M2.1

LLM

MiniMax

MiniMax M2.1 is an open-weight agentic coding model excelling at multilingual programming, tool use, and real-world office automation with advanced interleaved thinking and strong full-stack development.

Context tokens

196,000

Output tokens

32,768

Docs

Model documentation

Released

Dec 23, 2025

Schema

Anthropic-compatible chat format.

Schema documentation

Capabilities

Tool use

Structured output

Thinking

Multilingual

Supported languages

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	3.99	Credits per 1k tokens
Output	15.96	Credits per 1k tokens

Variants