chore: add DeepSeek V4.1 Flash and other missed models to the known models catalog - #29585
Merged
Merged
Conversation
…odels catalog Add the models that landed on models.dev since the September 4 curation pass, plus cross-provider gaps where a model was curated on one provider but not on the others that serve it. Claude Mythos 5.1 is injected in overrides.jq as a copy of claude-fable-5-1, mirroring the existing claude-mythos-5 injection, and added to the Anthropic thinking-mode pin. knownModelsGenerated.json and prices.json are regenerated with make gen/aibridge-prices from the same models.dev snapshot.
Codex Review SummaryThis comment shows the latest Codex review activity on this pull request.
ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings. |
Collaborator
Author
|
@codex review |
|
Codex Review: Didn't find any major issues. Delightful! Reviewed commit: ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
If Codex has suggestions, it will comment; otherwise it will react with 👍. Codex can also answer questions or update the PR. Try commenting "@codex address that feedback". |
ThomasK33
approved these changes
Sep 18, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Add the models that landed on models.dev since the September 4 curation pass (#28955), plus cross-provider gaps where a model was curated on one provider but not on the others that serve it, so they appear as suggestions when an admin adds a chat model in
/agentssettings.overrides.jqas a copy ofclaude-fable-5-1, mirroring the existingclaude-mythos-5injection. Anthropic's pricing page lists Mythos 5.1 at the same rates as Fable 5.1, including the reduced cache-read rate.global.alias), openrouter, vercelMythos 5.1 uses
reasoningEffort: highlike Fable 5.1 and is added to the Anthropic thinking-mode pin inknownModelsGenerated.test.ts. Gateway entries follow the existing convention: no reasoning default and upstream display names. New entries sort ahead of the models they supersede.Deliberately not added:
openai.*models on Bedrock (chatd's Bedrock provider wraps the Anthropic client, so they cannot be used from Coder Agents), models.dev's~-prefixed rolling aliases on OpenRouter, andcopilot(unsupported in chatd).knownModelsGenerated.jsonandcoderd/aibridge/prices/data/prices.jsonare regenerated withmake gen/aibridge-pricesfrom the same models.dev snapshot. Apart from theclaude-mythos-5-1row, theprices.jsonchanges are upstream drift since the last weekly refresh, the same content the scheduled refresh PR would produce.Validation:
go test ./scripts/aibridgepricesgen/... ./coderd/aibridge/prices/...andpnpm test src/modules/aiModels/(174 tests) pass.