miniMax-M3.1-Flash
Call the MiniMax-M3.1-Flash OpenAI-compatible chat model via the baze platform. The model supports a 1,000,000-token context window with text, image, and video inputs. Thinking is always on; tune its depth with reasoning_effort. The same model is also available through POST /v1/messages and POST /v1/responses.
POST
Authorizations
Body
application/json
Thinking depth level. MiniMax-M3.1-Flash always thinks and cannot disable it, so this field is the only way to control depth. Higher values produce more output tokens and longer waits. Defaults to max when omitted. On the Responses path, express the same setting with reasoning.effort.
Available options:
low, medium, high, xhigh, max