feat: upgrade MiniMax default model to M3#202
Open
octo-patch wants to merge 1 commit into
Open
Conversation
- Add MiniMax-M3 to model lists and set as new default - Retain MiniMax-M2.7 and MiniMax-M2.7-highspeed as alternatives - Remove deprecated MiniMax-M2.5 / MiniMax-M2.5-highspeed - Extend think-tag stripping regex to cover M3 alongside M2 - Update README, examples, and tests accordingly
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 MiniMax model configuration to include the latest M3 model as default across docs, examples, and the evaluation framework.
Changes
MiniMax-M3to the model list and set it as the new defaultMiniMax-M2.7andMiniMax-M2.7-highspeedas available alternativesMiniMax-M2.5/MiniMax-M2.5-highspeed) from documentation<think>tag stripping regex inevaluation/agent_loop.pyto coverM3alongsideM2README.md,examples/minimax-integration/, andevaluation/docs/CLI help/tests accordinglyWhy
MiniMax-M3 is the new flagship model with a 512K context window, 128K max output, and image input support across both OpenAI-compatible and Anthropic-compatible interfaces. This change keeps the docs and defaults aligned with the latest recommended SKU while still letting users pick the previous M2.7 family.
Testing
python3 -m unittest test_openai_agent_loop— 19 tests pass (including temperature clamping and<think>tag stripping for M3)evaluation/agent_loop.pyregex matches bothMiniMax-M2.xandMiniMax-M3test_minimax_integration.py) auto-skip without aMINIMAX_API_KEY; their model strings now referenceMiniMax-M3for the smoke and function-calling cases