fix(agent): use standard MiniMax-M2.7 for auxiliary model instead of highspeed#4115
Closed
shannonsands wants to merge 1 commit into
Closed
fix(agent): use standard MiniMax-M2.7 for auxiliary model instead of highspeed#4115shannonsands wants to merge 1 commit into
shannonsands wants to merge 1 commit into
Conversation
…highspeed MiniMax-M2.7-highspeed is the same model running on faster hardware at 2x the price ($0.60/$2.40 per M tokens vs $0.30/$1.20). For auxiliary tasks like summarization and compression where throughput is not critical, the standard variant is the correct default. Closes #4082
8 tasks
Contributor
|
Fixed in PR #6082 — aux model switched from highspeed to standard. Thanks! |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What does this PR do?
Changes the default MiniMax auxiliary model from
MiniMax-M2.7-highspeedtoMiniMax-M2.7. The highspeed variant is the same model running on faster hardware at exactly 2x the price — users with MiniMax as their provider are silently paying double for every auxiliary call (summarization, compression, vision).For auxiliary side tasks where latency is not critical, the standard tier is the correct default.
Source: OpenRouter pricing, MiniMax pricing docs
Related Issue
Fixes #4082
Type of Change
Changes Made
agent/auxiliary_client.pylines 59-60:MiniMax-M2.7-highspeed→MiniMax-M2.7for bothminimaxandminimax-cnentries in_API_KEY_PROVIDER_AUX_MODELSHow to Test
MiniMax-M2.7(notMiniMax-M2.7-highspeed) in logsChecklist
Code
pytest tests/ -qand all tests pass — N/A (config value change, no logic affected)Documentation & Housekeeping
cli-config.yaml.example— N/ACONTRIBUTING.mdorAGENTS.md— N/A