M2.7 Highspeed

LLM

MiniMax

M2.7 Highspeed is built for fast coding, automation, and developer workflows. With 10B parameters and heavy optimization, it runs up to 3x faster than larger models while handling code generation, analytics, and structured out

Context tokens

205,000

Output tokens

131,072

Docs

Model documentation

Released

Apr 2, 2026

Schema

Schema documentation

Capabilities

Tool use

Structured output

Supported tools

Seclai Web Tools
Fetch web pages and search the web from within agent prompt calls. Includes seclai_web_fetch for retrieving page content in markdown, HTML, or plain text, and seclai_web_search for finding relevant pages with content snippets.

Pricing

Type	Credits	Units
Input	—	Credits per 1k tokens
Output	—	Credits per 1k tokens

Variants