feat: upgrade MiniMax default model to M3#245
Open
octo-patch wants to merge 2 commits into
Open
Conversation
added 2 commits
April 14, 2026 15:16
…tely - Add scira-minimax-m2.7 mapped to MiniMax-M2.7 (Peak Performance model) - Add scira-minimax-m2.7-highspeed mapped to MiniMax-M2.7-highspeed (faster variant) - Update model descriptions to reflect capabilities - Add MINIMAX_API_KEY to .env.example documentation - Set temperature to 1.0 for both models per MiniMax API constraints
- Add MiniMax-M3 to model list as the primary/default MiniMax model - Keep MiniMax-M2.7 and MiniMax-M2.7-highspeed as alternatives - Remove older models (M1, M2, M2.1, M2.1-lightning, M2.5) - Update README Minimax model list - Enable image input (vision) for M3
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 MiniMax integration to make MiniMax-M3 the primary model, keep
MiniMax-M2.7andMiniMax-M2.7-highspeedas alternatives, and drop older M1/M2/M2.1/M2.5 entries that no longer reflect Minimax's current lineup.Changes
ai/models.tsscira-minimax-m3→MiniMax M3as the first MiniMax entry (markedisNew: true,vision: truefor image input)scira-minimax-m2.7andscira-minimax-m2.7-highspeed(no longer flaggedisNew)scira-minimax(M1 80K),scira-minimax-m2,scira-minimax-m2.1,scira-minimax-m2.1-lightning,scira-minimax-m2.5ai/providers.ts'scira-minimax-m3': minimax.chatModel('MiniMax-M3')directly on the OpenAI-compatible MiniMax client (https://api.minimax.io/v1)README.mdM3, M2.7, M2.7 Highspeed.env.example(from prior commit on this branch)MINIMAX_API_KEYis documented for new contributorsWhy M3?
MiniMax-M3is Minimax's latest flagship model:https://api.minimax.io/v1base URL andMINIMAX_API_KEYalready wired up for M2.7Removing the M1/M2/M2.1/M2.5 entries cleans up the model picker around the current lineup and keeps the registry pointed at routes that Minimax still actively maintains.
Testing
git diff --stat upstream/main..HEADkeeps the change tightly scoped to model registration (3 source files + .env.example).MINIMAX_API_KEYset:scira-minimax-m3resolves throughminimax.chatModel('MiniMax-M3')and returns streaming completions;scira-minimax-m2.7/-highspeedcontinue to work unchanged.API References