M2.7

LLM

MiniMax

M2.7 is designed for agentic tasks and coding. It supports text and image inputs, offers a 1M-token context window, and delivers strong performance in tool use, planning, and complex multi-step workflows.

Context tokens

1,000,192

Output tokens

8,192

Docs

Model documentation

Released

Mar 17, 2026

Schema

Tool choice is limited to automatic or disabled.

Schema documentation

Capabilities

Tool use

Structured output

Multilingual

Multimodal

Supported languages

Supported input media

image

text

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
Cache hit	0.80	Credits per 1k tokens

Variants