LLM ReferenceLLM Reference

MiniMax M2.7 Highspeed

minimax-m2.7-highspeed

Proprietary

About

MiniMax M2.7 Highspeed is the inference-optimized variant of MiniMax M2.7, released simultaneously on March 18, 2026. It reaches 100 tokens per second output speed, about 66% faster than standard M2.7, while preserving identical intelligence and outputs through engine optimization rather than weight changes. It supports a 204,800-token context window, 131,072-token max output, function calling, structured output, and reasoning. API model ID: MiniMax-M2.7-highspeed.

MiniMax M2.7 Highspeed has a 200K-token context window.

Capabilities

VisionMultimodalReasoningFunction CallingTool UseStructured OutputsCode ExecutionPrompt CachingBatch APIAudioFine-tuning

Providers(1)

ProviderInput (per 1M)Output (per 1M)Type
MiniMaxServerless

Rankings

Specifications

Released2026-03-18
Parameters10B active
Context205K
Max output131,072
ArchitectureDecoder Only
Specializationgeneral
LicenseProprietary

Created by

Developing AI for gaming and entertainment.

Minhang, Shanghai, China
Founded 2021
Website

Providers(1)