-
Notifications
You must be signed in to change notification settings - Fork 2.8k
feat: add MiniMax-M2-Stable model and enable prompt caching #9072
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Merged
Conversation
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
- Add MiniMax-M2-Stable model for high concurrency commercial use - Enable prompt caching for both MiniMax-M2 and MiniMax-M2-Stable models - Update pricing information for cache reads (0.03/M tokens) and writes (0.375/M tokens) - Update tests to cover new model and caching support Fixes #9070
Contributor
Author
Re-review complete. Latest changes look good - the description update is a minor documentation improvement with no functional impact. The implementation correctly:
Mention @roomote to ask your PR Fixer agent to address the feedback. |
2 tasks
Removed 'Limited-time Free' from MiniMax M2 description.
daniel-lxs
approved these changes
Nov 6, 2025
daniel-lxs
approved these changes
Nov 6, 2025
cte
approved these changes
Nov 6, 2025
mini2s
added a commit
to zgsm-ai/costrict
that referenced
this pull request
Nov 7, 2025
Related GitHub Issue
Closes: #9070
Roo Code Task Context (Optional)
N/A - This PR was created by an automated workflow.
Description
This PR addresses the enhancement request to add the new MiniMax-M2-Stable model option and enable prompt caching support for MiniMax provider models.
Key implementation details:
Test Procedure
Automated Tests:
Manual Verification:
All automated tests are passing (19 tests).
Pre-Submission Checklist
Screenshots / Videos
N/A - This is a backend change for model configuration.
Documentation Updates
The changes are self-documenting through the model configuration and descriptions.
Additional Notes
This implementation follows the pricing and specifications provided in the MiniMax official documentation:
Feedback and guidance are welcome!
Get in Touch
N/A - Automated workflow
Important
Add
MiniMax-M2-Stablemodel and enable prompt caching for MiniMax models with updated tests.MiniMax-M2-Stablemodel tominimax.tswith specs identical toMiniMax-M2.MiniMax-M2andMiniMax-M2-Stablewith specific cache pricing.minimax.spec.tsto verifyMiniMax-M2-Stableconfiguration and prompt caching.This description was created by
for 7a93d2d. You can customize this summary. It will automatically update as commits are pushed.