MinimaxfastTool use

MiniMax M2

MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-frontier intelligence across general reasoning, tool use, and multi-step task execution while maintaining low latency and deployment efficiency. The model excels in code generation, multi-file editing, compile-run-fix loops, and test-validated repair, showing strong results on SWE-Bench Verified, Multi-SWE

200K context·~150K words·8K max output
Context window200Ktokens
Max output8Ktokens

Context window

This model accepts 200K tokens in one request (~150K words of text).

Context window size200K tokens
4K32K128K1M10M

What fits in one request

  • Short document
    About 1,500 words of text
    Fits
  • Long document
    About 37K words of text
    Fits
  • Small codebase
    About 150K words of text
    Fits
  • Full novel
    About 375K words of text
    Won't fit

Specifications

Context size, pricing, and release info in one place.

Context window
200,000 tokens (200K)
Max output tokens
8,192 tokens (8K)
Speed tier
fast
Provider
Minimax
Release date
Oct 2025
Input cost
$0.300/M / 1M tokens
Output cost
$1.20/M / 1M tokens

Capabilities

See which features this model supports, such as vision, tools, and streaming.

Supported (5)
Tool use
Supported
Function calling
Supported
Extended thinking
Supported
Streaming
Supported
Prompt caching
Supported
Not supported (3)
Vision
Not supported
Web search
Not supported
Batch API
Not supported

Best for

Jump to a guide or ranking that matches each workload.

Compare MiniMax M2

Open a side-by-side comparison with one click.

Frequently asked questions

Short answers about context size and how this model behaves.

MiniMax M2 has a context window of 200K tokens (200,000 tokens). This large window is well-suited for long document analysis, extensive codebases, and multi-session agent workflows.

More from Minimax

Other models by Minimax in our catalog.

Powered by Mem0

Use a smaller model.
Get better results.

Mem0 gives your AI long-term memory so you stop re-sending context on every call. That means you can use a smaller, faster, cheaper model — and still get better answers.

Example: a multi-turn chat session

Without Mem0~128K tokens sent
Full history
Repeated info
Old context
With Mem0~20K tokens sent
Key memories
Current turn

80% less to send — works with any model