Skip to content

chore: sync models with dashboard API - #7

Closed
amaan-ai20 wants to merge 1 commit into
mainfrom
model-sync/2026-09-14-1350
Closed

amaan-ai20 wants to merge 1 commit into
mainfrom
model-sync/2026-09-14-1350

Conversation

@amaan-ai20

Copy link
Copy Markdown
Collaborator

Automated model-catalog sync. The dashboard API is the source of truth; every value below was taken from it. Merging publishes v3.8.0 to npm.

Corrected

Model Field Was Now
all-minilm-l6-v2 input price $0.50 $0.004
bge-small-en-v1.5 input price $0.50 $0.004
glm-5.2 context (notes) 1M / 1,048,576 262,144
gpt-oss-120b parameters (notes) 117B 120B
qwen3-30b-a3b-fp8 parameters (notes) 30.5B 30B

Renamed

  • deepseek-v4-flashdeepseek-v4-flash-0731 (also repriced: $0.07/$0.14 → $0.16/$0.38) — pricing, CHAT_MODELS, README, DOCUMENTATION, ADDING_COMMANDS, -m example

Added

  • zlm-v1-signal-extract — pricing only ($0.02/$0.05); no command calls it (Text Classification, priced for future use)

Removed

  • t5-small — pricing dropped, no command referenced it
  • zlm-v1-multi-iab-classify — pricing dropped, no command referenced it
  • zlm-v1-followup-questions-edge — pricing dropped; the generate_followups command that routed to it is deleted (src/commands/generateFollowups.ts, its src/cli.ts registration, README ToC/section, DOCUMENTATION §4.14 section removed and classify_domain renumbered §4.15 → §4.14, §5 exceptions sentence)

Verification

  • audit-models.py --strict — clean apart from NOTE lines (priced-only models with no command)
  • npm run lint, npm run build, npm test pass (40/40 tests)
  • zerogpu chat --help lists exactly the API's 6 Text Generation models
  • zerogpu --help no longer lists generate_followups
  • Repo-wide grep confirms no remaining references to the renamed/removed ids

🤖 Generated with Claude Code

https://claude.ai/code/session_01VMLgNX5mY94eviR5dsqa4N


Generated by Claude Code

- all-minilm-l6-v2: input $0.50 -> $0.004 (ZGPU_PRICING, test CATALOG)
- bge-small-en-v1.5: input $0.50 -> $0.004 (ZGPU_PRICING, test CATALOG)
- glm-5.2: notes 1M/1,048,576 context -> 262,144 context (README, DOCUMENTATION, chat example comment)
- gpt-oss-120b: notes 117B -> 120B params (README, DOCUMENTATION)
- qwen3-30b-a3b-fp8: notes 30.5B -> 30B params (README, DOCUMENTATION)
- rename deepseek-v4-flash -> deepseek-v4-flash-0731 (new rate $0.16/$0.38): pricing, CHAT_MODELS, README + DOCUMENTATION + ADDING_COMMANDS, chat -m example
- add zlm-v1-signal-extract: pricing only, no command calls it (Text Classification)
- remove t5-small: pricing dropped, no command referenced it
- remove zlm-v1-multi-iab-classify: pricing dropped, no command referenced it
- remove zlm-v1-followup-questions-edge: pricing dropped; command generate_followups deleted (src/commands/generateFollowups.ts, src/cli.ts registration, README ToC/section, DOCUMENTATION §4.14 section + renumbered classify_domain to §4.14, §5 exceptions sentence)
- version 3.7.2 -> 3.8.0 (minor: deepseek-v4-flash-0731 added to chat --model)

Source: https://api-dashboard.zerogpu.ai/api/models

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01VMLgNX5mY94eviR5dsqa4N
@amaan-ai20 amaan-ai20 closed this Sep 16, 2026
@amaan-ai20
amaan-ai20 deleted the model-sync/2026-09-14-1350 branch September 16, 2026 12:05
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants