diff --git a/docs/changelogs/index.md b/docs/changelogs/index.md
index 121c2d5..0656a0f 100644
--- a/docs/changelogs/index.md
+++ b/docs/changelogs/index.md
@@ -2,6 +2,7 @@
Welcome to the TimeCopilot Changelog. Here, you will find a comprehensive list of all the changes, updates, and improvements made to the TimeCopilot project. This section is designed to keep you informed about the latest features, bug fixes, and enhancements as we continue to develop and refine the TimeCopilot experience. Stay tuned for regular updates and feel free to explore the details of each release below.
+- [v0.0.36](v0.0.36.md)
- [v0.0.35](v0.0.35.md)
- [v0.0.34](v0.0.34.md)
- [v0.0.33](v0.0.33.md)
diff --git a/docs/changelogs/v0.0.36.md b/docs/changelogs/v0.0.36.md
new file mode 100644
index 0000000..abfc65b
--- /dev/null
+++ b/docs/changelogs/v0.0.36.md
@@ -0,0 +1,29 @@
+### Features
+
+* **T0 family checkpoints**: Document and compare T0 alpha and beta via the existing `T0` class (`foundationforecast>=0.1.8`, `tfc-t0>=0.5.0`). Pass `repo_id` to select the checkpoint:
+
+ - `theforecastingcompany/t0-alpha` (default) — ~102M parameters
+ - `theforecastingcompany/t0-beta` — ~256M parameters ([model card](https://huggingface.co/theforecastingcompany/t0-beta))
+
+ ```python
+ import pandas as pd
+ from timecopilot.models.foundation.t0 import T0
+
+ df = pd.read_csv(
+ "https://timecopilot.s3.amazonaws.com/public/data/air_passengers.csv",
+ parse_dates=["ds"],
+ )
+
+ model = T0(
+ repo_id="theforecastingcompany/t0-beta",
+ alias="t0-beta",
+ context_length=512,
+ )
+ fcst_df = model.forecast(df, h=12, freq="MS", level=[80, 90])
+ ```
+
+* **T0 family notebook**: Added [`t0-family` example notebook](../examples/t0-family.ipynb) comparing `t0-alpha` and `t0-beta` on event page-views, including prediction intervals and evaluation metrics.
+
+---
+
+**Full Changelog**: https://github.com/TimeCopilot/timecopilot/compare/v0.0.35...v0.0.36
diff --git a/docs/examples/index.md b/docs/examples/index.md
index 6d64907..0b81bb0 100644
--- a/docs/examples/index.md
+++ b/docs/examples/index.md
@@ -30,6 +30,7 @@ For model API details, see the [Model Hub](../model-hub.md).
| [Chronos Family](chronos-family.ipynb) | Forecast with Chronos 1.x and 2.x checkpoints | Python 3.10+ |
| [TimesFM Family](timesfm-family.ipynb) | Forecast with TimesFM 1.0, 2.0, 2.5, and 3.0 with prediction intervals | Python 3.10+ |
| [PatchTST-FM Family](patchtst-fm-family.ipynb) | Forecast with IBM Research PatchTST-FM r1 and Granite PatchTST-FM r1/r2 | Python 3.11–3.13; GPU recommended |
+| [T0 Family](t0-family.ipynb) | Forecast with T0 alpha and beta with prediction intervals | Python 3.11–3.13; GPU recommended |
| [TabPFN Family](tabpfn-family.ipynb) | Forecast with TabPFN-2 and TabPFN-3 with prediction intervals | Python 3.10–3.12; `TABPFN_TOKEN` for LOCAL |
| [TiRex Family](tirex-family.ipynb) | Forecast with TiRex 1.0 and 2.0 | Python 3.11+ |
| [Toto Family](toto-family.ipynb) | Forecast with Toto 1.0 and 2.0 | Python 3.10+ |
diff --git a/docs/examples/t0-family.ipynb b/docs/examples/t0-family.ipynb
new file mode 100644
index 0000000..3494f18
--- /dev/null
+++ b/docs/examples/t0-family.ipynb
@@ -0,0 +1,608 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "id": "3e223474",
+ "metadata": {},
+ "source": [
+ "# Forecast Using the T0 Family\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "7471dfd7",
+ "metadata": {},
+ "source": [
+ "TimeCopilot ships a single `T0` class for The Forecasting Company open-weights checkpoints. Pass the Hugging Face `repo_id` to select the model:\n",
+ "\n",
+ "| Release | `repo_id` | Size |\n",
+ "|---------|-----------|------|\n",
+ "| **T0 alpha** (default) | `theforecastingcompany/t0-alpha` | ~102M |\n",
+ "| **T0 beta** | `theforecastingcompany/t0-beta` | ~256M |\n",
+ "\n",
+ "*Requirements*:\n",
+ "\n",
+ " - Python 3.11 – 3.13\n",
+ " - `foundationforecast>=0.1.8` (pulls `tfc-t0>=0.5.0` for beta)\n",
+ " - CUDA recommended (CPU works but is slower)\n",
+ "\n",
+ "**Quantiles:** `t0-alpha` uses 5 native quantile knots; `t0-beta` uses 21 levels (0.01–0.99). Pass `level` or `quantiles`; requested levels are interpolated from native knots.\n",
+ "\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "e209fdc2",
+ "metadata": {},
+ "source": [
+ "## Import libraries\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "id": "d8df60df",
+ "metadata": {
+ "execution": {
+ "iopub.execute_input": "2026-09-23T20:20:53.772699Z",
+ "iopub.status.busy": "2026-09-23T20:20:53.772622Z",
+ "iopub.status.idle": "2026-09-23T20:21:02.487061Z",
+ "shell.execute_reply": "2026-09-23T20:21:02.486780Z"
+ }
+ },
+ "outputs": [
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "INFO:datasets:JAX version 0.7.1 available.\n",
+ "2026-09-29 13:59:22,270\tINFO util.py:155 -- Missing packages: ['ipywidgets']. Run `pip install -U ipywidgets`, then restart the notebook server for rich notebook output.\n",
+ "2026-09-29 13:59:22,616\tINFO util.py:155 -- Missing packages: ['ipywidgets']. Run `pip install -U ipywidgets`, then restart the notebook server for rich notebook output.\n"
+ ]
+ }
+ ],
+ "source": [
+ "import sys\n",
+ "\n",
+ "import pandas as pd\n",
+ "\n",
+ "from timecopilot import TimeCopilotForecaster\n",
+ "\n",
+ "if sys.version_info < (3, 11) or sys.version_info >= (3, 14):\n",
+ " raise RuntimeError(\"T0 requires Python >= 3.11 and < 3.14\")\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "f25cbb5a",
+ "metadata": {},
+ "source": [
+ "## Load the dataset\n",
+ "\n",
+ "The DataFrame must include at least the following columns:\n",
+ "- unique_id: Unique identifier for each time series (string)\n",
+ "- ds: Date column (datetime format)\n",
+ "- y: Target variable for forecasting (float format)\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "id": "296a7e2a",
+ "metadata": {
+ "execution": {
+ "iopub.execute_input": "2026-09-23T20:21:02.488315Z",
+ "iopub.status.busy": "2026-09-23T20:21:02.488235Z",
+ "iopub.status.idle": "2026-09-23T20:21:02.858483Z",
+ "shell.execute_reply": "2026-09-23T20:21:02.858142Z"
+ }
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | \n",
+ " unique_id | \n",
+ " ds | \n",
+ " y | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " | 0 | \n",
+ " Oktoberfest | \n",
+ " 2020-01-31 | \n",
+ " 25376 | \n",
+ "
\n",
+ " \n",
+ " | 1 | \n",
+ " Oktoberfest | \n",
+ " 2020-02-29 | \n",
+ " 28470 | \n",
+ "
\n",
+ " \n",
+ " | 2 | \n",
+ " Oktoberfest | \n",
+ " 2020-03-31 | \n",
+ " 23816 | \n",
+ "
\n",
+ " \n",
+ " | 3 | \n",
+ " Oktoberfest | \n",
+ " 2020-04-30 | \n",
+ " 46186 | \n",
+ "
\n",
+ " \n",
+ " | 4 | \n",
+ " Oktoberfest | \n",
+ " 2020-05-31 | \n",
+ " 31213 | \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "
"
+ ]
+ },
+ "execution_count": 3,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "TimeCopilotForecaster.plot(df)\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "232f095e",
+ "metadata": {},
+ "source": [
+ "## Create a TimeCopilotForecaster\n",
+ "\n",
+ "We compare T0 alpha and beta. Each model gets a distinct `alias` so forecasts are easy to identify.\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 4,
+ "id": "b455275d",
+ "metadata": {
+ "execution": {
+ "iopub.execute_input": "2026-09-23T20:21:02.897878Z",
+ "iopub.status.busy": "2026-09-23T20:21:02.897799Z",
+ "iopub.status.idle": "2026-09-23T20:21:02.903296Z",
+ "shell.execute_reply": "2026-09-23T20:21:02.903116Z"
+ }
+ },
+ "outputs": [],
+ "source": [
+ "from timecopilot.models.foundation.t0 import T0\n",
+ "\n",
+ "context_length = 512\n",
+ "batch_size = 8\n",
+ "\n",
+ "models = [\n",
+ " T0(\n",
+ " repo_id=\"theforecastingcompany/t0-alpha\",\n",
+ " alias=\"t0-alpha\",\n",
+ " context_length=context_length,\n",
+ " batch_size=batch_size,\n",
+ " ),\n",
+ " T0(\n",
+ " repo_id=\"theforecastingcompany/t0-beta\",\n",
+ " alias=\"t0-beta\",\n",
+ " context_length=context_length,\n",
+ " batch_size=batch_size,\n",
+ " ),\n",
+ "]\n",
+ "\n",
+ "tcf = TimeCopilotForecaster(models=models)\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "8fb70efe",
+ "metadata": {},
+ "source": [
+ "## Cross-validate with prediction intervals\n",
+ "\n",
+ "Beta supports fine-grained quantiles; alpha interpolates from its 5 native knots.\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 5,
+ "id": "96b89954",
+ "metadata": {
+ "execution": {
+ "iopub.execute_input": "2026-09-23T20:21:02.904237Z",
+ "iopub.status.busy": "2026-09-23T20:21:02.904175Z",
+ "iopub.status.idle": "2026-09-23T20:21:36.929928Z",
+ "shell.execute_reply": "2026-09-23T20:21:36.929457Z"
+ }
+ },
+ "outputs": [
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "0it [00:00, ?it/s]Warning: You are sending unauthenticated requests to the HF Hub. Please set a HF_TOKEN to enable higher rate limits and faster downloads.\n",
+ "WARNING:huggingface_hub.utils._http:Warning: You are sending unauthenticated requests to the HF Hub. Please set a HF_TOKEN to enable higher rate limits and faster downloads.\n",
+ "100%|██████████| 1/1 [00:00<00:00, 33.07it/s]\n",
+ "1it [00:01, 1.36s/it]\n",
+ "100%|██████████| 1/1 [00:00<00:00, 12.14it/s]\n",
+ "1it [00:04, 4.24s/it]\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | \n",
+ " unique_id | \n",
+ " ds | \n",
+ " cutoff | \n",
+ " y | \n",
+ " t0-alpha | \n",
+ " t0-alpha-lo-80 | \n",
+ " t0-alpha-hi-80 | \n",
+ " t0-alpha-lo-90 | \n",
+ " t0-alpha-hi-90 | \n",
+ " t0-beta | \n",
+ " t0-beta-lo-80 | \n",
+ " t0-beta-hi-80 | \n",
+ " t0-beta-lo-90 | \n",
+ " t0-beta-hi-90 | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " | 0 | \n",
+ " Black Friday | \n",
+ " 2024-09-30 | \n",
+ " 2024-08-31 | \n",
+ " 2607 | \n",
+ " 2116.718506 | \n",
+ " 1641.902588 | \n",
+ " 3565.373779 | \n",
+ " 1641.902588 | \n",
+ " 3565.373779 | \n",
+ " 2067.666260 | \n",
+ " 1619.116943 | \n",
+ " 2988.298828 | \n",
+ " 1468.435547 | \n",
+ " 4289.673828 | \n",
+ "
\n",
+ " \n",
+ " | 1 | \n",
+ " Black Friday | \n",
+ " 2024-10-31 | \n",
+ " 2024-08-31 | \n",
+ " 2470 | \n",
+ " 2536.804688 | \n",
+ " 1639.148682 | \n",
+ " 7205.684570 | \n",
+ " 1639.148682 | \n",
+ " 7205.684570 | \n",
+ " 2855.733154 | \n",
+ " 1799.611572 | \n",
+ " 7728.554199 | \n",
+ " 1571.173096 | \n",
+ " 12572.298828 | \n",
+ "
\n",
+ " \n",
+ " | 2 | \n",
+ " Black Friday | \n",
+ " 2024-11-30 | \n",
+ " 2024-08-31 | \n",
+ " 11058 | \n",
+ " 10990.619141 | \n",
+ " 2503.651855 | \n",
+ " 23642.492188 | \n",
+ " 2503.651855 | \n",
+ " 23642.492188 | \n",
+ " 10715.068359 | \n",
+ " 1846.131592 | \n",
+ " 27632.449219 | \n",
+ " 1418.302246 | \n",
+ " 32104.906250 | \n",
+ "
\n",
+ " \n",
+ " | 3 | \n",
+ " Black Friday | \n",
+ " 2024-12-31 | \n",
+ " 2024-08-31 | \n",
+ " 3548 | \n",
+ " 4139.507812 | \n",
+ " 1690.802002 | \n",
+ " 22400.281250 | \n",
+ " 1690.802002 | \n",
+ " 22400.281250 | \n",
+ " 6946.167969 | \n",
+ " 1764.462891 | \n",
+ " 22927.335938 | \n",
+ " 1441.465332 | \n",
+ " 28249.667969 | \n",
+ "
\n",
+ " \n",
+ " | 4 | \n",
+ " Black Friday | \n",
+ " 2025-01-31 | \n",
+ " 2024-08-31 | \n",
+ " 1724 | \n",
+ " 2066.241943 | \n",
+ " 1512.723145 | \n",
+ " 3874.775635 | \n",
+ " 1512.723145 | \n",
+ " 3874.775635 | \n",
+ " 2339.218750 | \n",
+ " 1589.121826 | \n",
+ " 5747.300781 | \n",
+ " 1378.156006 | \n",
+ " 9279.615234 | \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "
"
+ ]
+ },
+ "execution_count": 6,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "tcf.plot(df, cv_df.drop(columns=[\"cutoff\", \"y\"]), level=[80])"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "4757c778",
+ "metadata": {},
+ "source": [
+ "## Evaluate\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 8,
+ "id": "56e13034",
+ "metadata": {
+ "execution": {
+ "iopub.execute_input": "2026-09-23T20:21:36.976483Z",
+ "iopub.status.busy": "2026-09-23T20:21:36.976307Z",
+ "iopub.status.idle": "2026-09-23T20:21:37.017400Z",
+ "shell.execute_reply": "2026-09-23T20:21:37.017196Z"
+ }
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | metric | \n",
+ " mase | \n",
+ " scaled_crps | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " | t0-beta | \n",
+ " 1.279 | \n",
+ " 0.166 | \n",
+ "
\n",
+ " \n",
+ " | t0-alpha | \n",
+ " 0.883 | \n",
+ " 0.177 | \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "