feat: upgrade MiniMax default model to M3#753
Open
octo-patch wants to merge 3 commits into
Open
Conversation
Add first-class support for MiniMax LLM models (MiniMax-M2.5, MiniMax-M2.5-highspeed) via their OpenAI-compatible API endpoint. Changes: - Auto-detect MINIMAX_API_KEY env var and configure the API endpoint - Temperature clamping for MiniMax models (0.0 → 0.01) since MiniMax requires temperature in (0.0, 1.0] - Documentation in README with usage examples and Docker setup - 5 unit tests + 3 integration tests Co-Authored-By: Octopus <liyuan851277048@icloud.com>
- Update default model from MiniMax-M2.5 to MiniMax-M2.7 in README examples - Add MiniMax-M2.7 and MiniMax-M2.7-highspeed to available models list - Update unit tests to use M2.7 as primary model - Update integration tests to use M2.7 as primary model - Add backward compatibility tests for MiniMax-M2.5 - Keep all previous models as available alternatives
octo-patch
changed the title
- Promote MiniMax-M3 to the recommended default in README and examples - Add MiniMax-M3 unit/integration tests; remove M2.5 references - Keep MiniMax-M2.7 and MiniMax-M2.7-highspeed as alternatives
octo-patch
changed the title
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Upgrade the existing MiniMax provider integration to use
MiniMax-M3as the recommended default model while keepingMiniMax-M2.7/MiniMax-M2.7-highspeedas alternatives.Changes
README.md: defaultDEFAULT_MODELswitched toMiniMax-M3(env, config file, and Docker example) and model lineup updated to list M3 firsttests/test_minimax.py: default-model temperature clamping and chat-mode tests useMiniMax-M3; the previous-generation test now exercisesMiniMax-M2.7tests/test_minimax_integration.py: real-API integration tests useMiniMax-M3(default prompt, code generation, temperature); the previous-generation case exercisesMiniMax-M2.7MiniMax-M2.5/MiniMax-M2.5-highspeedWhy
MiniMax-M3is the latest flagship: 512K context window, up to 128K output, and image input support. Promoting it as the default showcases the new model and matches the upgrade guidance, while keepingMiniMax-M2.7available for users who prefer the previous generation.Testing
tests/test_minimax.pypassTestMiniMaxIntegrationupdated and structured identically (skips whenMINIMAX_API_KEYis unset)