ORorthogonal
MiniMax

Same quality as M2.7 at ~100 tps, 204.8k context. OpenAI-compatible Chat Completions. The model is fixed to MiniMax-M2.7-highspeed; stream is fixed to false and service_tier to standard.

Changed on
post/minimax-08853f/v1/chat/completions/minimax-m2.7-highspeed

Request

  • Base URL
    https://api.orthogonal.com/mpp
  • Auth
    none declared

Request body

messagesstring[] required

Conversation messages (OpenAI format). Supports text, image and video content parts plus tool call/result messages.

max_completion_tokensinteger

Max output tokens.

temperaturenumber

Sampling temperature [0,2], default 1.

top_pnumber

Nucleus sampling [0,1].

toolsstring[]

Function tool definitions (type: function).

tool_choicestring

Tool choice behavior.

thinkingobject

Thinking control, e.g. {"type":"adaptive"} or {"type":"disabled"} (model dependent).

reasoning_splitboolean

If true, reasoning is returned in reasoning_content instead of <think> tags.

Response

Successful response

Changes