Skip to content

Python: Add MiniMax AI connector with M2.7 default model#13662

Open
octo-patch wants to merge 2 commits intomicrosoft:mainfrom
octo-patch:feature/add-minimax-provider
Open

Python: Add MiniMax AI connector with M2.7 default model#13662
octo-patch wants to merge 2 commits intomicrosoft:mainfrom
octo-patch:feature/add-minimax-provider

Conversation

@octo-patch
Copy link

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

Summary

  • Add MiniMax AI connector for chat completion via OpenAI-compatible API
  • Support MiniMax-M2.7 (default), MiniMax-M2.7-highspeed, MiniMax-M2.5, and MiniMax-M2.5-highspeed models
  • MiniMax-M2.7 is the latest flagship model with enhanced reasoning and coding capabilities

Changes

  • MiniMax chat completion service with streaming support
  • MiniMax prompt execution settings with temperature clamping
  • MiniMax settings with environment variable configuration
  • Handler for OpenAI-compatible API communication
  • Comprehensive unit tests (16 tests)
  • README documentation with usage examples

Testing

  • All 16 unit tests passing
  • Integration tested with MiniMax API

Add a new AI connector for MiniMax, a cloud-based LLM provider offering
OpenAI-compatible API. This follows the same pattern as the existing NVIDIA
connector, using the AsyncOpenAI client with a custom base URL.

New connector includes:
- MiniMaxChatCompletion service with streaming support
- MiniMaxSettings for configuration via env vars (MINIMAX_API_KEY, etc.)
- MiniMaxChatPromptExecutionSettings with MiniMax-specific constraints
- Unit tests for settings, prompt execution settings, and chat completion
- README with quick-start guide and available models

Supported models: MiniMax-M2.5, MiniMax-M2.5-highspeed (204K context)
API endpoint: https://api.minimax.io/v1
@octo-patch octo-patch requested a review from a team as a code owner March 15, 2026 15:38
- 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
- Update related tests and documentation
@octo-patch octo-patch changed the title Python: Add MiniMax AI connector for chat completion Python: Add MiniMax AI connector with M2.7 default model Mar 18, 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.

1 participant