MiniMax M2.5 Highspeed

by MiniMax · chat

Low-latency version of MiniMax M2.5, 2x faster for production environments requiring minimum latency

Pricing

Input: $0.558/M tokens · Output: $2.232/M tokens

Capabilities

Function Calling, JSON Mode, Streaming, Reasoning

Context: 205K tokens

Max output: 33K tokens

Routes: 1/1 healthy