Skip to content

feat: upgrade MiniMax default model to M3#191

Open
octo-patch wants to merge 2 commits into
shareAI-lab:mainfrom
octo-patch:feature/add-minimax-m2.7-provider
Open

feat: upgrade MiniMax default model to M3#191
octo-patch wants to merge 2 commits into
shareAI-lab:mainfrom
octo-patch:feature/add-minimax-m2.7-provider

Conversation

@octo-patch
Copy link
Copy Markdown

@octo-patch octo-patch commented Apr 7, 2026

Summary

Upgrade MiniMax provider defaults to use the latest MiniMax-M3 as the recommended model.

Changes

  • Add MiniMax-M3 as the default in the provider table of .env.example
  • Keep MiniMax-M2.7 and MiniMax-M2.7-highspeed as alternatives
  • Apply changes to both international (api.minimax.io) and China mainland (api.minimaxi.com) endpoint examples
  • Replace the previously suggested MiniMax-M2.5 line with MiniMax-M3

Why

MiniMax-M3 is the latest generation with a 512K context window, up to 128K output, and image input support. Keeping the provider example in sync with the current model lineup helps new users start with the recommended model.

Models

Model ID Description
MiniMax-M3 Latest generation. 512K context, 128K max output, image input (default)
MiniMax-M2.7 Peak Performance. Ultimate Value. Master the Complex
MiniMax-M2.7-highspeed Same performance, faster and more agile

API Reference

Testing

  • Smoke tests pass: pytest tests/ (15/15)
  • .env.example validated for both international and China mainland endpoints

- Update provider table in .env.example to reference MiniMax-M2.7
- Add MiniMax-M2.7-highspeed as a faster alternative variant
- Apply changes to both international (api.minimax.io) and China mainland (api.minimaxi.com) endpoints
@vercel
Copy link
Copy Markdown

vercel Bot commented Apr 7, 2026

@octo-patch is attempting to deploy a commit to the crazyboym's projects Team on Vercel.

A member of the Team first needs to authorize it.

@tourclassic567-glitch
Copy link
Copy Markdown

tourclassic567-glitch commented Apr 7, 2026 via email

- Add MiniMax-M3 as the default model in .env.example
- Keep MiniMax-M2.7 and MiniMax-M2.7-highspeed as alternatives
- Update both international (api.minimax.io) and China mainland (api.minimaxi.com) endpoint examples
- Remove implicit reference to older MiniMax-M2.5 line
@octo-patch octo-patch changed the title feat: upgrade MiniMax provider to M2.7 feat: upgrade MiniMax default model to M3 Jun 2, 2026
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.

2 participants