feat(minimax): default MiniMax model to M3#257
Merged
Conversation
MiniMax released M3 as the new flagship model. Update the default MiniMax model id from M2.7 to M3 in the quickstart example, the plugin reference docs, and the test fixtures. Drop the unit-test coverage for the deprecated M2.5 / M2.5-highspeed variants and keep a single test that exercises M2.7 as a legacy fallback. API URL, env-var, mode, and assistant role are unchanged.
Eigenwise
approved these changes
Jun 3, 2026
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
MiniMax released M3 as the new flagship model. This PR updates the default MiniMax model id from
MiniMax-M2.7toMiniMax-M3so new users land on the recommended model out of the box.What changed
atomic-examples/quickstart/quickstart/4_basic_chatbot_different_providers.py— provider example now usesMiniMax-M3claude-plugin/atomic-agents/skills/framework/references/providers.md— reference snippet usesM3; comment notesM2.7is still available as a legacy optionatomic-agents/tests/agents/test_minimax_provider.py— default in unit tests bumped toM3;test_minimax_m25_modelandtest_minimax_m25_highspeed_model(both deprecated variants) replaced by a singletest_minimax_m27_legacy_modelthat pins continued support forM2.7atomic-agents/tests/agents/test_minimax_integration.py— integration helper default and the structured-output test pin toMiniMax-M3What did not change
https://api.minimax.io/v1base URLMINIMAX_API_KEYenv var nameMode.JSONInstructor mode andassistant_role="assistant"Test plan
pytest atomic-agents/tests/agents/test_minimax_provider.py -v— 14 passedpytest atomic-agents/tests— 321 passed (no regressions in the rest of the suite)black --check --line-length=127— cleanflake8 --max-line-length=127— 0 errorshttps://api.minimax.io/v1withmodel="MiniMax-M3"reaches the API (request accepted; only blocked by account balance on this side)