M2

LLM
MiniMax

MiniMax M2 is a text model built for agentic workflows and coding. It handles long-context tasks up to 1M tokens, excels at multi-step tool calling, and supports end-to-end development across tools like Cursor and Claude Code.

Context tokens

1,000,192

Output tokens

8,192

Released

Jun 16, 2025

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

TypeCreditsUnits
Input3.99Credits per 1k tokens
Output15.96Credits per 1k tokens

Variants

No variants available for this model.

Try This Model

Write a prompt and experiment with M2 in the model experiments page. You can compare it with other models side by side.