Skip to content
This repository was archived by the owner on Jun 2, 2026. It is now read-only.

feat: upgrade MiniMax default model to M3#950

Open
octo-patch wants to merge 5 commits into
voideditor:mainfrom
octo-patch:feature/add-minimax-provider
Open

feat: upgrade MiniMax default model to M3#950
octo-patch wants to merge 5 commits into
voideditor:mainfrom
octo-patch:feature/add-minimax-provider

Conversation

@octo-patch
Copy link
Copy Markdown

@octo-patch octo-patch commented Mar 15, 2026

Summary

Upgrade the MiniMax provider's default model to MiniMax-M3, the latest flagship release.

Changes

  • Add MiniMax-M3 to the model selection list and set it as the default
  • Keep MiniMax-M2.7 and MiniMax-M2.7-highspeed as alternatives
  • Remove older models (MiniMax-M2.5 / MiniMax-M2.5-highspeed)
  • Update the model fallback handler to route unknown MiniMax models to M3

Models

Model Context Reserved Output Input Output Cache Read
MiniMax-M3 (default) 512K 16K $0.60/M $2.40/M $0.12/M
MiniMax-M2.7 204K 8K $0.30/M $1.20/M
MiniMax-M2.7-highspeed 204K 8K $0.60/M $2.40/M

Why

MiniMax-M3 is the latest MiniMax model with a 512K context window, up to 128K max output, and image input support. Older M2.5 variants are superseded and removed; M2.7 family is retained for users who need the previous behavior.

Testing

  • Model list updated and statically validated against VoidStaticModelInfo (via satisfies)
  • Fallback handler routes unknown MiniMax model names to MiniMax-M3
  • OpenAI-compatible endpoint unchanged: https://api.minimax.io/v1

octo-patch and others added 4 commits March 15, 2026 21:11
- Add MiniMax-M2.7 and MiniMax-M2.7-highspeed to model list
- Set MiniMax-M2.7 as default model
- Keep all previous models as alternatives
@octo-patch octo-patch changed the title feat: add MiniMax provider support feat: add MiniMax provider support with M2.7 default model Mar 18, 2026
- Add MiniMax-M3 to model list and set as default (512K context, 16K reserved output)
- Keep MiniMax-M2.7 and MiniMax-M2.7-highspeed as alternatives
- Remove older models (M2.5/M2.5-highspeed)
- Update fallback handler to route unknown MiniMax models to M3
@octo-patch octo-patch changed the title feat: add MiniMax provider support with M2.7 default model feat: upgrade MiniMax default model to M3 Jun 2, 2026
@sonarqubecloud
Copy link
Copy Markdown

sonarqubecloud Bot commented Jun 2, 2026

@andrewpareles andrewpareles force-pushed the main branch 11 times, most recently from 360390b to b3166e7 Compare June 2, 2026 22:03
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant