feat(wafer/MiniMax-M3): add new models [bot]#1592
Conversation
|
/test-models |
Gateway test setup failed for
|
There was a problem hiding this comment.
Cursor Bugbot has reviewed your changes and found 1 potential issue.
❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.
Reviewed by Cursor Bugbot for commit f416fe1. Configure here.
| - text | ||
| - image | ||
| - video | ||
There was a problem hiding this comment.
Unsupported PDF modality listed
Medium Severity
The new MiniMax-M3 entry lists pdf under input modalities, but MiniMax M3’s documented multimodal inputs are text, image, and video. Other MiniMax-M3 configs in this repo omit pdf, so consumers may treat PDF uploads as supported when the underlying API likely rejects them.
Reviewed by Cursor Bugbot for commit f416fe1. Configure here.


Auto-generated by model-addition-agent for
wafer/MiniMax-M3.Note
Low Risk
Single new YAML catalog entry with no runtime, auth, or application logic changes.
Overview
Adds a new wafer provider definition for
MiniMax-M3, registering it as an active serverless chat model with thinking enabled.The entry includes pay-as-you-go token pricing (including cache-read input), a 1M-token context window, multimodal inputs (text, image, video, PDF), and capabilities for function calling and prompt caching, with links to MiniMax pricing and M3 documentation as sources.
Reviewed by Cursor Bugbot for commit f416fe1. Bugbot is set up for automated code reviews on this repo. Configure here.