Update all your AI model ids with one agent skill
Point Codex, Claude Code, OpenCode, or any CLI app to one URL and update all your repos at once.
curl -fsSL https://aistackregistry.com/catalog.json52 models. 7 providers. One fetch for the lineup. Listed in models means current. A retired id names its replacement or null.
How one update runs
Provider docs and model IDs change. The catalog puts current model facts, connection settings, and first-party source links in one JSON response.
-
Fetch once
Codex or Claude Code downloads
/catalog.jsononce for the whole update. -
Check every repo
The agent reuses the same catalog as it checks model settings across your repositories.
-
You approve the edits
Review one plan per repo and apply the changes you want. Then run each repo's own checks.
Use the tool you already have
Codex or Claude Code
Put one instruction in AGENTS.md for Codex or CLAUDE.md for Claude Code, or
install the shared skill.
CI
Fetch /catalog.json in a read-only job and compare the model IDs, limits, and provider
settings your repo pins.
Current models
Every model its provider lists as current, from the catalog this page was built with. Token limits are
the ones the provider publishes. Connections, request controls, and source links are in
catalog.json and controls.json.
| Model id | Provider | Context tokens | Max output tokens | Input | Output | Aliases |
|---|---|---|---|---|---|---|
claude-fable-5-1 | Anthropic | 1,000,000 | 128,000 | image, text | text | |
claude-haiku-5-5 | Anthropic | 1,000,000 | 128,000 | image, text | text | |
claude-opus-5-5 | Anthropic | 1,000,000 | 128,000 | image, text | text | |
claude-sonnet-5-5 | Anthropic | 1,000,000 | 128,000 | image, text | text | |
deepseek-flash | DeepSeek | 1,048,576 | 393,216 | image, text | text | |
deepseek-v4-pro | DeepSeek | 1,048,576 | 393,216 | text | text | |
gemini-3-pro-image | Google Gemini API | 65,536 | 32,768 | image, text | image, text | |
gemini-3.1-flash-lite-image | Google Gemini API | 65,536 | 4,096 | image, pdf, text, video | image, text | |
gemini-3.1-pro-preview | Google Gemini API | 1,048,576 | 65,536 | audio, image, pdf, text, video | text | |
gemini-3.5-flash-lite | Google Gemini API | 1,048,576 | 65,536 | audio, image, pdf, text, video | text | |
gemini-3.6-flash | Google Gemini API | 1,048,576 | 65,536 | audio, image, pdf, text, video | text | |
gemini-3.8-flash | Google Gemini API | 1,048,576 | 65,536 | audio, image, pdf, text, video | text | |
gemini-4-argon | Google Gemini API | 1,048,576 | 65,536 | audio, image, pdf, text, video | text | |
gemini-nano-banana-2.1 | Google Gemini API | 131,072 | 32,768 | image, pdf, text, video | image, text | |
muse-image-1.0 | Meta Model API | not published | not published | image, text | image | |
muse-spark-1.1 | Meta Model API | 1,048,576 | not published | audio, image, pdf, text, video | text | |
muse-spark-1.2 | Meta Model API | 1,048,576 | not published | audio, image, pdf, text, video | text | |
muse-spark-1.2-contributor | Meta Model API | 1,048,576 | not published | audio, image, pdf, text, video | text | |
muse-spark-1.3 | Meta Model API | 1,048,576 | 131,072 | audio, image, pdf, text, video | text | |
muse-spark-1.3-contributor | Meta Model API | 1,048,576 | not published | audio, image, pdf, text, video | text | |
muse-wonder-1.0 | Meta Model API | 1,048,576 | not published | audio, image, pdf, text, video | text | |
kimi-k3 | Kimi API by Moonshot AI | 1,048,576 | 1,048,576 | image, text, video | text | |
kimi-k3.1-pro | Kimi API by Moonshot AI | 1,048,576 | 1,048,576 | image, text, video | text | |
kimi-k3.1-pro-highspeed | Kimi API by Moonshot AI | 1,048,576 | 1,048,576 | image, text, video | text | |
gpt-5.2 | OpenAI | 400,000 | 128,000 | image, text | text | gpt-5.2-2025-12-11 |
gpt-5.2-pro | OpenAI | 400,000 | 128,000 | image, text | text | gpt-5.2-pro-2025-12-11 |
gpt-5.4 | OpenAI | 1,050,000 | 128,000 | image, text | text | gpt-5.4-2026-03-05 |
gpt-5.4-mini | OpenAI | 400,000 | 128,000 | image, text | text | gpt-5.4-mini-2026-03-17 |
gpt-5.4-pro | OpenAI | 1,050,000 | 128,000 | image, text | text | gpt-5.4-pro-2026-03-05 |
gpt-5.5 | OpenAI | 1,050,000 | 128,000 | image, text | text | gpt-5.5-2026-04-23 |
gpt-5.5-pro | OpenAI | 1,050,000 | 128,000 | image, text | text | gpt-5.5-pro-2026-04-23 |
gpt-5.6-luna | OpenAI | 1,050,000 | 128,000 | image, text | text | |
gpt-5.6-sol | OpenAI | 1,050,000 | 128,000 | image, text | text | gpt-5.6 |
gpt-5.6-terra | OpenAI | 1,050,000 | 128,000 | image, text | text | |
gpt-6-astra | OpenAI | 1,050,000 | 128,000 | image, text | text | |
gpt-6-luna | OpenAI | 1,050,000 | 128,000 | image, text | text | |
gpt-6-sol | OpenAI | 1,050,000 | 128,000 | image, text | text | |
gpt-6.1-sol | OpenAI | 1,050,000 | 128,000 | image, text | text | |
gpt-6.1-terra | OpenAI | 1,050,000 | 128,000 | image, text | text | |
gpt-image-2 | OpenAI | not published | not published | image, text | image | gpt-image-2-2026-04-21 |
gpt-image-2.5-flare | OpenAI | not published | not published | image, text | image | gpt-image-2.5-flare-2026-09-08 |
gpt-image-2.5-sunburst | OpenAI | not published | not published | image, text | image | gpt-image-2.5-sunburst-2026-09-08 |
grok-4.20-0309-non-reasoning | xAI | 1,000,000 | not published | image, text | text | grok-4.20-beta-0309-non-reasoning, grok-4.20-beta-latest-non-reasoning, grok-4.20-beta-non-reasoning, grok-4.20-experimental-beta-0304-non-reasoning, grok-4.20-experimental-beta-non-reasoning-latest, grok-4.20-non-reasoning, grok-4.20-non-reasoning-gv2, grok-4.20-non-reasoning-latest |
grok-4.20-0309-reasoning | xAI | 1,000,000 | not published | image, text | text | grok-4.20, grok-4.20-0309, grok-4.20-beta, grok-4.20-beta-0309, grok-4.20-beta-0309-reasoning, grok-4.20-beta-latest, grok-4.20-beta-latest-reasoning, grok-4.20-beta-reasoning, grok-4.20-experimental-beta-0304, grok-4.20-experimental-beta-0304-reasoning, grok-4.20-experimental-beta-latest, grok-4.20-experimental-beta-reasoning-latest, grok-4.20-reasoning, grok-4.20-reasoning-gv2, grok-4.20-reasoning-latest |
grok-4.20-multi-agent-0309 | xAI | 1,000,000 | not published | image, text | text | grok-4.20-multi-agent, grok-4.20-multi-agent-beta-0309, grok-4.20-multi-agent-beta-latest, grok-4.20-multi-agent-experimental-beta-0304, grok-4.20-multi-agent-experimental-beta-latest, grok-4.20-multi-agent-latest |
grok-4.3 | xAI | 1,000,000 | not published | image, text | text | grok-4.3-latest |
grok-4.5 | xAI | 500,000 | not published | image, text | text | grok-4.5-latest, grok-build-latest |
grok-4.6 | xAI | 500,000 | not published | image, text | text | |
grok-4.7 | xAI | 500,000 | not published | image, text | text | |
grok-build-0.1 | xAI | 256,000 | not published | image, text | text | grok-code-fast, grok-code-fast-1-0825 |
grok-imagine-image | xAI | not published | not published | image, text | image | grok-imagine-image-2026-03-02 |
grok-imagine-image-2.0 | xAI | not published | not published | image, text | image |
Retired ids and their replacements (30)
| Retired id | Provider | Replaced by | Aliases |
|---|---|---|---|
claude-fable-5 | Anthropic | null | |
claude-haiku-4-5-20251001 | Anthropic | claude-haiku-5-5 | claude-haiku-4-5 |
claude-opus-4-5-20251101 | Anthropic | null | claude-opus-4-5 |
claude-opus-4-6 | Anthropic | null | |
claude-opus-4-7 | Anthropic | null | |
claude-opus-4-8 | Anthropic | null | |
claude-opus-5 | Anthropic | null | |
claude-sonnet-4-5-20250929 | Anthropic | claude-sonnet-5-5 | claude-sonnet-4-5 |
claude-sonnet-4-6 | Anthropic | null | |
claude-sonnet-5 | Anthropic | null | |
deepseek-v4-flash | DeepSeek | deepseek-flash | |
deepseek-v4-flash-vision-exp | DeepSeek | deepseek-flash | |
gemini-3-flash-preview | Google Gemini API | gemini-3.6-flash | |
gemini-3-pro-image-preview | Google Gemini API | gemini-3-pro-image | |
gemini-3-pro-preview | Google Gemini API | gemini-3.1-pro-preview | |
gemini-3.1-flash-image | Google Gemini API | gemini-nano-banana-2.1 | |
gemini-3.1-flash-image-preview | Google Gemini API | gemini-3.1-flash-image | |
gemini-3.1-flash-lite | Google Gemini API | gemini-3.5-flash-lite | |
gemini-3.1-flash-lite-preview | Google Gemini API | gemini-3.1-flash-lite | |
gemini-3.5-flash | Google Gemini API | gemini-3.6-flash | |
gemini-3.7-flash | Google Gemini API | gemini-3.8-flash | |
kimi-k2.6 | Kimi API by Moonshot AI | kimi-k3.1-pro | |
kimi-k2.7-code | Kimi API by Moonshot AI | kimi-k3.1-pro | |
kimi-k2.7-code-highspeed | Kimi API by Moonshot AI | kimi-k3.1-pro | |
gpt-5.3-codex | OpenAI | gpt-6-sol | |
gpt-5.4-nano | OpenAI | gpt-6-luna | gpt-5.4-nano-2026-03-17 |
grok-4-1-fast-non-reasoning | xAI | grok-4.3 | |
grok-4-1-fast-reasoning | xAI | grok-4.3 | |
grok-code-fast-1 | xAI | grok-build-0.1 | |
grok-imagine-image-quality | xAI | grok-imagine-image-2.0 | grok-imagine-image-pro, grok-imagine-image-quality-20260403, grok-imagine-image-quality-latest |
Check the first-party sources.
Each model entry links to the provider documentation used to verify it. A fact that documentation leaves out stays out of the entry.
Questions developers ask
- Does this update my repos by itself?
- No. Give Codex or Claude Code a target model, review the plan, then approve the edits. Run the same process whenever a model changes.
- Does my agent need provider API keys?
- No. The catalog already contains provider connection settings and model facts. Your update job does not call model providers.
- Why not send every agent to provider docs?
- That repeats the same calls for every repo and can give each update a different answer. Fetch one catalog and reuse it across the whole update.
- Can CI use it?
- Yes. The setup page has a job that checks a configured model ID against the catalog.