feat: upgrade MiniMax default model to M3#1859
Open
octo-patch wants to merge 1 commit into
Open
Conversation
- Set MiniMax-M3 as the new default in the API config - Update example to use MiniMax-M3 and refresh the available models list - Retain MiniMax-M2.7 and MiniMax-M2.7-highspeed; drop the deprecated MiniMax-M2.5 and MiniMax-M2.5-highspeed entries from the example MiniMax-M3 is the new flagship model with 512K context window, 128K max output, and image input support across both OpenAI-compatible and Anthropic-compatible interfaces. Co-Authored-By: Octopus <liyuan851277048@icloud.com>
octo-patch
force-pushed
the
feature/upgrade-minimax-m3
branch
from
f33c69b to
b1ba305
Compare
Collaborator
|
Automated Test Results: PASSED Cloud test-engine rerun against
Manual code review is still required before merge. |
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
4 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Upgrades the MiniMax default chat model from M2.7 to M3 in MemOS, following the established pattern from the merged PR #1291 (M2.6 -> M2.7).
M3 is the new MiniMax flagship: 512K context window, 128K max output tokens, and image input support across both the OpenAI-compatible and Anthropic-compatible interfaces exposed by
https://api.minimax.io.Changes
src/memos/api/config.py: DefaultMOS_CHAT_MODELfallback switched fromMiniMax-M2.7toMiniMax-M3inAPIConfig.minimax_config().examples/basic_modules/llm.py: Scenario 7 example updated to useMiniMax-M3, and the "Available models" comment refreshed to list the current supported set.Model support matrix
MiniMax-M3MiniMax-M2.7MiniMax-M2.7-highspeedMiniMax-M2.5MiniMax-M2.5-highspeedM2.7andM2.7-highspeedare intentionally kept: the change only flips the default whenMOS_CHAT_MODELis unset; users who pin a specific model via env var are unaffected. TheMinimaxLLMandMinimaxLLMConfigclasses are untouched, and no API URL or provider wiring changes are introduced.Scope
tests/llms/test_minimax.py,tests/configs/test_llm.py) continues to exercise M2.7 / M2.7-highspeed and is unchanged.Verification
python -m pytest tests/llms/test_minimax.py tests/configs/test_llm.pycontinues to pass (existing tests pin M2.7 / M2.7-highspeed, both still valid).MiniMax-M3is reachable via the OpenAI-compatible endpoint athttps://api.minimax.io/v1.