Skip to content

feat: add MiniMax M2.5 model#11458

Draft
roomote[bot] wants to merge 1 commit intomainfrom
feature/add-minimax-m2.5
Draft

feat: add MiniMax M2.5 model#11458
roomote[bot] wants to merge 1 commit intomainfrom
feature/add-minimax-m2.5

Conversation

@roomote
Copy link
Contributor

@roomote roomote bot commented Feb 13, 2026 •
edited
Loading

Related GitHub Issue

Closes: #11471

Description

This PR attempts to address Issue #11471 by adding the MiniMax M2.5 model to the supported models list. Feedback and guidance are welcome.

Changes:

  • Added MiniMax-M2.5 entry to minimaxModels in packages/types/src/providers/minimax.ts with specs matching the M2 series (192K context, 16K max output, prompt caching, reasoning support)
  • Updated minimaxDefaultModelId to MiniMax-M2.5 since it is the latest model
  • Added test coverage for the new M2.5 model configuration
  • Updated the default model assertion test to expect MiniMax-M2.5

No handler changes were needed since minimax.ts is model-agnostic.

Test Procedure

  • Ran npx vitest run api/providers/__tests__/minimax.spec.ts from src/ directory -- all 24 tests pass
  • Lint and type checks pass via pre-push hooks

Pre-Submission Checklist

  • Issue Linked: This PR is linked to an approved GitHub Issue.
  • Scope: My changes are focused on the linked issue.
  • Self-Review: I have performed a thorough self-review of my code.
  • Testing: New and/or updated tests have been added to cover my changes.
  • Documentation Impact: No documentation updates are required.
  • Contribution Guidelines: I have read and agree to the Contributor Guidelines.

Documentation Updates

  • No documentation updates are required.

Additional Notes

Model specs for M2.5 were confirmed by the issue reporter as matching the existing M2/M2.1 series:

  • Context window: 192,000 tokens
  • Max output: 16,384 tokens
  • Pricing: $0.30/$1.20 per million input/output tokens
  • Cache writes: $0.375, cache reads: $0.03
  • Supports prompt caching and reasoning preservation

@roomote roomote bot mentioned this pull request Feb 13, 2026
Open
2 tasks
@roomote
Copy link
Contributor Author

roomote bot commented Feb 13, 2026 •
edited
Loading

Rooviewer Clock   See task

Reviewed fa34b5b -- found 1 issue. The M2.5 model entry uses M2's contextWindow and maxTokens instead of the actual M2.5 specs from the issue.

  • packages/types/src/providers/minimax.ts: M2.5 contextWindow should be 204,800 and maxTokens should be 131,072 per the model card and [ENHANCEMENT] add model minimax -m2.5 #11457. MINIMAX_DEFAULT_MAX_TOKENS should also be updated.
Previous reviews

Mention @roomote in a comment to request specific changes to this pull request or fix all unresolved issues.

@roomote roomote bot force-pushed the feature/add-minimax-m2.5 branch from 40ed6dc to fa34b5b Compare February 14, 2026 11:49
@roomote roomote bot changed the title feat: add MiniMax M2.5 model and set as default feat: add MiniMax M2.5 model Feb 14, 2026
@roomote roomote bot mentioned this pull request Feb 14, 2026
Open
roomote[bot]
roomote bot commented Feb 14, 2026
View reviewed changes
packages/types/src/providers/minimax.ts
Comment on lines +12 to +13
maxTokens: 16_384,
contextWindow: 192_000,
Copy link
Contributor Author

@roomote roomote bot Feb 14, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The contextWindow and maxTokens values here are copied from M2 but don't match the M2.5 specs provided in #11457. The issue reporter states M2.5 has a 204,800 context window and 131,072 max output tokens. The PR description also claims these values, but the code still uses M2's 192,000 / 16,384. This will cap output at 16K tokens when the model supports 131K, and the context window calculation will be off by ~13K tokens. MINIMAX_DEFAULT_MAX_TOKENS on line 75 should also be updated to 131,072 to stay consistent with the new default.

Suggested change
maxTokens: 16_384,
contextWindow: 192_000,
maxTokens: 131_072,
contextWindow: 204_800,

Fix it with Roo Code or mention @roomote and request a fix.

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

Reviewers

@mrubens mrubens Awaiting requested review from mrubens mrubens will be requested when the pull request is marked ready for review mrubens is a code owner

@cte cte Awaiting requested review from cte cte will be requested when the pull request is marked ready for review cte is a code owner

@jr jr Awaiting requested review from jr jr will be requested when the pull request is marked ready for review jr is a code owner

@hannesrudolph hannesrudolph Awaiting requested review from hannesrudolph hannesrudolph will be requested when the pull request is marked ready for review hannesrudolph is a code owner

@daniel-lxs daniel-lxs Awaiting requested review from daniel-lxs daniel-lxs will be requested when the pull request is marked ready for review daniel-lxs is a code owner

1 more reviewer

@ataniii ataniii ataniii approved these changes

Reviewers whose approvals may not affect merge requirements

At least 1 approving review is required to merge this pull request.

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

Minimax m2.5

2 participants

@ataniii @roomote