MiniMax-M2.7-highspeed

Operational
Reasoning
Tools
Open weights
200K

Standard & Paid Price

Standard Price
MeterStandard Price
Input price$0.6000 / 1M tokens
Completion price$2.4000 / 1M tokens
Cache read price$0.0600 / 1M tokens
Cache creation price$0.3750 / 1M tokens
Billing details

Description

MiniMax M2.7 Highspeed — the same M2.7 model served at roughly 100 tokens per second for low-latency coding and agent workflows, with a 204,800-token context window. Text only: the API accepts text and tool-call content blocks, not images or video. Supports tool calling; thinking is always on and cannot be disabled.

Capabilities

Input modalities
text
Output modalities
text
Tasks
chat, reasoning

API endpoints

  • POST /v1/messages (anthropic)
  • POST /v1/chat/completions (openai)