mode and is never remembered between runs. Where it shows: @@ -109,7 +110,7 @@ tokens while output accounts for most of the price. |------|-----------| | Uncached input | Input rate | | Output | Output rate | -| Reasoning | Output rate; counted separately only when the harness records it apart from output | +| Reasoning | Output rate, or the card's own reasoning rate where models.dev publishes one (some Qwen and DeepSeek routes); counted separately only when the harness records it apart from output | | Cache read | Cache-read rate | | Cache write | Cache-write rate ([lifetimes](#cache-write-lifetimes)) | @@ -141,7 +142,9 @@ and marked `~` with an explanation in Token economics. That happens for summary- records, older exports, Codex deltas that span several requests, and VS Code chat. CSV/JSONL producers can supply `context_tokens` to avoid it. -The `P` table shows **base rates**; tiers apply per request, not to monthly totals. +The `P` table shows **base rates** with a `↑272k` tag on rows whose rates rise; tiers +apply per request, not to monthly totals. `Enter` on a row lists each tier's rates and +how much of your list cost ran at them ([model card](#the-model-card)). ### Cache-write lifetimes @@ -206,7 +209,24 @@ Press `p` (or `h` / `l`, or click a tab) to switch: In the models.dev view the same model repeats across gateways on purpose: resale markups are the point. Your models keep their use bar on every route that sells them. -Free and local models are left out, and a tag marks alpha, beta and deprecated models. +Free and local models are left out, and a tag marks alpha, beta and deprecated models +and non-chat ones such as `embedding`. In every view, `↑272k` marks rates that rise +above that request context. + +### The model card + +`Enter` opens a row's sessions under a card with what models.dev knows about it: + +| Line | Shows | +|------|-------| +| **List rates** | The row's rates, plus a reasoning rate where the card publishes one that differs from output | +| **Above 272k** | Each context tier's rates; a request over the threshold bills whole at them | +| **Your use** | The share of your list cost that ran at long-context rates, and the share whose request size is unknown, which is priced at base | +| **Model** | Release date, knowledge cutoff, context window, maximum output, open weights, model type | +| **Cheapest route** | For open-weight models, a provider selling the same model at least 5% cheaper at your mix. Free cards, local servers and subscription routes such as Copilot don't count, and hosts can differ in quantization and limits. Closed models get no such line: a far cheaper route for one is grey-market resale | + +Lines without data are left out. Your use follows the table's scope: all time, the +current identity filters, ignored sessions per `I`. ### Keys @@ -214,7 +234,7 @@ Free and local models are left out, and a tag marks alpha, beta and deprecated m |-----|--------| | `j` / `k` | Select a row | | `Space` | Pin the row to a ★ shortlist shown first in every view; pinning a catalog row pins only that route. Remembered between runs | -| `Enter` | Show the sessions that used the model, across routes and spellings | +| `Enter` | Show the model card and the sessions that used the model, across routes and spellings | | `s` (or click a header) | Sort by model, eff, use or a rate | | `~` (or click the header again) | Reverse the sort | | `f` | Filter by model, vendor or route; matches word starts, so `opus48` and `snt45` work | @@ -222,6 +242,9 @@ Free and local models are left out, and a tag marks alpha, beta and deprecated m | `p` / `h` / `l` | Switch views | The web browser has the same table on `P`, with clickable ☆/★ pins saved in the browser. +Click a row to expand its model card. In the models.dev view the browser's card has +rates, tiers and type only, because the facts for thousands of catalog rows would bloat +every report. ## Refreshing rates diff --git a/docs/programmatic.md b/docs/programmatic.md index 3981b74..f36db30 100644 --- a/docs/programmatic.md +++ b/docs/programmatic.md @@ -69,6 +69,12 @@ For `models list`, `--search` matches model names. With `--catalog` it browses t price list without opening sessions, and only `--search`, `--limit`, `--offset`, `--no-state` and `--pretty` apply. +Each model row carries its `*_usd_per_mtok` rates, including `reasoning_usd_per_mtok` +(the output rate unless the card publishes its own), and models.dev's card facts: +`context_tiers` (rates above `above_context_tokens`, per request), `release_date`, +`knowledge_cutoff`, `max_output_tokens`, `open_weights` and `model_type`. Facts the +catalog lacks are `null`; `model_type` is `null` only for a model with no catalog card. + ### Dates select whole sessions A range selects sessions by the day their **root session started**, and each one diff --git a/src/opentab/__init__.py b/src/opentab/__init__.py index 80a1746..f88414f 100644 --- a/src/opentab/__init__.py +++ b/src/opentab/__init__.py @@ -66,6 +66,7 @@ "cache_ttl_seconds", "cache_write_1h_price", "canonical_model", + "catalog_card", "catalog_models", "display_model", "effective_price", @@ -75,12 +76,14 @@ "is_local_provider", "model_context_window", "model_family", + "model_card_info", "model_matches", "model_price", "price_cache_meta", "price_cache_path", "price_source_meta", "prune_models_dev", + "reasoning_price", "refresh_model_prices", ), ), diff --git a/src/opentab/accounting/pricing.py b/src/opentab/accounting/pricing.py index 9724ee9..b4733fd 100644 --- a/src/opentab/accounting/pricing.py +++ b/src/opentab/accounting/pricing.py @@ -214,10 +214,14 @@ def effective_price( # Both layers share one on-disk schema, {"source", "fetched_at", "providers": -# {pid: {"name", "models": {mid: {"cost": [in, out, cr, cw], "status"?, -# "limit"?}}}}}. Only explicit refreshes write the cache; normal runs stay offline. +# {pid: {"name", "models": {mid: {"cost": [in, out, cr, cw], "status"?, "limit"?, +# "tiers"?, **CARD_INFO_KEYS?}}}}}. Only explicit refreshes write the cache; normal +# runs stay offline. MODELS_DEV_URL = "https://models.dev/api.json" _MODEL_STATUSES = ("alpha", "beta", "deprecated") +# Card facts kept beside the rates. "reasoning" is a rate, present only where it differs +# from output; "type" only for non-chat models; "open" only when the weights are open. +CARD_INFO_KEYS = ("reasoning", "released", "knowledge", "max_output", "open", "type") # Parsed layer: prices, context limits, provider tree, metadata, vendor-route flags. _BUNDLED: tuple[dict, dict, dict, dict | None] | None = None _PRICE_CACHE: tuple[dict, dict, dict, dict | None] | None = None @@ -251,9 +255,63 @@ def _catalog_entry(cost: dict, m: dict) -> dict | None: ctx = limit.get("context") if isinstance(limit, dict) else None if isinstance(ctx, (int, float)) and ctx > 0: entry["limit"] = int(ctx) + out_limit = limit.get("output") if isinstance(limit, dict) else None + entry.update( + _card_info( + { + "reasoning": _reasoning_rate(cost), + "released": m.get("release_date"), + "knowledge": m.get("knowledge"), + "max_output": out_limit, + "open": m.get("open_weights"), + "type": m.get("type"), + } + ) + ) return entry +def _rate(value) -> float | None: + if isinstance(value, bool) or not isinstance(value, (int, float)): + return None + return float(value) if math.isfinite(value) and value >= 0 else None + + +def _reasoning_rate(cost: dict) -> float | None: + """A published reasoning rate, kept only where it actually differs from output.""" + rate, out = _rate(cost.get("reasoning")), _rate(cost.get("output")) + return rate if rate is not None and rate != out else None + + +_ISO_DATE = re.compile(r"^\d{4}-\d{2}(?:-\d{2})?$") + + +def _card_info(raw: dict) -> dict: + """Validate card facts from either a models.dev model or a snapshot row.""" + info: dict = {} + rate = _rate(raw.get("reasoning")) + if rate is not None: + info["reasoning"] = rate + for key in ("released", "knowledge"): + value = raw.get(key) + if isinstance(value, str) and _ISO_DATE.match(value): + info[key] = value + out = raw.get("max_output") + if ( + isinstance(out, (int, float)) + and not isinstance(out, bool) + and math.isfinite(out) + and out > 0 + ): + info["max_output"] = int(out) + if raw.get("open") is True: + info["open"] = True + kind = raw.get("type") + if isinstance(kind, str) and kind and kind != "chat": + info["type"] = kind + return info + + def _context_tiers(cost: dict) -> list[dict]: """Normalize context thresholds, preferring explicit tiers over the legacy field.""" tiers = {} @@ -290,13 +348,18 @@ def _context_tiers(cost: dict) -> list[dict]: for v in values ): continue - tiers.setdefault(int(size), [float(v) for v in values]) + # A tier without its own reasoning rate bills reasoning at the tier's output. + reasoning = _rate(item.get("reasoning")) + row = {"cost": [float(v) for v in values]} + if reasoning is not None and reasoning != row["cost"][1]: + row["reasoning"] = reasoning + tiers.setdefault(int(size), row) # Legacy metadata has a literal 200k boundary. Never insert that boundary when # an explicit table supplies a different one (e.g. OpenAI's 272k threshold). legacy = cost.get("context_over_200k") if not tiers and isinstance(legacy, dict): tiers = { - t["tier"]["size"]: t["cost"] + t["tier"]["size"]: {k: v for k, v in t.items() if k != "tier"} for t in _context_tiers( { **cost, @@ -306,8 +369,7 @@ def _context_tiers(cost: dict) -> list[dict]: ) } return [ - {"tier": {"type": "context", "size": size}, "cost": values} - for size, values in sorted(tiers.items()) + {"tier": {"type": "context", "size": size}, **row} for size, row in sorted(tiers.items()) ] @@ -372,11 +434,12 @@ def prune_models_dev(data: dict) -> dict: class _Prices(dict): - """Resolved rate cards and their matching tiers, indexed together once per layer.""" + """Resolved rate cards, their tiers and card facts, indexed together once per layer.""" def __init__(self): super().__init__() self.tiers = {} + self.info = {} def _parse_catalog(data) -> tuple[dict, dict, dict, dict | None, dict]: @@ -412,6 +475,8 @@ def _parse_catalog(data) -> tuple[dict, dict, dict, dict | None, dict]: limit = m.get("limit") if isinstance(limit, (int, float)) and limit > 0: entry["limit"] = int(limit) + info = _card_info(m) + entry.update(info) kept[str(mid)] = entry bare = str(mid).rsplit("/", 1)[-1].lower() # Subscription-only zero cards must not shadow published metered rates. @@ -420,6 +485,7 @@ def _parse_catalog(data) -> tuple[dict, dict, dict, dict | None, dict]: if bare not in rank or score > rank[bare]: prices[bare], rank[bare] = row, score prices.tiers[bare] = entry.get("tiers", []) + prices.info[bare] = info if "limit" in entry: limits[bare] = entry["limit"] else: @@ -470,11 +536,9 @@ def _layer_shaped(layer) -> bool: # A decodable payload can still be the wrong structure; never adopt one. return ( isinstance(layer, tuple) - and len(layer) == 6 - and isinstance(layer[0], dict) - and isinstance(layer[1], dict) - and all(isinstance(layer[i], dict) for i in (2, 3, 5)) - and (layer[4] is None or isinstance(layer[4], dict)) + and len(layer) == 7 + and all(isinstance(layer[i], dict) for i in (0, 1, 2, 3, 4, 6)) + and (layer[5] is None or isinstance(layer[5], dict)) ) @@ -517,15 +581,22 @@ def _parse_catalog_bytes(raw: bytes, kind: str) -> tuple: if _layer_shaped(layer): out = _Prices() out.update(layer[0]) - out.tiers = layer[1] - return (out, *layer[2:]) + out.tiers, out.info = layer[1], layer[2] + return (out, *layer[3:]) except (OSError, EOFError, ValueError, TypeError): pass parsed = _parse_catalog(_decode_catalog(raw)) tmp = None try: os.makedirs(folder, exist_ok=True) - payload = marshal.dumps((dict(parsed[0]), getattr(parsed[0], "tiers", {}), *parsed[1:])) + payload = marshal.dumps( + ( + dict(parsed[0]), + getattr(parsed[0], "tiers", {}), + getattr(parsed[0], "info", {}), + *parsed[1:], + ) + ) fd, tmp = tempfile.mkstemp(prefix="catalog.", dir=folder) with os.fdopen(fd, "wb") as fh: fh.write(hashlib.sha1(payload).digest() + payload) @@ -603,9 +674,46 @@ def catalog_models() -> list[tuple[str, str, tuple[float, float, float, float], return [] +# (provider tree, {(pid, mid): public card}): keyed on the tree object itself, so a +# refreshed or swapped layer can never serve another catalog's cards. +_CARD_INDEX: tuple | None = None + + +def catalog_card(provider: str, model: str) -> dict: + """Tiers and card facts of one provider route, from the layer catalog_models() lists. + + The returned dict is shared between callers; treat it as read-only. + """ + global _CARD_INDEX + for _prices, _limits, tree, _meta, _vendor in _layers(): + if tree: + if _CARD_INDEX is None or _CARD_INDEX[0] is not tree: + _CARD_INDEX = (tree, {}) + index = _CARD_INDEX[1] + key = (provider, model) + if key not in index: + card = tree.get(provider, {}).get("models", {}).get(model) + index[key] = _public_card(model, card) if card else {} + return index[key] + return {} + + +def _public_card(mid: str, card: dict) -> dict: + out = {k: card[k] for k in CARD_INFO_KEYS if k in card} + tiers = [ + (t["tier"]["size"], _with_openai_cache_write(mid, tuple(t["cost"])), t.get("reasoning")) + for t in card.get("tiers", []) + ] + if tiers: + out["tiers"] = tiers + if card.get("limit"): + out["context"] = card["limit"] + return out + + def invalidate_price_cache() -> None: - global _PRICE_CACHE, _BUNDLED - _PRICE_CACHE = _BUNDLED = None + global _PRICE_CACHE, _BUNDLED, _CARD_INDEX + _PRICE_CACHE = _BUNDLED = _CARD_INDEX = None model_tiers.cache_clear() @@ -721,18 +829,18 @@ def _vendor_spelling(mid: str, vendor: dict) -> str: return dashed if dashed != mid and vendor.get(dashed) and not vendor.get(mid) else mid -@lru_cache(maxsize=8192) -def model_tiers(name: str) -> tuple: - """Return the selected rate card's context tiers, with the same alias/route rules.""" +def _selected_card(name: str) -> tuple: + """(spelling, raw tiers, card facts) of the card model_price() resolves. + + Mirrors _base_model_price's alias and route rules; () tiers and {} facts mean the + model fell through to a family or generic guess. + """ if is_local_provider(name): - return () - name = _mode_price_name(name) + return name, (), {} card = _copilot_card(name) if card is not None: - return tuple( - (t["tier"]["size"], _with_openai_cache_write(name, tuple(t["cost"]))) - for t in card[0].get("tiers", []) - ) + row = card[0] + return name, tuple(row.get("tiers", [])), {k: row[k] for k in CARD_INFO_KEYS if k in row} spelled = _gpt_version_to_dots(str(name).rsplit("/", 1)[-1].lower()) for prices, _limits, _tree, _meta, vendor in _layers(): mid = _vendor_spelling(spelled, vendor) @@ -749,11 +857,44 @@ def model_tiers(name: str) -> tuple: selected, row = plain, alt if row is None: continue - return tuple( - (t["tier"]["size"], _with_openai_cache_write(mid, tuple(t["cost"]))) - for t in getattr(prices, "tiers", {}).get(selected, []) + return ( + mid, + tuple(getattr(prices, "tiers", {}).get(selected, [])), + dict(getattr(prices, "info", {}).get(selected, {})), ) - return () + return spelled, (), {} + + +@lru_cache(maxsize=8192) +def model_tiers(name: str) -> tuple: + """Return the selected rate card's context tiers, with the same alias/route rules.""" + mid, tiers, _info = _selected_card(_mode_price_name(name)) + return tuple( + (t["tier"]["size"], _with_openai_cache_write(mid, tuple(t["cost"]))) for t in tiers + ) + + +def reasoning_price(name: str, context_tokens: float | None = None) -> float: + """Reasoning tokens bill at output unless the selected card publishes its own rate. + + A context tier without its own reasoning rate bills reasoning at the tier's output. + """ + out = model_price(name, context_tokens)[1] + _mid, tiers, info = _selected_card(_mode_price_name(name)) + if context_tokens is not None: + for t in reversed(tiers): + if context_tokens > t["tier"]["size"]: + return float(t.get("reasoning", out)) + return float(info.get("reasoning", out)) + + +def model_card_info(name: str) -> dict: + """Card facts (CARD_INFO_KEYS) and context tiers of the card model_price() resolves. + + Tiers are (threshold, rates, reasoning rate or None); empty for guessed prices. + """ + mid, tiers, info = _selected_card(_mode_price_name(name)) + return _public_card(mid, {**info, "tiers": list(tiers)}) def _base_model_price(name: str) -> tuple[float, float, float, float]: @@ -829,7 +970,7 @@ def model_context_window(name: str) -> int: # Argument-order labels. Input is the uncached residual, disjoint from cache reads/writes; -# reasoning bills at output rates but remains visible as its own category. +# reasoning bills at output rates (or a card's own reasoning rate) as its own category. TOKEN_TYPES = ("Uncached input", "Output", "Reasoning", "Cache read", "Cache write") @@ -861,9 +1002,11 @@ def api_equivalent_cost( context_tokens: float | None = None, ) -> float: # ``cache_write_1h`` replaces the rate for a subset of total writes; it is not an - # additive sixth token type. Reasoning bills at the output rate. + # additive sixth token type. Reasoning bills at output unless the card says otherwise. ir, orr, crr, cwr = model_price(name, context_tokens) - cost = inp * ir + (out + reasoning) * orr + cache_read * crr + cost = inp * ir + out * orr + cache_read * crr + if reasoning: + cost += reasoning * reasoning_price(name, context_tokens) long = min(max(cache_write_1h, 0.0), cache_write) if long: cost += (cache_write - long) * cwr + long * cache_write_1h_price(name, context_tokens) diff --git a/src/opentab/accounting/tiers.py b/src/opentab/accounting/tiers.py index 6631934..e2d5c14 100644 --- a/src/opentab/accounting/tiers.py +++ b/src/opentab/accounting/tiers.py @@ -11,6 +11,7 @@ model_price, model_price_source, model_tiers, + reasoning_price, ) from opentab.util import model_row_1h_write, model_row_split @@ -302,9 +303,11 @@ def estimated_token_split(row: dict) -> tuple: return tuple(tokens) -def row_cost_parts(row: dict, model: str | None = None, prefix: str = "") -> tuple: - name = model if model is not None else str(row.get("model_name") or "") - cost = [0.0] * 5 +def _sample_costs(row: dict, name: str, prefix: str = ""): + """Yield (rate band, context, per-type list cost) for each priceable request bucket. + + The band is the tier threshold the request exceeded, or None at base rates. + """ # Thousands of request contexts usually share only one or two rate bands. # Resolve aliases/catalog cards once per used band, not once per request. # Keep this memo local so price refreshes cannot leave stale dollar estimates. @@ -316,22 +319,51 @@ def row_cost_parts(row: dict, model: str | None = None, prefix: str = "") -> tup continue band = next((size for size in thresholds if context is not None and context > size), None) if band not in rates: - rates[band] = model_price(name, context) - ir, out, cr, cw = rates[band] + rates[band] = (*model_price(name, context), reasoning_price(name, context)) + ir, out, cr, cw, rr = rates[band] long = min(max(tok[5], 0.0), tok[4]) if long and band not in long_rates: long_rates[band] = cache_write_1h_price(name, context) - values = ( - tok[0] * ir, - tok[1] * out, - tok[2] * out, - tok[3] * cr, - (tok[4] - long) * cw + (long * long_rates[band] if long else 0), + yield ( + band, + context, + ( + tok[0] * ir / 1e6, + tok[1] * out / 1e6, + tok[2] * rr / 1e6, + tok[3] * cr / 1e6, + ((tok[4] - long) * cw + (long * long_rates[band] if long else 0)) / 1e6, + ), ) - cost = [a + b / 1e6 for a, b in zip(cost, values)] + + +def row_cost_parts(row: dict, model: str | None = None, prefix: str = "") -> tuple: + name = model if model is not None else str(row.get("model_name") or "") + cost = [0.0] * 5 + for _band, _context, values in _sample_costs(row, name, prefix): + cost = [a + b for a, b in zip(cost, values)] return tuple(cost) +def row_tier_split(row: dict, model: str | None = None) -> tuple[float, float, float]: + """(list cost at long-context rates, total list cost, list cost of unknown context). + + Unknown-context buckets are priced at base rates like everywhere else; the third + value lets a caller say how much of the split is a lower bound. + """ + name = model if model is not None else str(row.get("model_name") or "") + tiered = total = unknown = 0.0 + has_tiers = bool(model_tiers(name)) + for band, context, values in _sample_costs(row, name): + cost = sum(values) + total += cost + if band is not None: + tiered += cost + elif context is None and has_tiers: + unknown += cost + return tiered, total, unknown + + def row_list_cost(row: dict, model: str | None = None, prefix: str = "") -> float: return sum(row_cost_parts(row, model, prefix)) diff --git a/src/opentab/api/service.py b/src/opentab/api/service.py index c8d60dd..f752519 100644 --- a/src/opentab/api/service.py +++ b/src/opentab/api/service.py @@ -11,13 +11,16 @@ from opentab.accounting.pricing import ( cache_write_1h_price, canonical_model, + catalog_card, catalog_models, has_known_price, is_copilot_model, is_local_provider, + model_card_info, model_context_window, model_price, price_source_meta, + reasoning_price, ) from opentab.accounting.tiers import ( node_api_cost, @@ -60,6 +63,28 @@ ) +def _card_fields(card: dict) -> dict: + """Context tiers and models.dev card facts; absent facts are None, never guessed.""" + return { + "context_tiers": [ + { + "above_context_tokens": size, + "input_usd_per_mtok": rates[0], + "output_usd_per_mtok": rates[1], + "cache_read_usd_per_mtok": rates[2], + "cache_write_usd_per_mtok": rates[3], + "reasoning_usd_per_mtok": rates[1] if rr is None else rr, + } + for size, rates, rr in card.get("tiers", ()) + ], + "release_date": card.get("released"), + "knowledge_cutoff": card.get("knowledge"), + "max_output_tokens": card.get("max_output"), + "open_weights": bool(card.get("open")), + "model_type": card.get("type", "chat") if card else None, + } + + class ServiceError(Exception): """A stable domain error suitable for CLI and MCP clients.""" @@ -1567,6 +1592,8 @@ def list_models( "cache_read_usd_per_mtok": price[2], "cache_write_usd_per_mtok": price[3], "cache_write_1h_usd_per_mtok": cache_write_1h_price(name), + "reasoning_usd_per_mtok": reasoning_price(name), + **_card_fields(model_card_info(name)), "pinned": name in pinned_models or canonical_model(name) in pinned_models, } ) @@ -1597,6 +1624,7 @@ def list_model_catalog( name = f"{provider}/{model}" if search and search.lower() not in name.lower(): continue + card = catalog_card(provider, model) rows.append( { "model": name, @@ -1605,6 +1633,8 @@ def list_model_catalog( "cache_read_usd_per_mtok": price[2], "cache_write_usd_per_mtok": price[3], "cache_write_1h_usd_per_mtok": cache_write_1h_price(name), + "reasoning_usd_per_mtok": card.get("reasoning", price[1]), + **_card_fields(card), "status": status, "pinned": name in pinned_models or canonical_model(name) in pinned_models, } diff --git a/src/opentab/tui/app.py b/src/opentab/tui/app.py index 9d34070..5f63037 100644 --- a/src/opentab/tui/app.py +++ b/src/opentab/tui/app.py @@ -26,6 +26,7 @@ row_cost_parts, row_estimate_reasons, row_list_cost, + row_tier_split, unknown_tier_context, ) from opentab.stores.opencode import Store @@ -52,6 +53,7 @@ LOCAL_PROVIDERS, TOKEN_TYPES, canonical_model, + catalog_card, catalog_models, display_model, effective_price, @@ -60,6 +62,7 @@ invalidate_price_cache, is_local_provider, is_vendor_route, + model_card_info, model_family, model_matches, model_price, @@ -226,6 +229,14 @@ class PriceEntry(NamedTuple): approx: bool status: str = "" pinned: bool = False + # pricing.model_card_info()/catalog_card() of the displayed rates: tiers and facts. + card: dict | None = None + + +# models.dev types that cannot stand in for a chat model in a `w` comparison. +NON_CHAT_TYPES = frozenset( + {"embedding", "image", "video", "speech", "transcription", "reranking", "realtime"} +) class BrowseMode(NamedTuple): @@ -400,6 +411,13 @@ def __init__( # Defer the corpus-wide model scan until after the fast first frame. self._model_by_root: dict[str, list[dict]] = defaultdict(list) self._model_economics_cache: dict[int, tuple] = {} + # Per-row long-context split and the cheapest route per canonical model, both + # list-price projections dropped with the economics memo on reload/refresh. + self._tier_split_cache: dict[int, tuple] = {} + self._cheapest_routes: tuple | None = None + # (UI-state key, entries) for the P table: the models.dev view rebuilds ~7k + # rows, too slow to redo on every keypress and paint while j is held. + self._price_entries_memo: tuple | None = None self._models_loaded = False self._tool_by_session: dict[str, list[dict]] = {} self._turns_by_session: dict[str, list[dict]] = {} @@ -591,6 +609,8 @@ def __init__( # Pins are route-scoped so one gateway never pins every reseller of a model. self.pinned_models: set[str] = set() self.prices_model: str | None = None + # The row Enter drilled into: its route and rate card head the drill-in. + self.prices_entry: PriceEntry | None = None self.prices_sort = "eff" self.prices_sort_reverse = False self.prices_view = "flat" @@ -1663,6 +1683,9 @@ def restore_selection(self, anchor: SelectionAnchor) -> None: @debug.timed("app.load_models") def _load_model_cache(self) -> None: self._model_economics_cache.clear() + self._tier_split_cache.clear() + self._cheapest_routes = None + self._price_entries_memo = None self._model_by_root: dict[str, list[dict]] = defaultdict(list) with debug.span("app.fetch_models") as info: rows = self.store.model_breakdown() @@ -3466,6 +3489,8 @@ def whatif_catalog_candidates(self) -> list[tuple[str, float, bool]]: for pid, mid, price, _status in catalog_models(): if pid.lower() in LOCAL_PROVIDERS or (price[0] <= 0 and price[1] <= 0): continue + if catalog_card(pid, mid).get("type") in NON_CHAT_TYPES: + continue bare = mid.rsplit("/", 1)[-1].lower() rank = ( is_vendor_route(pid, bare), @@ -3908,6 +3933,9 @@ def poll_price_refresh(self) -> None: tool_key = (selected["kind"], selected["name"]) if selected else None invalidate_price_cache() self._model_economics_cache.clear() + self._tier_split_cache.clear() + self._cheapest_routes = None + self._price_entries_memo = None self.renderer._turn_layout_cache = None self.renderer._trace_layout_cache = None self._whatif_catalog_rows = None @@ -4670,18 +4698,42 @@ def price_token_mix(self) -> tuple[tuple[float, float, float, float], int] | Non return self._token_mix(self._priced_model_roots()) @staticmethod - def _best_alias_price(aliases: dict[str, float]) -> tuple[float, float, float, float]: + def _best_alias_price(aliases: dict[str, float]) -> tuple[tuple, str]: # Prefer the most complete alias rate card; break ties by observed usage. - best, best_key = (0.0, 0.0, 0.0, 0.0), (-1, -1.0) + best, best_name, best_key = (0.0, 0.0, 0.0, 0.0), "", (-1, -1.0) for alias, tok in aliases.items(): - for candidate in {alias, display_model(alias)}: + for candidate in sorted({alias, display_model(alias)}): p = model_price(candidate) key = (sum(1 for v in p if v > 0), tok) if key > best_key: - best, best_key = tuple(p), key - return best + best, best_name, best_key = tuple(p), candidate, key + return best, best_name def priced_model_entries(self) -> list[PriceEntry]: + # Memoized on every input the rows read; model rows and rates drop the memo + # where they are rebuilt (_load_model_cache, the rate refresh). + key = ( + self.prices_view, + self.query, + self.prices_sort, + self.prices_sort_reverse, + frozenset(self.pinned_models), + self.show_api_prices, + None if self.machine_filter is None else frozenset(self.machine_filter), + None if self.harness_filter is None else frozenset(self.harness_filter), + self.show_ignored_projects, + frozenset(self.ignored_sessions), + frozenset(self.ignored_projects), + len(self.loaded), + ) + # Held by reference, not id(): a replaced list's id can be reused. + rows, loaded = self._model_by_root, self.loaded + memo = self._price_entries_memo + if memo is None or memo[0] != key or memo[1] is not rows or memo[2] is not loaded: + memo = self._price_entries_memo = (key, rows, loaded, self._build_price_entries()) + return list(memo[3]) + + def _build_price_entries(self) -> list[PriceEntry]: # Flat/family views canonicalize aliases; provider view retains gateway pricing. # Local models have no API rate and remain outside this list-price reference. mix = self.price_token_mix() @@ -4712,7 +4764,7 @@ def priced_model_entries(self) -> list[PriceEntry]: d["aliases"][bare] += tok entries = [] for (route, canon), d in raw.items(): - price = self._best_alias_price(d["aliases"]) + price, priced_as = self._best_alias_price(d["aliases"]) eff, approx = effective_price(price, shares) routes_t = tuple(sorted(d["routes"])) entries.append( @@ -4732,6 +4784,7 @@ def priced_model_entries(self) -> list[PriceEntry]: eff=eff, approx=approx, pinned=self._is_pinned(canon, routes_t), + card=model_card_info(priced_as), ) ) return self._order_price_entries(self._filter_price_entries(entries)) @@ -4770,9 +4823,9 @@ def _catalog_price_entries(self, shares: tuple) -> list[PriceEntry]: key = (sum(1 for v in price if v > 0), -len(mid)) cur = best.get((pid, canon)) if cur is None or key > cur[0]: - best[(pid, canon)] = (key, bare, canon, pid, price, status) + best[(pid, canon)] = (key, bare, canon, pid, price, status, mid) entries = [] - for _key, bare, canon, pid, price, status in best.values(): + for _key, bare, canon, pid, price, status, mid in best.values(): u = usage.get(canon) eff, approx = effective_price(price, shares) entries.append( @@ -4789,10 +4842,65 @@ def _catalog_price_entries(self, shares: tuple) -> list[PriceEntry]: approx=approx, status=status, pinned=self._is_pinned(canon, (pid,)), + card=catalog_card(pid, mid), ) ) return entries + def price_tier_exposure(self, canon: str, route: str | None = None) -> tuple | None: + """(long-context list cost, total list cost, unknown-context list cost) or None. + + Scope matches the price table: all time, identity filters, local models excluded. + A route restricts to that access route (the provider view). Per-row splits are + memoized like model_row_economics and dropped on reload or a rate refresh. + """ + tiered = total = unknown = 0.0 + for rows in self._priced_model_roots().values(): + for m in rows: + name = str(m.get("model_name") or "") + if is_local_provider(name) or canonical_model(name.rsplit("/", 1)[-1]) != canon: + continue + if route is not None and (name.rsplit("/", 1)[0] if "/" in name else "") != route: + continue + cached = self._tier_split_cache.get(id(m)) + if cached is None or cached[0] is not m: + cached = (m, row_tier_split(m)) + self._tier_split_cache[id(m)] = cached + t, a, u = cached[1] + tiered, total, unknown = tiered + t, total + a, unknown + u + return (tiered, total, unknown) if total > 0 else None + + def price_cheapest_route(self, entry: PriceEntry) -> tuple[str, float, bool] | None: + """(provider, eff $/M, approx) of the cheapest metered route for an open model. + + Ranked at the same token mix as eff $/M. Free (zero-rate) cards, local servers + and subscription routes such as Copilot are not purchasable per token. Closed + weights are sold legitimately only by their vendor and its clouds, so a far + cheaper "route" for one is grey-market resale, not advice: open weights only. + """ + if not (entry.card or {}).get("open"): + return None + canon = entry.canon + mix = self.price_token_mix() + shares = mix[0] if mix else (1.0, 0.0, 0.0, 0.0) + if self._cheapest_routes is None or self._cheapest_routes[0] != shares: + best: dict[str, tuple[float, str, bool]] = {} + for pid, mid, price, _status in catalog_models(): + if ( + pid.lower() in LOCAL_PROVIDERS + or pid == "github-copilot" + or price[0] <= 0 + or price[1] <= 0 + ): + continue + key = canonical_model(display_model(mid.rsplit("/", 1)[-1])) + eff, approx = effective_price(price, shares) + if key not in best or (eff, pid) < best[key][:2]: + best[key] = (eff, pid, approx) + self._cheapest_routes = (shares, best) + hit = self._cheapest_routes[1].get(canon) + return (hit[1], hit[0], hit[2]) if hit else None + def _order_price_entries(self, entries: list[PriceEntry]) -> list[PriceEntry]: # Pins always float; grouped views rank groups by spend with Other last. pinned = self._sort_price_entries([e for e in entries if e.pinned]) @@ -8748,9 +8856,10 @@ def _handle_price_models_key(self, key: int | str, stdscr: curses.window | None elif act == "bottom": self.prices_index = max(0, n - 1) elif act == "select": - names = self.priced_model_names() - if names: - self.prices_model = names[max(0, min(self.prices_index, len(names) - 1))] + entries = self.priced_model_entries() + if entries: + self.prices_entry = entries[max(0, min(self.prices_index, len(entries) - 1))] + self.prices_model = self.prices_entry.bare self.prices_scroll = 0 elif act == "refresh": self.refresh_prices_action() # keeps the overlay open diff --git a/src/opentab/tui/renderer.py b/src/opentab/tui/renderer.py index f0ae7a3..5f284e0 100644 --- a/src/opentab/tui/renderer.py +++ b/src/opentab/tui/renderer.py @@ -164,6 +164,7 @@ model_context_window, model_price, price_source_meta, + reasoning_price, ) from opentab.presentation.formatting import ( BAR_CELLS, @@ -3720,7 +3721,8 @@ def _price_split_dollars( ir, orr, crr, cwr = model_price(name) if inp is None: inp = max(0, tok - cr - cw - out - reasoning) - raw = (inp * ir, cr * crr, cw * cwr, out * orr, reasoning * orr) + rr = reasoning_price(name) if reasoning else orr + raw = (inp * ir, cr * crr, cw * cwr, out * orr, reasoning * rr) total = sum(raw) scale = cost / total if cost > 0 and total > 0 else 0.0 return tuple(value * scale for value in raw) @@ -5663,7 +5665,22 @@ def draw_prices(self, stdscr: curses.window, y: int, bottom: int, width: int) -> stdscr, list_top, width - 1, layout.total_rows, visible, layout.scroll ) + def price_card_lines(self) -> list[str]: + """The drilled row's model card, or nothing when the drill came from elsewhere.""" + entry = self.app.prices_entry + if entry is None or entry.bare != self.app.prices_model: + return [] + tiers = (entry.card or {}).get("tiers") + route = entry.group if self.app.prices_view == "provider" else None + return price_view.card_lines( + entry, + context_window=model_context_window(entry.bare), + exposure=self.app.price_tier_exposure(entry.canon, route) if tiers else None, + cheapest=self.app.price_cheapest_route(entry), + ) + def price_session_lines(self, model: str, width: int) -> list[str]: + card = self.price_card_lines() rows = [ price_view.PriceSessionEntry( workflow.created_at, @@ -5673,7 +5690,8 @@ def price_session_lines(self, model: str, width: int) -> list[str]: ) for workflow, cost, tokens in self.price_model_sessions(model) ] - return price_view.session_lines(rows, model, self.src_col()) + body = price_view.session_lines(rows, model, self.src_col()) + return [*card, "", *body] if card else body def draw_price_sessions(self, stdscr: curses.window, y: int, bottom: int, width: int) -> None: # The P overlay's per-model drill-in (Enter on a model). The subtotal + @@ -5697,6 +5715,21 @@ def draw_price_sessions(self, stdscr: curses.window, y: int, bottom: int, width: self.write(stdscr, y + 1, width - len(hint) - 2, hint, curses.color_pair(4)) inner_w = width - 4 top = y + 2 + card = self.price_card_lines() + if card and bottom - top > len(card) + 4: + label_w = price_view.CARD_LABEL_W + for offset, line in enumerate(card): + label, rest = line[:label_w], line[label_w:] + self.write( + stdscr, + top + offset, + 2, + shorten(label, inner_w), + curses.color_pair(1) | curses.A_DIM, + ) + if inner_w > label_w: + self.write(stdscr, top + offset, 2 + label_w, shorten(rest, inner_w - label_w)) + top += len(card) + 1 rows = [ price_view.PriceSessionEntry( workflow.created_at, diff --git a/src/opentab/tui/views/prices.py b/src/opentab/tui/views/prices.py index 6fd284e..151d45f 100644 --- a/src/opentab/tui/views/prices.py +++ b/src/opentab/tui/views/prices.py @@ -24,7 +24,15 @@ PRICE_USE_BAR = 5 PRICE_USE_W = PRICE_USE_BAR + 4 PRICE_BLOCK_W = PRICE_EFF_W + 2 + PRICE_USE_W + 2 + PRICE_COL_W * 4 + 3 +# Room kept for the route/tier tag once names have PRICE_NAME_KEEP_W: one long +# catalog name must not push every tag offscreen. +PRICE_TAG_MIN_W = 20 +PRICE_NAME_KEEP_W = 28 ROUTE_ABBR = {"github-copilot": "copilot"} +# Resale cards round differently; name a cheaper route only past this margin. +CHEAPER_ROUTE_MARGIN = 0.05 +# Model-card label column: the longest label ("Cheapest route") plus two spaces. +CARD_LABEL_W = 16 class PriceSpan(NamedTuple): @@ -94,9 +102,23 @@ def intro_lines( f"{cache_write:.1%} cacheW" ) parts.append("~ = no cacheR rate") + parts.append("↑ = dearer above that context") return (" · ".join(parts), "") +def context_label(size: int) -> str: + """Compact context threshold: 272k, 1M, 1.5M.""" + if size >= 1_000_000: + return f"{size / 1_000_000:.3g}M" + return f"{size / 1000:.3g}k" + + +def tier_tag(entry) -> str: + """The lowest context threshold that raises this row's rates, as ↑272k.""" + tiers = (getattr(entry, "card", None) or {}).get("tiers") or () + return f"↑{context_label(tiers[0][0])}" if tiers else "" + + def route_tag(routes: Iterable[str]) -> str: seen: list[str] = [] for route in routes: @@ -170,7 +192,8 @@ def name_width(entries: Sequence, width: int) -> int: widest = max( len(entry.bare) + (2 if getattr(entry, "pinned", False) else 0) for entry in entries ) - return min(widest, max(12, width - PRICE_BLOCK_W - 3)) + room = width - PRICE_BLOCK_W - 3 + return min(widest, max(12, room - PRICE_TAG_MIN_W, min(room, PRICE_NAME_KEEP_W))) def use_peak(entries: Sequence) -> float: @@ -206,12 +229,87 @@ def group_label(group: str, view: str) -> str: def entry_tag(entry, view: str) -> str: if view == "provider": - return family_label(entry.family) - tag = route_tag(entry.routes) - status = getattr(entry, "status", "") - if status and view == "all": - tag = f"{tag}·{status}" if tag else status - return tag + parts = [family_label(entry.family)] + else: + parts = [route_tag(entry.routes)] + status = getattr(entry, "status", "") + if status and view == "all": + parts.append(status) + kind = (getattr(entry, "card", None) or {}).get("type") + if kind and view == "all": + parts.append(kind) + parts.append(tier_tag(entry)) + return "·".join(part for part in parts if part) + + +def _rates_text(rates: Sequence[float], reasoning: float | None) -> str: + input_rate, output_rate, cache_read, cache_write = rates + cache_read_text = "—" if cache_read <= 0 < input_rate else f"{cache_read:.2f}" + text = ( + f"in {input_rate:.2f} · out {output_rate:.2f} · cacheR {cache_read_text} · " + f"cacheW {cache_write:.2f}" + ) + if reasoning is not None and reasoning != output_rate: + text += f" · reasoning {reasoning:.2f}" + return text + + +def card_lines( + entry, + *, + context_window: int | None = None, + exposure: tuple[float, float, float] | None = None, + cheapest: tuple[str, float, bool] | None = None, +) -> list[str]: + """The drill-in's model card: rates, context tiers, your tier exposure, facts. + + ``exposure`` is (long-context list cost, total list cost, unknown-context list + cost); ``cheapest`` is (provider, eff $/M, approx) at the same mix as eff $/M. + """ + card = getattr(entry, "card", None) or {} + label = CARD_LABEL_W + lines = [f"{'List rates':<{label}}{_rates_text(entry.price, card.get('reasoning'))} $/M"] + tiers = card.get("tiers") or () + for size, rates, reasoning in tiers: + lines.append(f"{'Above ' + context_label(size):<{label}}{_rates_text(rates, reasoning)}") + if tiers: + lines.append(f"{'':<{label}}a request over the threshold bills whole at the higher rates") + elif card: + lines.append(f"{'Long context':<{label}}no surcharge: the same rates at any request size") + if tiers and exposure is not None: + tiered, total, unknown = exposure + if unknown >= total: + text = "request sizes unknown, so all of it is priced at base rates (~)" + else: + text = f"{tiered / total:.0%} of your list cost ran at long-context rates" + if unknown > 0: + text += f" · {unknown / total:.0%} lacks request size, priced at base (~)" + lines.append(f"{'Your use':<{label}}{text}") + facts = [] + if card.get("released"): + facts.append(f"released {card['released']}") + if card.get("knowledge"): + facts.append(f"knowledge {card['knowledge'][:7]}") + window = card.get("context") or context_window + if window: + facts.append(f"{context_label(window)} context") + if card.get("max_output"): + facts.append(f"{context_label(card['max_output'])} max output") + if card.get("open"): + facts.append("open weights") + if card.get("type"): + facts.append(f"{card['type']} model") + if facts: + lines.append(f"{'Model':<{label}}{' · '.join(facts)}") + if cheapest is not None and entry.eff > 0: + route, eff, approx = cheapest + own = set(entry.routes) + if route not in own and eff < entry.eff * (1 - CHEAPER_ROUTE_MARGIN): + lines.append( + f"{'Cheapest route':<{label}}{route} {'~' if approx else ''}{eff:.2f} eff $/M, " + f"{1 - eff / entry.eff:.0%} below this row at your mix" + ) + return lines def empty_message(query: str, view: str) -> str: diff --git a/src/opentab/web/page.py b/src/opentab/web/page.py index 5e5a349..c1e7422 100644 --- a/src/opentab/web/page.py +++ b/src/opentab/web/page.py @@ -390,6 +390,12 @@ table.prices td.l{text-align:left;white-space:normal;overflow-wrap:anywhere} table.prices tr:last-child td{border-bottom:0} table.prices tr.grp td{color:var(--accent);font-weight:600;padding-top:9px;border-bottom:0} +table.prices tr.pr-row{cursor:pointer} +table.prices tr.pr-row:hover td,table.prices tr.pr-row.open td{background:var(--line2)} +table.prices tr.pr-card td{text-align:left;white-space:normal;padding:6px 9px 10px 32px} +table.prices tr.pr-card dl{display:grid;grid-template-columns:max-content 1fr;gap:3px 14px;margin:0;font-size:12px} +table.prices tr.pr-card dt{color:var(--mut)} +table.prices tr.pr-card dd{margin:0;color:var(--ink2)} table.prices .tag{color:var(--mut);font-size:11px;margin-left:7px} .pr-use{display:inline-flex;align-items:center;gap:6px;justify-content:flex-end} .pr-use .hb{position:relative;width:64px;height:8px;background:var(--line2);border-radius:2px;overflow:hidden;display:inline-block} @@ -736,7 +742,7 @@ const TREND_TABS = ['Daily', 'Weekly', 'Monthly', 'Calendar', 'Models', 'Providers', 'Projects', 'Harnesses'].concat(META.machines ? ['Machines'] : []); let TRENDS = { open: false, tab: 'Daily', monthIdx: 0, weekIdx: 0, yearIdx: 0, drill: null, drillTab: null, sort: 'cost', desc: true }; const PRICE_VIEWS = [['flat', 'flat list'], ['family', 'by vendor'], ['provider', 'by provider'], ['all', 'models.dev']]; -let PRICES = { open: false, view: 'flat', sort: 'eff', desc: false, q: '' }; +let PRICES = { open: false, view: 'flat', sort: 'eff', desc: false, q: '', expanded: null }; // `w` affects only a session's Overview/tree and must remain independent of `$`. // It is deliberately transient: never localStorage and never the URL hash. let WHATIF = { model: null, open: false, q: '', i: 0, cat: false }; @@ -982,11 +988,12 @@ // Mirror api_equivalent_cost exactly; the effective-price cache fallback does not apply. function whatifCost(tok, rates) { if (!tok || !rates) return 0; - const [inp, out, reason, cr, cw, cw1h] = tok, [ir, orr, crr, cwr, cwr1h] = rates; + const [inp, out, reason, cr, cw, cw1h] = tok, [ir, orr, crr, cwr, cwr1h, rr] = rates; // cw1h replaces a subset of cw at the long-TTL rate; it is never extra volume. const long = Math.min(Math.max(cw1h || 0, 0), cw || 0); const write = (cw - long) * cwr + long * (cwr1h || cwr); - return (inp * ir + (out + reason) * orr + cr * crr + write) / 1e6; + // Reasoning bills at output unless the card publishes its own rate (sixth slot). + return (inp * ir + out * orr + reason * (rr ?? orr) + cr * crr + write) / 1e6; } function requestRates(model, context) { let rates = WI_PRICE.get(model); @@ -1088,11 +1095,11 @@ b.tok.slice(0, 5).forEach((v, i) => { tokens[i] += v; }); const p = requestRates(r.model, b.context); if (!p) return; - const [ir, orr, crr, cwr, cwr1h] = p, bt = b.tok; + const [ir, orr, crr, cwr, cwr1h, rr] = p, bt = b.tok; const long1h = Math.min(Math.max(bt[5] || 0, 0), bt[4] || 0); cost[0] += bt[0] * ir / 1e6; cost[1] += bt[1] * orr / 1e6; - cost[2] += bt[2] * orr / 1e6; + cost[2] += bt[2] * (rr ?? orr) / 1e6; cost[3] += bt[3] * crr / 1e6; cost[4] += ((bt[4] - long1h) * cwr + long1h * (cwr1h || cwr)) / 1e6; if (crr <= 0 && bt[3] > 0 && ir > 0) missingCache = true; @@ -3566,7 +3573,11 @@ const [ir, orr, cr, cw] = c.p; const approx = cr <= 0 && ir > 0; const eff = mix[0] * ir + mix[1] * orr + mix[2] * (approx ? ir : cr) + mix[3] * cw; - return { model: c.m, familyLabel: '', routes: [c.r], spend: 0, share: c.u || 0, price: c.p, eff, approx, status: c.s || '' }; + const card = {}; + if (c.t) card.tiers = c.t; + if (c.rr != null) card.reasoning = c.rr; + if (c.y) card.type = c.y; + return { model: c.m, familyLabel: '', routes: [c.r], spend: 0, share: c.u || 0, price: c.p, eff, approx, status: c.s || '', card }; }); } return DATA.prices.catalogRows; @@ -3581,7 +3592,52 @@ 'eff $/M prices each model’s list rates at your token mix: ', h('b', null, p(m[0]) + ' input'), ' · ' + p(m[1]) + ' output · ' + p(m[2]) + ' cacheR · ' + p(m[3]) + ' cacheW', DATA.prices.mixTokens ? ' (' + hTok(DATA.prices.mixTokens) + ' tokens).' : '.', - ' models.dev snapshot: ' + ((DATA.meta.priceSource || {}).fetched_at || 'unavailable') + '. Copilot estimates use its route list prices.'); + ' models.dev snapshot: ' + ((DATA.meta.priceSource || {}).fetched_at || 'unavailable') + '. Copilot estimates use its route list prices.', + ' ↑ marks rates that rise above a context size; click a row for its model card.'); +} +// Mirrors views/prices.context_label: three significant digits, k below a million. +const ctxLabel = n => n >= 1e6 ? +(n / 1e6).toPrecision(3) + 'M' : +(n / 1e3).toPrecision(3) + 'k'; +const tierTag = r => ((r.card || {}).tiers || []).length ? '↑' + ctxLabel(r.card.tiers[0][0]) : ''; +function ratesText(rates, rr) { + const [ir, orr, crr, cwr] = rates; + let t = 'in ' + ir.toFixed(2) + ' · out ' + orr.toFixed(2) + ' · cacheR ' + (crr <= 0 && ir > 0 ? '—' : crr.toFixed(2)) + + ' · cacheW ' + cwr.toFixed(2); + if (rr != null && rr !== orr) t += ' · reasoning ' + rr.toFixed(2); + return t; +} +// The TUI drill-in's model card (views/prices.card_lines), as label/value rows. +function priceCardRows(r) { + const card = r.card || {}, rows = [['List rates', ratesText(r.price, card.reasoning) + ' $/M']]; + const tiers = card.tiers || []; + tiers.forEach(([size, rates, rr]) => rows.push(['Above ' + ctxLabel(size), ratesText(rates, rr)])); + if (tiers.length) rows.push(['', 'a request over the threshold bills whole at the higher rates']); + else if (Object.keys(card).length) rows.push(['Long context', 'no surcharge: the same rates at any request size']); + if (tiers.length && r.tierShare) { + const [tiered, total, unknown] = r.tierShare; + let t = 'request sizes unknown, so all of it is priced at base rates (~)'; + if (unknown < total) { + t = Math.round(100 * tiered / total) + '% of your list cost ran at long-context rates'; + if (unknown > 0) t += ' · ' + Math.round(100 * unknown / total) + '% lacks request size, priced at base (~)'; + } + rows.push(['Your use', t]); + } + const facts = []; + if (card.released) facts.push('released ' + card.released); + if (card.knowledge) facts.push('knowledge ' + card.knowledge.slice(0, 7)); + const win = card.context || r.context; + if (win) facts.push(ctxLabel(win) + ' context'); + if (card.maxOutput) facts.push(ctxLabel(card.maxOutput) + ' max output'); + if (card.open) facts.push('open weights'); + if (card.type) facts.push(card.type + ' model'); + if (facts.length) rows.push(['Model', facts.join(' · ')]); + if (r.cheapest && r.eff > 0) { + const [route, eff, approx] = r.cheapest; + if (!r.routes.includes(route) && eff < r.eff * 0.95) { + rows.push(['Cheapest route', route + ' ' + (approx ? '~' : '') + eff.toFixed(2) + ' eff $/M, ' + + Math.round(100 * (1 - eff / r.eff)) + '% below this row at your mix']); + } + } + return rows; } function renderPrices() { const host = document.getElementById('prices'); @@ -3634,7 +3690,12 @@ const crCell = crr <= 0 && ir > 0 ? h('td', { class: 'mut' }, '—') : heatTd(crr, ranges[3], crr.toFixed(2)); let tag = PRICES.view === 'provider' ? r.familyLabel : (r.routes.length ? r.routes.join(' ') : ''); if (PRICES.view === 'all' && r.status) tag = tag ? tag + ' · ' + r.status : r.status; - body.push(h('tr', null, + if (PRICES.view === 'all' && (r.card || {}).type) tag = tag ? tag + ' · ' + r.card.type : r.card.type; + if (tierTag(r)) tag = tag ? tag + ' · ' + tierTag(r) : tierTag(r); + const rowKey = PRICES.view + ':' + r.routes.join(',') + ':' + r.model; + const open = PRICES.expanded === rowKey; + body.push(h('tr', { class: 'pr-row' + (open ? ' open' : ''), title: 'model card', + onclick: () => { PRICES.expanded = open ? null : rowKey; renderPrices(); } }, h('td', { class: 'l' }, h('span', { class: 'pin' + (pinnedRow ? ' on' : ''), title: pinnedRow ? 'unpin' : 'pin', onclick: ev => { ev.stopPropagation(); togglePin(r); renderPrices(); } }, pinnedRow ? '★' : '☆'), @@ -3646,6 +3707,8 @@ heatTd(orr, ranges[2], orr.toFixed(2)), crCell, heatTd(cwr, ranges[4], cwr.toFixed(2)))); + if (open) body.push(h('tr', { class: 'pr-card' }, h('td', { colspan: 7 }, + h('dl', null, priceCardRows(r).flatMap(([k, v]) => [h('dt', null, k), h('dd', null, v)]))))); }); if (cut) body.push(h('tr', { class: 'grp' }, h('td', { colspan: 7, class: 'mut' }, '… ' + cut.toLocaleString() + ' more — filter or sort to narrow'))); const panel = h('div', { class: 'tr-panel' }, diff --git a/src/opentab/web/report.py b/src/opentab/web/report.py index 0ca8fc5..6e1c744 100644 --- a/src/opentab/web/report.py +++ b/src/opentab/web/report.py @@ -30,6 +30,7 @@ model_price, model_tiers, price_source_meta, + reasoning_price, ) from opentab.accounting.tiers import ( detail_api_cost, @@ -132,10 +133,7 @@ def _whatif_payload(app: App) -> dict: for m in rows: name = str(m.get("model_name") or "") if name and name not in rates: - # The fifth rate prices the token split's 1h cache-write subset. - rates[name] = [round(float(v), 6) for v in model_price(name)] + [ - round(cache_write_1h_price(name), 6) - ] + rates[name] = _rate_card(name) # `unpriced` marks fallback-priced baselines as approximate. `catalog` reuses the # TUI's canonical ordering; `local` is excluded from both token-economics measures. return { @@ -145,17 +143,13 @@ def _whatif_payload(app: App) -> dict: ], "local": sorted(name for name in rates if is_local_provider(name)), "catalog": [ - { - "m": name, - "p": [round(float(v), 6) for v in model_price(name)] - + [round(cache_write_1h_price(name), 6)], - } + {"m": name, "p": _rate_card(name)} for name, _eff, _approx in app.whatif_catalog_candidates() ], "rates": rates, "tiers": { name: [ - {"context": size, "price": list(price) + [cache_write_1h_price(name, size + 1)]} + {"context": size, "price": _rate_card(name, size + 1, price)} for size, price in model_tiers(name) ] for name in set(rates) | {n for n, _eff, _approx in app.whatif_catalog_candidates()} @@ -167,8 +161,50 @@ def _whatif_payload(app: App) -> dict: } -def _price_entry(e) -> dict: - # A zero cache-read rate means missing data, never a discount. +def _rate_card(name: str, context: float | None = None, price=None) -> list[float]: + # [in, out, cacheR, cacheW, 1h cacheW, reasoning]: the fifth rate prices the token + # split's 1h cache-write subset, the sixth its reasoning tokens. + price = model_price(name, context) if price is None else price + return [round(float(v), 6) for v in price] + [ + round(cache_write_1h_price(name, context), 6), + round(reasoning_price(name, context), 6), + ] + + +def _card_payload(card: dict | None) -> dict: + # Rates are rounded like every other payload price; absent facts stay absent. + card = card or {} + out = { + key: card[key] + for key in ("released", "knowledge", "open", "type", "context") + if key in card + } + if "max_output" in card: + out["maxOutput"] = card["max_output"] + if "reasoning" in card: + out["reasoning"] = round(float(card["reasoning"]), 6) + if card.get("tiers"): + out["tiers"] = [ + [size, [round(float(v), 6) for v in rates], None if rr is None else round(float(rr), 6)] + for size, rates, rr in card["tiers"] + ] + return out + + +def _price_entry(e, app: App | None = None, route: str | None = None) -> dict: + # A zero cache-read rate means missing data, never a discount. Exposure and the + # cheapest route are the App's own projections, so both frontends say the same. + extra: dict = {} + if app is not None: + if (e.card or {}).get("tiers"): + exposure = app.price_tier_exposure(e.canon, route) + if exposure is not None: + extra["tierShare"] = [_money6(v) for v in exposure] + cheapest = app.price_cheapest_route(e) + if cheapest is not None: + extra["cheapest"] = [cheapest[0], round(cheapest[1], 6), bool(cheapest[2])] + if not (e.card or {}).get("context"): + extra["context"] = model_context_window(e.bare) return { "model": e.bare, "canon": e.canon, @@ -181,6 +217,8 @@ def _price_entry(e) -> dict: "eff": round(float(e.eff), 6), "approx": bool(e.approx), "status": getattr(e, "status", ""), + "card": _card_payload(e.card), + **extra, } @@ -195,6 +233,11 @@ def _catalog_entry(e) -> dict: out["u"] = round(e.share, 6) if e.status: out["s"] = e.status + # Thousands of rows: only the rate-shaping facts travel (tiers, reasoning, type). + card = _card_payload(e.card) + for key, short in (("tiers", "t"), ("reasoning", "rr"), ("type", "y")): + if key in card: + out[short] = card[key] return out @@ -206,9 +249,9 @@ def _prices_payload(app: App) -> dict: app.query = "" try: app.prices_view = "flat" - by_model = [_price_entry(e) for e in app.priced_model_entries()] + by_model = [_price_entry(e, app) for e in app.priced_model_entries()] app.prices_view = "provider" - by_route = [_price_entry(e) for e in app.priced_model_entries()] + by_route = [_price_entry(e, app, e.group) for e in app.priced_model_entries()] app.prices_view = "all" catalog = [_catalog_entry(e) for e in app.priced_model_entries()] finally: diff --git a/tests/_support.py b/tests/_support.py index 9a32796..25c9576 100644 --- a/tests/_support.py +++ b/tests/_support.py @@ -134,6 +134,84 @@ def tier_prices(): pricing.model_tiers.cache_clear() +# models.dev-shaped cards for rate-card facts: a published reasoning rate (base and +# tier), release/knowledge/output facts, a cheaper resale route, a free route, a Copilot +# route and an embedding model. Shared by pricing, TUI, web and service regressions. +CARD_CATALOG = { + "alibaba": { + "name": "Alibaba", + "models": { + "qwen-plus": { + "release_date": "2024-01-25", + "knowledge": "2024-04", + "open_weights": True, + "limit": {"context": 1_000_000, "output": 32768}, + "cost": { + "input": 0.4, + "output": 1.2, + "reasoning": 4, + "cache_read": 0.08, + "cache_write": 0.5, + "tiers": [ + { + "tier": {"type": "context", "size": 256000}, + "input": 1.2, + "output": 3.6, + "reasoning": 12, + "cache_read": 0.24, + "cache_write": 1.5, + } + ], + }, + }, + # Equal reasoning and output rates carry nothing worth keeping. + "qwen-flat": {"cost": {"input": 1, "output": 2, "reasoning": 2}}, + }, + }, + "deepinfra": { + "models": { + "qwen-plus": {"cost": {"input": 0.2, "output": 0.6, "cache_read": 0.04}}, + # A closed model far below its vendor's price: resale, never a recommendation. + "gpt-9": {"cost": {"input": 0.5, "output": 3, "cache_read": 0.05}}, + } + }, + "freeroute": {"models": {"qwen-plus": {"cost": {"input": 0, "output": 0}}}}, + "github-copilot": { + "models": {"qwen-plus": {"cost": {"input": 0.01, "output": 0.01, "cache_read": 0.001}}} + }, + "openai": { + "models": { + "text-embedding-9": { + "type": "embedding", + "limit": {"context": 8191, "output": 1536}, + "cost": {"input": 0.02, "output": 0}, + }, + "gpt-9": { + "type": "chat", + "release_date": "2026-01", + "cost": {"input": 5, "output": 30, "cache_read": 0.5}, + }, + } + }, +} + + +@contextmanager +def card_prices(): + """Install CARD_CATALOG as the only price layer, through the real prune/parse path.""" + from opentab.accounting import pricing + + layer = pricing._parse_catalog( + {"providers": pricing.prune_models_dev(CARD_CATALOG), "fetched_at": "2099"} + ) + pricing.model_tiers.cache_clear() + try: + with patch.object(pricing, "_layers", return_value=[layer]): + yield layer + finally: + pricing.model_tiers.cache_clear() + + def workflow( id, created_at, title=None, cost=1.0, tokens=100, directory="/tmp/project", ended_at="" ): diff --git a/tests/test_pricing.py b/tests/test_pricing.py index a9fcf2f..031b79c 100644 --- a/tests/test_pricing.py +++ b/tests/test_pricing.py @@ -5,11 +5,14 @@ import tempfile import opentab as ot +from opentab.accounting.tiers import row_cost_parts, row_tier_split from tests._support import ( + CARD_CATALOG, CopilotEstimateStore, _model_row, app_with, + card_prices, copilot_prices, tier_prices, workflow, @@ -1220,6 +1223,7 @@ def test_parsed_catalog_cache_matches_a_fresh_parse_and_follows_its_content(): cached = pricing._parse_catalog_bytes(raw, "fetched") for layer in (written, cached): assert list(layer) == list(fresh) and layer[0].tiers == fresh[0].tiers + assert layer[0].info == fresh[0].info assert isinstance(layer[0], pricing._Prices) # Same size, same mtime, different rate: content is the identity, not stat. edited = raw.replace(b"[1, 2, 3, 4]", b"[9, 2, 3, 4]") @@ -1313,3 +1317,91 @@ def get_data(self, path): pricing._parser_digest() == _hashlib.sha1(b"parser source from inside a zip").hexdigest() ) + + +def test_catalog_keeps_reasoning_rates_and_card_facts_only_where_they_carry_information(): + providers = ot.pricing.prune_models_dev(CARD_CATALOG) + plus = providers["alibaba"]["models"]["qwen-plus"] + assert plus["reasoning"] == 4.0 and plus["tiers"][0]["reasoning"] == 12.0 + assert (plus["released"], plus["knowledge"], plus["max_output"]) == ( + "2024-01-25", + "2024-04", + 32768, + ) + assert plus["open"] is True + # A reasoning rate equal to output, a chat type and closed weights add nothing. + assert "reasoning" not in providers["alibaba"]["models"]["qwen-flat"] + gpt = providers["openai"]["models"]["gpt-9"] + assert "type" not in gpt and "open" not in gpt and gpt["released"] == "2026-01" + assert providers["openai"]["models"]["text-embedding-9"]["type"] == "embedding" + # Malformed facts are dropped rather than trusted. + bad = ot.pricing.prune_models_dev( + { + "x": { + "models": { + "m": { + "release_date": "soon", + "knowledge": 2024, + "open_weights": "yes", + "limit": {"output": True}, + "cost": {"input": 1, "output": 2, "reasoning": float("nan")}, + } + } + } + } + ) + assert set(bad["x"]["models"]["m"]) == {"cost"} + + +def test_reasoning_tokens_bill_at_a_published_reasoning_rate_including_its_tier(): + with card_prices(): + name = "alibaba/qwen-plus" + assert ot.pricing.reasoning_price(name) == 4.0 + assert ot.pricing.reasoning_price(name, 300_000) == 12.0 + assert ot.pricing.reasoning_price(name, 256_000) == 4.0 # strict boundary + # Cards without one bill reasoning at output, tiered or not. + assert ot.pricing.reasoning_price("openai/gpt-9") == 30.0 + assert ot.pricing.reasoning_price("alibaba/qwen-flat") == 2.0 + # One million reasoning tokens, everything else zero. + assert abs(ot.pricing.api_equivalent_cost(name, 0, 0, 1e6, 0, 0) - 4.0) < 1e-9 + assert ( + abs( + ot.pricing.api_equivalent_cost(name, 0, 0, 1e6, 0, 0, context_tokens=300_000) - 12.0 + ) + < 1e-9 + ) + row = { + "model_name": name, + "reasoning": 1e6, + "pricing": [ + {"context": 1000.0, "tok": [0, 0, 5e5, 0, 0, 0]}, + {"context": 300_000.0, "tok": [0, 0, 5e5, 0, 0, 0]}, + ], + } + assert abs(row_cost_parts(row)[2] - (2.0 + 6.0)) < 1e-9 + + +def test_model_card_info_and_catalog_card_follow_the_resolved_route(): + with card_prices(): + info = ot.pricing.model_card_info("qwen-plus") + assert info["reasoning"] == 4.0 and info["open"] is True + assert info["tiers"] == [(256000, (1.2, 3.6, 0.24, 1.5), 12.0)] + assert ot.pricing.model_card_info("unknown-model-x") == {} + embed = ot.pricing.catalog_card("openai", "text-embedding-9") + assert embed["type"] == "embedding" and embed["context"] == 8191 + assert ot.pricing.catalog_card("openai", "missing") == {} + + +def test_row_tier_split_separates_long_context_and_unknown_context_spend(): + with tier_prices() as name: + row = { + "model_name": name, + "input": 3e6, + "pricing": [ + {"context": 1000.0, "tok": [1e6, 0, 0, 0, 0, 0]}, + {"context": 300_000.0, "tok": [1e6, 0, 0, 0, 0, 0]}, + {"context": None, "tok": [1e6, 0, 0, 0, 0, 0]}, + ], + } + tiered, total, unknown = row_tier_split(row) + assert (tiered, total, unknown) == (8.0, 16.0, 4.0) diff --git a/tests/test_service.py b/tests/test_service.py index 8cc5130..27e1a80 100644 --- a/tests/test_service.py +++ b/tests/test_service.py @@ -973,6 +973,14 @@ def test_model_catalog_static_path_matches_instance_api_with_state_and_paging(): "cache_read_usd_per_mtok": 0.5, "cache_write_usd_per_mtok": 6.25, "cache_write_1h_usd_per_mtok": 10.0, + "reasoning_usd_per_mtok": 25, + # A patched row has no catalog card: no tiers, no facts, nothing guessed. + "context_tiers": [], + "release_date": None, + "knowledge_cutoff": None, + "max_output_tokens": None, + "open_weights": False, + "model_type": None, "status": "active", "pinned": True, } diff --git a/tests/test_tui_prices.py b/tests/test_tui_prices.py index bc9a3b7..9ca8691 100644 --- a/tests/test_tui_prices.py +++ b/tests/test_tui_prices.py @@ -3,7 +3,14 @@ import opentab as ot -from tests._support import FakeStore, _model_row, _price_sort_app, app_with, workflow +from tests._support import ( + FakeStore, + _model_row, + _price_sort_app, + app_with, + card_prices, + workflow, +) def test_price_refresh_is_nonblocking_single_flight_and_adopts_on_ui_thread(): @@ -604,7 +611,10 @@ def test_prices_enter_lists_sessions_that_used_the_model(): assert "c" not in [w.id for w, _c, _t in sessions] # c only used codex # The drill-in body lists those session titles (a's $5 ahead of b's $3), not gamma. body = app.renderer.price_session_lines("claude-opus-4-8", 80) - assert "2 session(s)" in body[0] and "$8.00" in body[0] + # The model card heads the drill-in, then a blank line and the session summary. + assert body[0].startswith("List rates") and "" in body + summary = body[body.index("") + 1] + assert "2 session(s)" in summary and "$8.00" in summary assert any("alpha" in ln for ln in body) and any("beta" in ln for ln in body) assert not any("gamma" in ln for ln in body) # Esc backs out to the model list; unbound keys are swallowed; q closes. @@ -917,3 +927,77 @@ def test_trends_and_prices_stack_over_each_other_in_either_order(): assert app.overlay_top == "prices" app.handle_key(None, 27) # Esc closes the table, not the charts under it assert app.trends and not app.show_prices and app.overlay_top == "trends" + + +def _card_app(): + app = app_with([workflow("a", "2026-06-01 12:00:00", directory="/x", title="alpha")]) + row = _model_row("alibaba/qwen-plus", 0.0, 3_000_000) + row["input"] = 3_000_000 + row["pricing"] = [ + {"context": 1000.0, "tok": [1e6, 0, 0, 0, 0, 0]}, + {"context": 300_000.0, "tok": [1e6, 0, 0, 0, 0, 0]}, + {"context": None, "tok": [1e6, 0, 0, 0, 0, 0]}, + ] + app._model_by_root = {"a": [row]} + return app + + +def test_prices_drill_in_heads_with_the_rows_model_card(): + with card_prices(): + app = _card_app() + app.handle_key(None, ord("P")) + (entry,) = app.priced_model_entries() + assert entry.card["tiers"] and "↑256k" in app.renderer.price_table_lines(120)[-1] + app.handle_key(None, 10) + assert app.prices_entry == entry + body = app.renderer.price_session_lines("qwen-plus", 120) + text = "\n".join(body) + assert body[0].startswith("List rates") and "reasoning 4.00" in body[0] + # 1M base (0.40) + 1M tiered (1.20) + 1M unknown at base (0.40) = $2.00. + assert "60% of your list cost ran at long-context rates" in text + assert "20% lacks request size" in text + assert "released 2024-01-25" in text and "open weights" in text + # The cheapest metered route: not Copilot (subscription) or a zero-rate card. + assert "Cheapest route deepinfra" in text # label and value never touch + assert any("alpha" in ln for ln in body) + + +def test_cheapest_route_names_only_metered_routes_for_open_weights(): + with card_prices(): + app = _card_app() + app._model_by_root["a"].append(_model_row("openai/gpt-9", 0.0, 10)) + by_name = {e.bare: e for e in app.priced_model_entries()} + route, eff, approx = app.price_cheapest_route(by_name["qwen-plus"]) + # Not Copilot's subscription card (0.01) nor the zero-rate free route. + assert route == "deepinfra" and not approx and eff > 0 + # Closed weights: deepinfra's cheaper gpt-9 card is resale, not advice. + assert app.price_cheapest_route(by_name["gpt-9"]) is None + + +def test_whatif_catalog_offers_only_chat_models(): + with card_prices(): + app = _card_app() + names = [name for name, _eff, _approx in app.whatif_catalog_candidates()] + assert "openai/gpt-9" in names + assert not any("embedding" in name for name in names) + + +def test_web_prices_payload_carries_the_same_card_exposure_and_route(): + with card_prices(): + app = _card_app() + app._models_loaded = True + prices = ot.build_payload(app)["prices"] + (row,) = prices["byModel"] + assert row["card"]["reasoning"] == 4.0 and row["card"]["open"] is True + assert row["card"]["tiers"] == [[256000, [1.2, 3.6, 0.24, 1.5], 12.0]] + assert row["tierShare"] == [1.2, 2.0, 0.4] + assert row["cheapest"][0] == "deepinfra" + # The slim catalog carries only the rate-shaping facts. + catalog = {(c["r"], c["m"]): c for c in prices["catalog"]} + assert catalog[("alibaba", "qwen-plus")]["rr"] == 4.0 + assert catalog[("alibaba", "qwen-plus")]["t"][0][0] == 256000 + assert catalog[("openai", "text-embedding-9")]["y"] == "embedding" + assert "released" not in catalog[("alibaba", "qwen-plus")] + whatif = ot.build_payload(app)["whatif"] + assert whatif["rates"]["alibaba/qwen-plus"][5] == 4.0 + assert whatif["tiers"]["alibaba/qwen-plus"][0]["price"][5] == 12.0 diff --git a/tests/test_tui_views_prices.py b/tests/test_tui_views_prices.py index 88413f0..62f6536 100644 --- a/tests/test_tui_views_prices.py +++ b/tests/test_tui_views_prices.py @@ -172,6 +172,14 @@ def test_boundary_widths_keep_core_tag_and_heat_as_separate_paint_operations(): ) +def test_one_long_catalog_name_keeps_the_tag_column_on_screen(): + # A 60-character catalog name used to take the whole name column at 124 wide, + # pushing every route/tier tag past the edge; narrow screens keep the old names. + entries = [entry("x" * 60, 1.0), entry("claude-opus-4-8", 5.0)] + assert prices.name_width(entries, 124) + 2 + prices.PRICE_BLOCK_W + 2 + 16 <= 124 + assert prices.name_width(entries, 80) >= len("claude-opus-4-8") + + def test_neutral_price_cells_keep_explicit_paint_positions_when_values_overflow(): entries = [entry("a", 1_000_000), entry("b", 1_000_000)] result = layout(entries, width=100) @@ -247,3 +255,70 @@ def test_session_text_builder_and_layout_leave_clipping_to_the_renderer(): assert lines[2].endswith(long_title) assert result.rows[0] == lines[2] assert "…" not in lines[2] + + +CardEntry = namedtuple( + "CardEntry", + "bare canon family routes spend group share price eff approx status pinned card", + defaults=("", False, None), +) + + +def card_entry(card, *, eff=2.0, routes=("alibaba",), status=""): + return CardEntry( + "qwen-plus", "qwen-plus", "qwen", routes, 0.0, "", 0.0, + (0.4, 1.2, 0.08, 0.5), eff, False, status, False, card, + ) # fmt: skip + + +TIERED = {"tiers": [(256000, (1.2, 3.6, 0.24, 1.5), 12.0)], "reasoning": 4.0} + + +def test_tier_tag_rides_in_every_views_tag_and_type_only_in_the_catalog(): + assert prices.context_label(272000) == "272k" and prices.context_label(1_048_576) == "1.05M" + tiered = card_entry(TIERED) + assert prices.tier_tag(tiered) == "↑256k" and prices.tier_tag(card_entry(None)) == "" + assert prices.entry_tag(tiered, "flat") == "alibaba·↑256k" + assert prices.entry_tag(tiered, "provider") == "Qwen·↑256k" + embed = card_entry({"type": "embedding"}, status="beta") + assert prices.entry_tag(embed, "all") == "alibaba·beta·embedding" + assert prices.entry_tag(embed, "flat") == "alibaba" + + +def test_card_lines_show_rates_tiers_exposure_facts_and_a_meaningfully_cheaper_route(): + card = { + **TIERED, + "released": "2024-01-25", + "knowledge": "2024-04-30", + "max_output": 32768, + "open": True, + } + lines = prices.card_lines( + card_entry(card), + context_window=1_000_000, + exposure=(2.0, 8.0, 1.0), + cheapest=("deepinfra", 1.0, False), + ) + text = "\n".join(lines) + assert lines[0].startswith("List rates") and "reasoning 4.00" in lines[0] + assert lines[1].startswith("Above 256k") and "reasoning 12.00" in lines[1] + assert "bills whole at the higher rates" in lines[2] + assert "25% of your list cost ran at long-context rates" in text + assert "12% lacks request size, priced at base (~)" in text + assert "released 2024-01-25 · knowledge 2024-04 · 1M context · 32.8k max output" in text + assert "open weights" in text + assert "deepinfra 1.00 eff $/M, 50% below this row at your mix" in text + unknown = prices.card_lines(card_entry(card), exposure=(0.0, 4.0, 4.0)) + assert any("request sizes unknown" in ln for ln in unknown) + assert not any("0% of your list cost" in ln for ln in unknown) + # No tiers: no tier lines, and exposure is meaningless without them. + plain = prices.card_lines(card_entry({}), exposure=(0.0, 1.0, 0.0)) + assert plain == [plain[0]] and "reasoning" not in plain[0] + # A known card without tiers says so, so a short card reads as flat, not missing. + flat = prices.card_lines(card_entry({"context": 1_000_000})) + assert flat[1].startswith("Long context") and "same rates at any request size" in flat[1] + # A route within rounding noise, or the row's own route, is not news. + for cheapest in (("deepinfra", 1.95, False), ("alibaba", 1.0, False)): + assert not any( + ln.startswith("Cheapest") for ln in prices.card_lines(card_entry({}), cheapest=cheapest) + ) diff --git a/tests/test_web.py b/tests/test_web.py index d9baff5..47e04c9 100644 --- a/tests/test_web.py +++ b/tests/test_web.py @@ -1817,7 +1817,7 @@ def test_whats_new_javascript_history_stops_at_bounds_and_requests_focus(): def _js_whatif_cost(tok, rates): # The page's whatifCost(), transcribed: the client mirrors pricing.api_equivalent_cost # over a [input, output, reasoning, cacheRead, cacheWrite, cacheWrite1h] split, priced - # with (input, output, cacheRead, cacheWrite, cacheWrite1h). Written out here so the + # with (input, output, cacheRead, cacheWrite, cacheWrite1h, reasoning). Written out here so the # serialized numbers can be repriced exactly the way the page reprices them -- and so a # drift between the two formulas fails a test. # @@ -1827,9 +1827,10 @@ def _js_whatif_cost(tok, rates): cw1h = tok[5] if len(tok) > 5 else 0 ir, orr, crr, cwr = rates[:4] cwr1h = rates[4] if len(rates) > 4 else cwr + rr = rates[5] if len(rates) > 5 else orr long = min(max(cw1h, 0), cw) write = (cw - long) * cwr + long * cwr1h - return (inp * ir + (out + reason) * orr + cr * crr + write) / 1e6 + return (inp * ir + out * orr + reason * rr + cr * crr + write) / 1e6 def _js_whatif_totals(payload, session_id, target): @@ -1867,13 +1868,16 @@ def test_web_payload_ships_the_whatif_ingredients(): ] assert [m["tokens"] for m in models] == [2_000_000, 1_000_000] for m in models: - # Five rates, not four: the catalog's (input, output, cacheRead, cacheWrite) plus - # the DERIVED 1h-TTL write rate, which models.dev does not carry. whatifCost needs - # it to bill the `tok` split's long-write subset at the long-TTL price. + # Six rates, not four: the catalog's (input, output, cacheRead, cacheWrite), the + # DERIVED 1h-TTL write rate, which models.dev does not carry, and the reasoning + # rate (output unless the card publishes its own). whatifCost needs both to bill + # the `tok` split's long-write and reasoning subsets. assert m["price"] == [round(float(v), 6) for v in ot.model_price(m["model"])] + [ - round(ot.cache_write_1h_price(m["model"]), 6) + round(ot.cache_write_1h_price(m["model"]), 6), + round(ot.reasoning_price(m["model"]), 6), ] - assert len(m["price"]) == 5 and m["price"][0] > 0 + assert len(m["price"]) == 6 and m["price"][0] > 0 + assert m["price"][5] == m["price"][1] # Claude publishes no separate reasoning rate assert m["price"][4] == round(2.0 * m["price"][0], 6) # 1h write == 2.00x input # ...and a rate card for every model used, armable or not: the baseline prices each # model's tokens at its own rates, so a model you cannot arm still has to be counted. @@ -1890,8 +1894,9 @@ def test_web_payload_ships_the_whatif_catalog_tier(): assert len(catalog) > 100 # the whole catalog, not just the two used models for c in catalog[:50]: assert c["p"] == [round(float(v), 6) for v in ot.model_price(c["m"])] + [ - round(ot.cache_write_1h_price(c["m"]), 6) - ] # the derived 1h-TTL write rate rides last, so arming a catalog row prices + round(ot.cache_write_1h_price(c["m"]), 6), + round(ot.reasoning_price(c["m"]), 6), + ] # the derived 1h-TTL write and reasoning rates ride last, so arming a catalog row prices # long writes exactly the way arming a used model does assert set(c) == {"m", "p"} # slim on purpose: ~1.5k rows ride in every payload # A catalog target the data never used still reprices client-side: whatifTotals @@ -1944,7 +1949,7 @@ def test_web_whatif_baseline_is_the_exact_per_model_list_price(): # The drift guard on the JS formula. Cache write is now split by TTL -- the 1h subset # by REPLACEMENT, so those tokens leave the 5m bucket instead of being billed twice. assert "const write = (cw - long) * cwr + long * (cwr1h || cwr);" in js - assert "return (inp * ir + (out + reason) * orr + cr * crr + write) / 1e6;" in js + assert "return (inp * ir + out * orr + reason * (rr ?? orr) + cr * crr + write) / 1e6;" in js assert "const long = Math.min(Math.max(cw1h || 0, 0), cw || 0);" in js # One shared reducer behind both panes (tree TOTAL + Overview summary), so they cannot # drift, and no per-node Δ column any more (a node's baseline isn't computable). @@ -2524,7 +2529,7 @@ def _js_token_economics(payload, session_ids, model=None): tokens[i] += v cost[0] += r["tok"][0] * ir / 1e6 cost[1] += r["tok"][1] * orr / 1e6 - cost[2] += r["tok"][2] * orr / 1e6 + cost[2] += r["tok"][2] * (rate_row[5] if len(rate_row) > 5 else orr) / 1e6 cost[3] += r["tok"][3] * crr / 1e6 long1h = min(max(r["tok"][5] if len(r["tok"]) > 5 else 0, 0), r["tok"][4]) cwr1h = rate_row[4] if len(rate_row) > 4 else cwr @@ -2550,7 +2555,8 @@ def test_web_token_economics_matches_the_tui_split_exactly(): # The pieces must stay pieces: summing them here would make the pane's TOTAL a second # implementation of the cost rather than a decomposition of the one on screen. assert "function tokenEconomics(" in js - assert "cost[2] += bt[2] * orr / 1e6" in js # reasoning bills at the request's output rate + # Reasoning bills at the request's output rate unless the card publishes its own. + assert "cost[2] += bt[2] * (rr ?? orr) / 1e6" in js # A missing cache rate is flagged, never read as free reads (the TUI's rule). assert "if (crr <= 0 && bt[3] > 0 && ir > 0) missingCache = true;" in js assert "WI_LOCAL.has(r.model)" in js # local models leave both rows From a370248d5d414fd3572cf951fc97a65e4d7188aa Mon Sep 17 00:00:00 2001 From: Mohamed Hamidi Date: Wed, 28 Oct 2026 21:33:32 +0100 Subject: [PATCH 3/4] fix(tui): drain held-key repeats so scrolling stops on release --- docs/tui.md | 3 +++ src/opentab/tui/app.py | 38 ++++++++++++++++++++++++++++++++++---- tests/test_tui_bindings.py | 34 ++++++++++++++++++++++++++++++++++ 3 files changed, 71 insertions(+), 4 deletions(-) diff --git a/docs/tui.md b/docs/tui.md index 5997ce3..3ff4b09 100644 --- a/docs/tui.md +++ b/docs/tui.md @@ -264,6 +264,9 @@ together. `get_wch` reads characters rather than UTF-8 bytes; `_read_key` return ASCII and special keys as integers, other characters as strings. Both forms go through action lookup, so non-ASCII keys can be bound as well as typed. Text prompts budget input length separately from visible width and scroll long input. +A held key queues repeats faster than a frame paints; `_drain_repeats` handles +queued copies of the same key before the next paint (at least every 100 ms), so +motion stops on release. A different key or a click waits for that paint. Search uses `[search.edit]`, `[search]` and shared `[menu]` bindings. Its tabs, pickers, footer, help and mouse regions reuse existing renderers. Results splits diff --git a/src/opentab/tui/app.py b/src/opentab/tui/app.py index 5f63037..c5b4837 100644 --- a/src/opentab/tui/app.py +++ b/src/opentab/tui/app.py @@ -233,6 +233,9 @@ class PriceEntry(NamedTuple): card: dict | None = None +# Longest a held key is handled without a repaint (App._drain_repeats). +REPEAT_DRAIN_S = 0.1 + # models.dev types that cannot stand in for a chat model in a `w` comparison. NON_CHAT_TYPES = frozenset( {"embedding", "image", "video", "speech", "transcription", "reranking", "realtime"} @@ -418,6 +421,7 @@ def __init__( # (UI-state key, entries) for the P table: the models.dev view rebuilds ~7k # rows, too slow to redo on every keypress and paint while j is held. self._price_entries_memo: tuple | None = None + self._pending_key: int | str | None = None self._models_loaded = False self._tool_by_session: dict[str, list[dict]] = {} self._turns_by_session: dict[str, list[dict]] = {} @@ -7483,14 +7487,40 @@ def _run(self, stdscr: curses.window) -> None: ): self._announce_whats_new() continue - timeout_ms = self._input_timeout_ms() - stdscr.timeout(timeout_ms) - key = self._read_key(stdscr, timeout_ms) + if self._pending_key is not None: + key, self._pending_key = self._pending_key, None + else: + timeout_ms = self._input_timeout_ms() + stdscr.timeout(timeout_ms) + key = self._read_key(stdscr, timeout_ms) if key == -1: continue # idle wake: check expiry and workers, then repaint - if not self.handle_key(stdscr, key): + if not self.handle_key(stdscr, key) or not self._drain_repeats(stdscr, key): break + def _drain_repeats(self, stdscr: curses.window, key: int | str) -> bool: + # A held key queues repeats faster than a frame paints, and the backlog kept + # the cursor moving after release. Handle queued copies of the same key before + # the next paint (still at least every REPEAT_DRAIN_S); any other key waits in + # _pending_key for the paint, so a click never lands on an unpainted layout. + if key in (curses.KEY_MOUSE, curses.KEY_RESIZE): + return True + deadline = time.monotonic() + REPEAT_DRAIN_S + try: + while time.monotonic() < deadline: + stdscr.timeout(0) + queued = self._read_key(stdscr, 0) + if queued == -1: + return True + if queued != key: + self._pending_key = queued + return True + if not self.handle_key(stdscr, queued): + return False + return True + finally: + stdscr.timeout(self._input_timeout_ms()) + @staticmethod def _read_key(stdscr: curses.window, timeout_ms: int = -1) -> int | str: # get_wch reads a *character* where getch hands back raw bytes -- so a note (or a diff --git a/tests/test_tui_bindings.py b/tests/test_tui_bindings.py index 00ae4c6..872bfce 100644 --- a/tests/test_tui_bindings.py +++ b/tests/test_tui_bindings.py @@ -3,6 +3,7 @@ from unittest.mock import patch import opentab as ot +from opentab.tui import app as tui_app from opentab.tui import bindings from tests._support import app_with, workflow @@ -153,6 +154,39 @@ def unget(self, event): assert ot.App._read_key(Input([])) == -1 +def test_held_key_repeats_are_handled_before_the_next_paint(): + # Repeats queued while a frame paints are drained in one go, so the cursor stops + # when j is released; a different key waits for the paint instead. + class Input: + def __init__(self, events): + self.events = list(events) + self.delay = 500 + + def get_wch(self): + if not self.events: + raise ot.curses.error() + return self.events.pop(0) + + def timeout(self, delay): + self.delay = delay + + app = app_with([]) + handled = [] + app.handle_key = lambda _screen, key: handled.append(key) or True + screen = Input(["j", "j", "j", "k"]) + assert app._drain_repeats(screen, ord("j")) + assert handled == [ord("j")] * 3 and app._pending_key == ord("k") and not screen.events + app._pending_key = None + # A click is never batched: its target comes from the painted layout. + screen = Input([ot.curses.KEY_MOUSE]) + assert app._drain_repeats(screen, ot.curses.KEY_MOUSE) and screen.events + # The drain is bounded, so a key held forever still repaints. + screen = Input(["j"] * 10_000) + with patch.object(tui_app, "REPEAT_DRAIN_S", 0.0): + assert app._drain_repeats(screen, ord("j")) + assert len(screen.events) == 10_000 + + def test_every_default_conf_roundtrip_is_silent_and_identical(): # ensure_user_keymap writes the generated file; loading it back must change # nothing and warn about nothing -- the shipped defaults are self-consistent. From 02706c09db970395747e55b01d67b9018545f16a Mon Sep 17 00:00:00 2001 From: Mohamed Hamidi Date: Wed, 28 Oct 2026 21:56:27 +0100 Subject: [PATCH 4/4] fix(tui): keep P cards current, rank routes by reasoning, guard drain --- docs/pricing.md | 2 +- src/opentab/tui/app.py | 94 +++++++++++++++++++++++++++------ src/opentab/tui/renderer.py | 7 ++- src/opentab/tui/views/prices.py | 14 ++--- src/opentab/web/page.py | 8 +-- src/opentab/web/report.py | 3 +- tests/_support.py | 4 ++ tests/test_tui_bindings.py | 22 ++++++++ tests/test_tui_prices.py | 40 ++++++++++++-- tests/test_tui_views_prices.py | 4 +- 10 files changed, 162 insertions(+), 36 deletions(-) diff --git a/docs/pricing.md b/docs/pricing.md index 6f3ab98..f1b1820 100644 --- a/docs/pricing.md +++ b/docs/pricing.md @@ -223,7 +223,7 @@ above that request context. | **Above 272k** | Each context tier's rates; a request over the threshold bills whole at them | | **Your use** | The share of your list cost that ran at long-context rates, and the share whose request size is unknown, which is priced at base | | **Model** | Release date, knowledge cutoff, context window, maximum output, open weights, model type | -| **Cheapest route** | For open-weight models, a provider selling the same model at least 5% cheaper at your mix. Free cards, local servers and subscription routes such as Copilot don't count, and hosts can differ in quantization and limits. Closed models get no such line: a far cheaper route for one is grey-market resale | +| **Cheapest route** | For open-weight models, a provider selling the same model at least 5% cheaper at your mix, with your reasoning tokens billed at each provider's own reasoning rate. Free cards, local servers and subscription routes such as Copilot don't count, and hosts can differ in quantization and limits. Closed models get no such line: a far cheaper route for one is grey-market resale | Lines without data are left out. Your use follows the table's scope: all time, the current identity filters, ignored sessions per `I`. diff --git a/src/opentab/tui/app.py b/src/opentab/tui/app.py index c5b4837..7019902 100644 --- a/src/opentab/tui/app.py +++ b/src/opentab/tui/app.py @@ -235,6 +235,14 @@ class PriceEntry(NamedTuple): # Longest a held key is handled without a repaint (App._drain_repeats). REPEAT_DRAIN_S = 0.1 +# Cursor-follow requests the next paint consumes; a repeat never drains past a new one. +FOLLOW_FLAGS = ( + "_tool_follow", + "_change_follow", + "_turn_follow", + "_trace_call_follow", + "_subagent_follow", +) # models.dev types that cannot stand in for a chat model in a `w` comparison. NON_CHAT_TYPES = frozenset( @@ -4851,6 +4859,25 @@ def _catalog_price_entries(self, shares: tuple) -> list[PriceEntry]: ) return entries + def drilled_price_entry(self) -> PriceEntry | None: + """The drilled P row as the table shows it now. + + A rate refresh or reload rebuilds the rows while the card is open; the card + must read the rebuilt row, not the one captured on Enter. + """ + entry = self.prices_entry + if entry is None: + return None + same = [ + e + for e in self.priced_model_entries() + if e.canon == entry.canon and e.group == entry.group + ] + exact = [e for e in same if e.routes == entry.routes] + if exact: + return exact[0] + return same[0] if len(same) == 1 else entry + def price_tier_exposure(self, canon: str, route: str | None = None) -> tuple | None: """(long-context list cost, total list cost, unknown-context list cost) or None. @@ -4874,20 +4901,42 @@ def price_tier_exposure(self, canon: str, route: str | None = None) -> tuple | N tiered, total, unknown = tiered + t, total + a, unknown + u return (tiered, total, unknown) if total > 0 else None - def price_cheapest_route(self, entry: PriceEntry) -> tuple[str, float, bool] | None: - """(provider, eff $/M, approx) of the cheapest metered route for an open model. - - Ranked at the same token mix as eff $/M. Free (zero-rate) cards, local servers - and subscription routes such as Copilot are not purchasable per token. Closed - weights are sold legitimately only by their vendor and its clouds, so a far - cheaper "route" for one is grey-market resale, not advice: open weights only. + def _reasoning_fraction(self) -> float: + # Reasoning tokens' share of the output bucket at the P scope; _token_mix + # folds them into output, which hides a route's separate reasoning rate. + out = reasoning = 0.0 + for rows in self._priced_model_roots().values(): + for m in rows: + name = m.get("model_name") + if not name or is_local_provider(name): + continue + _inp, o, r, _cr, _cw = model_row_split(m) + out += o + r + reasoning += r + return reasoning / out if out > 0 else 0.0 + + def price_cheapest_route(self, entry: PriceEntry) -> tuple[str, float, bool, float] | None: + """(provider, $/M, approx, this row's $/M) of the cheapest metered open route. + + Ranked at the eff $/M token mix, with each card's own reasoning rate billing + the reasoning share of output (one route can sell output cheap and reasoning + dear), and the row is priced the same way for the comparison. Free (zero-rate) + cards, local servers and subscription routes such as Copilot are not + purchasable per token. Closed weights are sold legitimately only by their + vendor and its clouds, so a far cheaper "route" for one is grey-market resale, + not advice: open weights only. """ if not (entry.card or {}).get("open"): return None - canon = entry.canon mix = self.price_token_mix() shares = mix[0] if mix else (1.0, 0.0, 0.0, 0.0) - if self._cheapest_routes is None or self._cheapest_routes[0] != shares: + frac = self._reasoning_fraction() + + def cost(price: tuple, reasoning: float | None) -> tuple[float, bool]: + out = price[1] * (1 - frac) + (price[1] if reasoning is None else reasoning) * frac + return effective_price((price[0], out, price[2], price[3]), shares) + + if self._cheapest_routes is None or self._cheapest_routes[0] != (shares, frac): best: dict[str, tuple[float, str, bool]] = {} for pid, mid, price, _status in catalog_models(): if ( @@ -4898,12 +4947,15 @@ def price_cheapest_route(self, entry: PriceEntry) -> tuple[str, float, bool] | N ): continue key = canonical_model(display_model(mid.rsplit("/", 1)[-1])) - eff, approx = effective_price(price, shares) + eff, approx = cost(price, (catalog_card(pid, mid) or {}).get("reasoning")) if key not in best or (eff, pid) < best[key][:2]: best[key] = (eff, pid, approx) - self._cheapest_routes = (shares, best) - hit = self._cheapest_routes[1].get(canon) - return (hit[1], hit[0], hit[2]) if hit else None + self._cheapest_routes = ((shares, frac), best) + hit = self._cheapest_routes[1].get(entry.canon) + if hit is None: + return None + own = cost(tuple(entry.price), (entry.card or {}).get("reasoning"))[0] + return hit[1], hit[0], hit[2], own def _order_price_entries(self, entries: list[PriceEntry]) -> list[PriceEntry]: # Pins always float; grouped views rank groups by spend with Other last. @@ -7495,10 +7547,16 @@ def _run(self, stdscr: curses.window) -> None: key = self._read_key(stdscr, timeout_ms) if key == -1: continue # idle wake: check expiry and workers, then repaint - if not self.handle_key(stdscr, key) or not self._drain_repeats(stdscr, key): + follows = self._pending_follows() + if not self.handle_key(stdscr, key) or not self._drain_repeats(stdscr, key, follows): break - def _drain_repeats(self, stdscr: curses.window, key: int | str) -> bool: + def _pending_follows(self) -> frozenset[str]: + return frozenset(flag for flag in FOLLOW_FLAGS if getattr(self, flag)) + + def _drain_repeats( + self, stdscr: curses.window, key: int | str, follows: frozenset[str] = frozenset() + ) -> bool: # A held key queues repeats faster than a frame paints, and the backlog kept # the cursor moving after release. Handle queued copies of the same key before # the next paint (still at least every REPEAT_DRAIN_S); any other key waits in @@ -7512,7 +7570,11 @@ def _drain_repeats(self, stdscr: curses.window, key: int | str) -> bool: queued = self._read_key(stdscr, 0) if queued == -1: return True - if queued != key: + # A follow scroll this burst requested waits for the paint; a further + # repeat at the list's end would clear it with the cursor offscreen. + # `follows` were already pending before the key (a diff never + # consumes _change_follow), so they cannot stop the drain for good. + if queued != key or self._pending_follows() - follows: self._pending_key = queued return True if not self.handle_key(stdscr, queued): diff --git a/src/opentab/tui/renderer.py b/src/opentab/tui/renderer.py index 5f284e0..287542f 100644 --- a/src/opentab/tui/renderer.py +++ b/src/opentab/tui/renderer.py @@ -5667,9 +5667,12 @@ def draw_prices(self, stdscr: curses.window, y: int, bottom: int, width: int) -> def price_card_lines(self) -> list[str]: """The drilled row's model card, or nothing when the drill came from elsewhere.""" - entry = self.app.prices_entry - if entry is None or entry.bare != self.app.prices_model: + # The drill's own row, checked by the name it was opened under: a refresh may + # pick another alias spelling to represent the same rebuilt row. + captured = self.app.prices_entry + if captured is None or captured.bare != self.app.prices_model: return [] + entry = self.app.drilled_price_entry() or captured tiers = (entry.card or {}).get("tiers") route = entry.group if self.app.prices_view == "provider" else None return price_view.card_lines( diff --git a/src/opentab/tui/views/prices.py b/src/opentab/tui/views/prices.py index 151d45f..e9698b6 100644 --- a/src/opentab/tui/views/prices.py +++ b/src/opentab/tui/views/prices.py @@ -259,12 +259,13 @@ def card_lines( *, context_window: int | None = None, exposure: tuple[float, float, float] | None = None, - cheapest: tuple[str, float, bool] | None = None, + cheapest: tuple[str, float, bool, float] | None = None, ) -> list[str]: """The drill-in's model card: rates, context tiers, your tier exposure, facts. ``exposure`` is (long-context list cost, total list cost, unknown-context list - cost); ``cheapest`` is (provider, eff $/M, approx) at the same mix as eff $/M. + cost); ``cheapest`` is (provider, $/M, approx, this row's $/M), both at the eff + $/M mix with reasoning billed at each card's reasoning rate. """ card = getattr(entry, "card", None) or {} label = CARD_LABEL_W @@ -301,13 +302,12 @@ def card_lines( facts.append(f"{card['type']} model") if facts: lines.append(f"{'Model':<{label}}{' · '.join(facts)}") - if cheapest is not None and entry.eff > 0: - route, eff, approx = cheapest - own = set(entry.routes) - if route not in own and eff < entry.eff * (1 - CHEAPER_ROUTE_MARGIN): + if cheapest is not None and cheapest[3] > 0: + route, eff, approx, row_eff = cheapest + if route not in entry.routes and eff < row_eff * (1 - CHEAPER_ROUTE_MARGIN): lines.append( f"{'Cheapest route':<{label}}{route} {'~' if approx else ''}{eff:.2f} eff $/M, " - f"{1 - eff / entry.eff:.0%} below this row at your mix" + f"{1 - eff / row_eff:.0%} below this row at your mix" ) return lines diff --git a/src/opentab/web/page.py b/src/opentab/web/page.py index c1e7422..4f0e925 100644 --- a/src/opentab/web/page.py +++ b/src/opentab/web/page.py @@ -3630,11 +3630,11 @@ if (card.open) facts.push('open weights'); if (card.type) facts.push(card.type + ' model'); if (facts.length) rows.push(['Model', facts.join(' · ')]); - if (r.cheapest && r.eff > 0) { - const [route, eff, approx] = r.cheapest; - if (!r.routes.includes(route) && eff < r.eff * 0.95) { + if (r.cheapest && r.cheapest[3] > 0) { + const [route, eff, approx, own] = r.cheapest; + if (!r.routes.includes(route) && eff < own * 0.95) { rows.push(['Cheapest route', route + ' ' + (approx ? '~' : '') + eff.toFixed(2) + ' eff $/M, ' - + Math.round(100 * (1 - eff / r.eff)) + '% below this row at your mix']); + + Math.round(100 * (1 - eff / own)) + '% below this row at your mix']); } } return rows; diff --git a/src/opentab/web/report.py b/src/opentab/web/report.py index 6e1c744..e669bd3 100644 --- a/src/opentab/web/report.py +++ b/src/opentab/web/report.py @@ -202,7 +202,8 @@ def _price_entry(e, app: App | None = None, route: str | None = None) -> dict: extra["tierShare"] = [_money6(v) for v in exposure] cheapest = app.price_cheapest_route(e) if cheapest is not None: - extra["cheapest"] = [cheapest[0], round(cheapest[1], 6), bool(cheapest[2])] + route, eff, approx, own = cheapest + extra["cheapest"] = [route, round(eff, 6), bool(approx), round(own, 6)] if not (e.card or {}).get("context"): extra["context"] = model_context_window(e.bare) return { diff --git a/tests/_support.py b/tests/_support.py index 25c9576..b344463 100644 --- a/tests/_support.py +++ b/tests/_support.py @@ -175,6 +175,10 @@ def tier_prices(): "gpt-9": {"cost": {"input": 0.5, "output": 3, "cache_read": 0.05}}, } }, + # Cheapest output, dearest reasoning: wins an output mix, loses a reasoning one. + "thinkdear": { + "models": {"qwen-plus": {"cost": {"input": 0.3, "output": 0.05, "reasoning": 50}}} + }, "freeroute": {"models": {"qwen-plus": {"cost": {"input": 0, "output": 0}}}}, "github-copilot": { "models": {"qwen-plus": {"cost": {"input": 0.01, "output": 0.01, "cache_read": 0.001}}} diff --git a/tests/test_tui_bindings.py b/tests/test_tui_bindings.py index 872bfce..9be976f 100644 --- a/tests/test_tui_bindings.py +++ b/tests/test_tui_bindings.py @@ -177,6 +177,28 @@ def timeout(self, delay): assert app._drain_repeats(screen, ord("j")) assert handled == [ord("j")] * 3 and app._pending_key == ord("k") and not screen.events app._pending_key = None + # A one-shot cursor follow waits for its paint: at a list's end the next repeat + # would clear it and leave the cursor offscreen. + handled.clear() + + def follow(_screen, key): + handled.append(key) + app._tool_follow = True + return True + + app.handle_key = follow + screen = Input(["j", "j", "j"]) + assert app._drain_repeats(screen, ord("j")) + assert handled == [ord("j")] and app._pending_key == ord("j") and screen.events == ["j"] + app._pending_key = None + # A follow already pending before the key (a diff never consumes _change_follow) + # cannot switch draining off for good. + handled.clear() + app.handle_key = lambda _screen, key: handled.append(key) or True + screen = Input(["j", "j"]) + assert app._drain_repeats(screen, ord("j"), frozenset({"_tool_follow"})) + assert handled == [ord("j")] * 2 and app._pending_key is None + app._tool_follow = False # A click is never batched: its target comes from the painted layout. screen = Input([ot.curses.KEY_MOUSE]) assert app._drain_repeats(screen, ot.curses.KEY_MOUSE) and screen.events diff --git a/tests/test_tui_prices.py b/tests/test_tui_prices.py index 9ca8691..f51f0d9 100644 --- a/tests/test_tui_prices.py +++ b/tests/test_tui_prices.py @@ -962,18 +962,51 @@ def test_prices_drill_in_heads_with_the_rows_model_card(): assert any("alpha" in ln for ln in body) +def test_open_card_follows_the_rebuilt_row_after_a_rate_refresh(): + # A refresh landing while the card is open rebuilds the rows; the card must show + # the table's new rates, not the row captured on Enter. + with card_prices(): + app = _card_app() + app.handle_key(None, ord("P")) + app.handle_key(None, 10) + app.prices_entry = app.prices_entry._replace(price=(9.0, 9.0, 9.0, 9.0)) + text = "\n".join(app.renderer.price_card_lines()) + assert "in 0.40 · out 1.20" in text and "9.00" not in text + # The refresh may elect another alias spelling for the same row: still its card. + app.prices_entry = app.prices_entry._replace(bare="qwen.plus") + app.prices_model = "qwen.plus" + assert "in 0.40 · out 1.20" in "\n".join(app.renderer.price_card_lines()) + + def test_cheapest_route_names_only_metered_routes_for_open_weights(): with card_prices(): app = _card_app() app._model_by_root["a"].append(_model_row("openai/gpt-9", 0.0, 10)) by_name = {e.bare: e for e in app.priced_model_entries()} - route, eff, approx = app.price_cheapest_route(by_name["qwen-plus"]) + route, eff, approx, own = app.price_cheapest_route(by_name["qwen-plus"]) # Not Copilot's subscription card (0.01) nor the zero-rate free route. - assert route == "deepinfra" and not approx and eff > 0 + assert route == "deepinfra" and not approx and (eff, own) == (0.2, 0.4) # Closed weights: deepinfra's cheaper gpt-9 card is resale, not advice. assert app.price_cheapest_route(by_name["gpt-9"]) is None +def test_cheapest_route_bills_reasoning_at_each_routes_reasoning_rate(): + # The token mix folds reasoning into output; ranking on output alone would send a + # thinking-heavy user to the route that sells output cheap and reasoning dear. + with card_prices(): + app = _card_app() + row = app._model_by_root["a"][0] + row.update(input=0, output=1_000_000, reasoning=0, tokens_total=1_000_000) + entry = next(e for e in app.priced_model_entries() if e.bare == "qwen-plus") + assert app.price_cheapest_route(entry) == ("thinkdear", 0.05, True, 1.2) + row.update(output=0, reasoning=1_000_000) + # Only the reasoning share changed: the route memo must notice by itself. + app._price_entries_memo = None + entry = next(e for e in app.priced_model_entries() if e.bare == "qwen-plus") + # deepinfra bills reasoning at its output rate; the row at alibaba's reasoning 4. + assert app.price_cheapest_route(entry) == ("deepinfra", 0.6, False, 4.0) + + def test_whatif_catalog_offers_only_chat_models(): with card_prices(): app = _card_app() @@ -991,7 +1024,8 @@ def test_web_prices_payload_carries_the_same_card_exposure_and_route(): assert row["card"]["reasoning"] == 4.0 and row["card"]["open"] is True assert row["card"]["tiers"] == [[256000, [1.2, 3.6, 0.24, 1.5], 12.0]] assert row["tierShare"] == [1.2, 2.0, 0.4] - assert row["cheapest"][0] == "deepinfra" + # The route and this row, both costed with reasoning at each card's own rate. + assert row["cheapest"] == ["deepinfra", 0.2, False, 0.4] # The slim catalog carries only the rate-shaping facts. catalog = {(c["r"], c["m"]): c for c in prices["catalog"]} assert catalog[("alibaba", "qwen-plus")]["rr"] == 4.0 diff --git a/tests/test_tui_views_prices.py b/tests/test_tui_views_prices.py index 62f6536..c66dff3 100644 --- a/tests/test_tui_views_prices.py +++ b/tests/test_tui_views_prices.py @@ -297,7 +297,7 @@ def test_card_lines_show_rates_tiers_exposure_facts_and_a_meaningfully_cheaper_r card_entry(card), context_window=1_000_000, exposure=(2.0, 8.0, 1.0), - cheapest=("deepinfra", 1.0, False), + cheapest=("deepinfra", 1.0, False, 2.0), ) text = "\n".join(lines) assert lines[0].startswith("List rates") and "reasoning 4.00" in lines[0] @@ -318,7 +318,7 @@ def test_card_lines_show_rates_tiers_exposure_facts_and_a_meaningfully_cheaper_r flat = prices.card_lines(card_entry({"context": 1_000_000})) assert flat[1].startswith("Long context") and "same rates at any request size" in flat[1] # A route within rounding noise, or the row's own route, is not news. - for cheapest in (("deepinfra", 1.95, False), ("alibaba", 1.0, False)): + for cheapest in (("deepinfra", 1.95, False, 2.0), ("alibaba", 1.0, False, 2.0)): assert not any( ln.startswith("Cheapest") for ln in prices.card_lines(card_entry({}), cheapest=cheapest) )