Skip to content

feat: add MiniMax-M2.7 model to provider registry#11982

Draft
roomote-v0[bot] wants to merge 1 commit intomainfrom
feature/add-minimax-m2.7-model
Draft

feat: add MiniMax-M2.7 model to provider registry#11982
roomote-v0[bot] wants to merge 1 commit intomainfrom
feature/add-minimax-m2.7-model

Conversation

@roomote-v0
Copy link
Copy Markdown
Contributor

@roomote-v0 roomote-v0 bot commented Mar 23, 2026

This PR attempts to address Issue #11981.

Changes

Adds the MiniMax-M2.7 model to the MiniMax provider registry with the confirmed specs:

  • Context window: 204,800 tokens
  • Max output: 131,072 tokens
  • Input price: $0.30 per million tokens
  • Output price: $1.20 per million tokens
  • Prompt caching: supported (cache writes: $0.375/M, cache reads: $0.03/M)
  • Images: not supported

The model follows the existing M2-series pattern with search_and_replace as included tool, apply_diff excluded, and preserveReasoning enabled.

Files changed

  • packages/types/src/providers/minimax.ts - Added MiniMax-M2.7 model entry
  • src/api/providers/__tests__/minimax.spec.ts - Added test coverage for the new model

All tests pass (26/26). Feedback and guidance are welcome.

Interactively review PR in Roo Code Cloud

Adds MiniMax-M2.7 with the following specs:
- Context window: 204,800 tokens
- Max output: 131,072 tokens
- Input price: $0.30/M tokens
- Output price: $1.20/M tokens
- Prompt caching: supported
- Images: not supported

Closes #11981
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant