Skip to content

feat: upgrade MiniMax default model to M3#1882

Open
octo-patch wants to merge 3 commits into
sinaptik-ai:mainfrom
octo-patch:feature/add-minimax-provider
Open

feat: upgrade MiniMax default model to M3#1882
octo-patch wants to merge 3 commits into
sinaptik-ai:mainfrom
octo-patch:feature/add-minimax-provider

Conversation

@octo-patch
Copy link
Copy Markdown

@octo-patch octo-patch commented Mar 14, 2026

Summary

Upgrade the MiniMax LLM extension to use MiniMax-M3 as the default model.

Changes

  • Add MiniMax-M3 to the model list and set as the default (512K context, 128K max output, supports image input)
  • Keep MiniMax-M2.7 and MiniMax-M2.7-highspeed as alternatives
  • Remove older models MiniMax-M2.5 and MiniMax-M2.5-highspeed
  • Update unit tests (M3 default model assertions, M2.5 test cases replaced with M3)
  • Update README.md and docs/v3/large-language-models.mdx

Files Changed

File Description
extensions/llms/minimax/pandasai_minimax/minimax.py Model list, default, docstring
extensions/llms/minimax/tests/test_minimax.py Updated default + model coverage tests
extensions/llms/minimax/README.md Models table updated
docs/v3/large-language-models.mdx Supported models line updated

Why

MiniMax-M3 is the latest generation model, with a 512K context window, 128K max output, and image input support.

Test Plan

  • All 16 unit tests pass

octo-patch and others added 3 commits March 14, 2026 11:33
Add a new LLM extension for MiniMax (https://www.minimaxi.com/), providing
support for MiniMax-M2.5 and MiniMax-M2.5-highspeed models with up to 204K
context window via an OpenAI-compatible API.

Changes:
- Add extensions/llms/minimax/ with MiniMax LLM class extending BaseOpenAI
- Add unit tests for MiniMax extension (15 tests)
- Update LLM documentation with MiniMax setup instructions
Add MiniMax-M2.7 and MiniMax-M2.7-highspeed models as the new default,
while retaining backward compatibility with M2.5 models.
- Add MiniMax-M3 to model list and set as default
- Keep MiniMax-M2.7 and MiniMax-M2.7-highspeed
- Remove older models (M2.5/M2.5-highspeed)
- Update related tests
@dosubot dosubot Bot added the size:L This PR changes 100-499 lines, ignoring generated files. label Jun 2, 2026
@octo-patch octo-patch changed the title feat: add MiniMax LLM extension feat: upgrade MiniMax default model to M3 Jun 2, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

size:L This PR changes 100-499 lines, ignoring generated files.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant