[github-actions]

Model deprecation audit

Each model below returned a definitive not-found / deprecated response from its provider (a single 404 / not-found is treated as authoritative). Account/region-scoped providers (bedrock, vertex, databricks) are surfaced for manual review, not auto-removed.

{
  "deprecations": [
    {
      "model": "deepseek-ai/DeepSeek-V3.1",
      "provider": "baseten",
      "reason": "absent from list + probe not-found",
      "status": 404,
      "detail": "{\"error\":\"model not found\"}\n"
    },
    {
      "model": "north-mini-code-1-0",
      "provider": "cohere",
      "reason": "absent from provider model list"
    },
    {
      "model": "north-small-translate-09-2026",
      "provider": "cohere",
      "reason": "absent from provider model list"
    },
    {
      "model": "anthropic/claude-sonnet-4",
      "provider": "openrouter",
      "reason": "absent from provider model list"
    },
    {
      "model": "arcee-ai/trinity-large-thinking",
      "provider": "openrouter",
      "reason": "absent from provider model list"
    },
    {
      "model": "deepseek/deepseek-r1",
      "provider": "openrouter",
      "reason": "absent from provider model list"
    },
    {
      "model": "deepseek/deepseek-v4.1-flash-1017-fast",
      "provider": "openrouter",
      "reason": "absent from provider model list"
    },
    {
      "model": "ibm-granite/granite-4.0-h-micro",
      "provider": "openrouter",
      "reason": "absent from provider model list"
    },
    {
      "model": "inclusionai/ling-3.0-flash-fin",
      "provider": "openrouter",
      "reason": "absent from provider model list"
    },
    {
      "model": "inclusionai/ling-3.0-flash-sante",
      "provider": "openrouter",
      "reason": "absent from provider model list"
    },
    {
      "model": "nvidia/nemotron-3.5-super-vl-120b-a12b",
      "provider": "openrouter",
      "reason": "absent from provider model list"
    },
    {
      "model": "poolside/laguna-s-2.1",
      "provider": "openrouter",
      "reason": "absent from provider model list"
    },
    {
      "model": "poolside/laguna-xs-2.1",
      "provider": "openrouter",
      "reason": "absent from provider model list"
    },
    {
      "model": "qwen/qwen3-next-80b-a3b-thinking",
      "provider": "openrouter",
      "reason": "absent from provider model list"
    },
    {
      "model": "sao10k/l3.3-euryale-70b",
      "provider": "openrouter",
      "reason": "absent from provider model list"
    },
    {
      "model": "unbiased/pareto",
      "provider": "openrouter",
      "reason": "absent from provider model list"
    },
    {
      "model": "unbiased/pareto-26.10-preview",
      "provider": "openrouter",
      "reason": "absent from provider model list"
    },
    {
      "model": "upstage/solar-pro-3",
      "provider": "openrouter",
      "reason": "absent from provider model list"
    },
    {
      "model": "wizardlm-2-8x22b",
      "provider": "openrouter",
      "reason": "absent from provider model list"
    },
    {
      "model": "LiquidAI/LFM2.5-8B-A1B",
      "provider": "together",
      "reason": "absent from list + probe not-found",
      "status": 404,
      "detail": "{\n  \"id\": \"p7Xj8uX-2kFHot-a538d46eda8e23ba\",\n  \"error\": {\n    \"message\": \"Unable to access model LiquidAI/LFM2.5-8B-A1B. Please visit https://api.together.ai/mo"
    },
    {
      "model": "nvidia/nemotron-3.5-super-vl-120b-a12b",
      "provider": "together",
      "reason": "absent from list + probe not-found",
      "status": 404,
      "detail": "{\n  \"id\": \"p7Xj8wa-2kFHot-a538d46f3ca82bbd\",\n  \"error\": {\n    \"message\": \"Unable to access model nvidia/nemotron-3.5-super-vl-120b-a12b. Please visit https://ap"
    },
    {
      "model": "grok-voice-2.0",
      "provider": "xAI",
      "reason": "absent from list + probe not-found",
      "status": 404,
      "detail": "{\"code\":\"not-found\",\"error\":\"The model grok-voice-2.0 does not exist or your team a52b2500-3797-4e92-98ad-4b03f9fb00a9 does not have access to it. If you believ"
    },
    {
      "model": "grok-voice-3.0",
      "provider": "xAI",
      "reason": "absent from list + probe not-found",
      "status": 404,
      "detail": "{\"code\":\"not-found\",\"error\":\"The model grok-voice-3.0 does not exist or your team a52b2500-3797-4e92-98ad-4b03f9fb00a9 does not have access to it. If you believ"
    },
    {
      "model": "grok-voice-latest",
      "provider": "xAI",
      "reason": "absent from list + probe not-found",
      "status": 404,
      "detail": "{\"code\":\"not-found\",\"error\":\"The model grok-voice-latest does not exist or your team a52b2500-3797-4e92-98ad-4b03f9fb00a9 does not have access to it. If you bel"
    }
  ],
  "reportOnly": [
    {
      "provider": "bedrock",
      "modelCount": 199
    },
    {
      "provider": "databricks",
      "modelCount": 68
    },
    {
      "provider": "fireworks",
      "modelCount": 287
    },
    {
      "provider": "vertex",
      "modelCount": 118
    }
  ],
  "skipped": [
    {
      "provider": "lepton",
      "reason": "no adapter"
    },
    {
      "provider": "replicate",
      "reason": "no adapter"
    },
    {
      "provider": "typesafe",
      "reason": "no adapter"
    }
  ]
}

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

Project	Deployment	Actions	Updated
ai-proxy	Ready	Preview	Nov 3, 2026 6:54pm UTC

[chatgpt-codex-connector]

Codex Review Summary

This comment shows the latest Codex review activity on this pull request.

Review	Status	Commit	Review trigger
📝 Code Review	✅ Completed 2026-10-30T06:37:26.398728Z	7af48b9	PR opened

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "Codex (@codex) review" or "Codex (@codex) security review".

Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings.

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 7af48b93e2

ℹ️ About Codex in GitHub

Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "Codex (@codex) review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "Codex (@codex) address that feedback".

[chatgpt-codex-connector]

Remove OpenRouter from the unquoted o1 route

When an installation has an OpenRouter credential, this catalog change does not actually stop o1 from being routed there: AvailableEndpointTypes in schema/index.ts still declares the unquoted o1: ["openai", "azure", "openrouter"], and getDirectModelEndpointTypes() prioritizes that mapping over available_providers. The deprecation rewriter only matches quoted keys, so o1 remains eligible for the provider that this audit determined no longer serves it, causing affected requests to continue failing; update the index mapping as well.

Useful? React with 👍 / 👎.