docs: sync README 'Available models' with docs.weco.ai - #165
docs: sync README 'Available models' with docs.weco.ai#165ZhengyaoJiang wants to merge 1 commit into
Conversation
The README's model list had drifted from the canonical list at docs.weco.ai/reference/supported-models. Adds the missing providers and models, and points readers at the docs as the source of truth. - Anthropic: add claude-opus-4-8 - Gemini: add gemini-3.5-flash, gemini-3.1-flash-lite-preview - Add the Concentrate AI section (kimi-k2-6/k2-5, minimax-m3/m2-7/m2-5, glm-5.1/glm-5, plus the concentrate/-prefixed proxied models) - Add the Kimi (Moonshot) section (kimi-k2.7-code) - Correct the no-model-specified behaviour: Weco uses the default model gemini-3-flash-preview rather than "automatically selects the best model" Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: e70adf89a4
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 review".
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".
|
|
||
| - `kimi-k2.7-code` — thinking-only coding model with a 256K context window | ||
|
|
||
| All models are available through Weco. If no model is specified, Weco uses the default model `gemini-3-flash-preview`. |
There was a problem hiding this comment.
When users pass --api-key without --model, this statement is incorrect: weco/cli.py calls get_default_model(api_keys=api_keys), which selects o4-mini for OpenAI keys and claude-opus-4-5 for Anthropic keys (and the CLI help explicitly documents this behavior). This newly changed wording can therefore cause BYOK users to expect Gemini even though their run will use a different provider's default.
Useful? React with 👍 / 👎.
1 participant
The README's Available models section had drifted from the canonical list at docs.weco.ai/reference/supported-models. This syncs it and adds a pointer to the docs so the next drift is self-correcting.
Changes
claude-opus-4-8gemini-3.5-flash,gemini-3.1-flash-lite-previewkimi-k2-6,kimi-k2-5,minimax-m3,minimax-m2-7,minimax-m2-5,glm-5.1,glm-5, plus theconcentrate/-prefixed proxied modelskimi-k2.7-codegemini-3-flash-preview(the previous "automatically selects the best model for your optimization task" was not accurate)Docs-only; no code paths touched.
🤖 Generated with Claude Code