CrossModel
MiniMax M2.7
minimax/minimax-m2.7
Back to model catalog

MiniMax · Model guide

MiniMax M2.7

Compare
minimax/minimax-m2.7

A 229B-parameter sparse MoE agent model for software engineering, office work and long-horizon tool use. M2.7 adds Agent Teams and stronger skills, tool discovery and multi-step execution over M2.5.

Modalities
TextText
Context
205K
Max output
131K
Price / 1M tokens
$ 0.33in$ 1.32out
StreamingTool callingJSON outputImage inputThinking mode

What this model is good at

What the vendor positions it for, and which of our models to reach for instead.

VendorA self-evolving agent model for coding, office work and complex multi-agent workflows.source

Best for

  • Complex agent workflows · Agent Teams, dynamic tool search and reusable skills target long-horizon execution.(vendor claim)source

  • Repository-scale coding · M2.7 improves multilingual and repository-level software-engineering evaluations.(vendor claim)source

Neighbouring models
  • minimax/minimax-m3successor —Choose M3 for native image/video understanding and a 1M context window.
Compare them side by side →

Pricing and billing

Billed per token. Cached input is charged at the cache-read rate.

Price / 1M tokensYou pay
Input$ 0.33
Output$ 1.32
Cache read$ 0.066
Cache write$ 0.42
Estimate a request
$ 0.0059
Estimated cost per request
10.0K × $ 0.33
+ 2.0K × $ 1.32
≈ $ 5.94 per 1,000 requests

Capabilities and limits

What CrossModel guarantees across every route this model can take right now.

Context window
204.8K tokens
Max output
131.1K tokens
Input / output modalities
Text → Text
Streaming
Supported
Tool calling
Supported
Structured output (JSON)
Supported
Image input
Not supported
Thinking mode
Supported· always on
Available endpoints
/v1/chat/completions · /v1/responses · /v1/messages
First-party sources:Specsminimax.ioCapabilitiesminimax.io

Published benchmarks

Scores the vendor reported, with the evaluation setup each one came from.

Agentic coding
  • Terminal-Bench 2.0
    pass_rate·MiniMax · 2026-03-18setup not fully disclosed
    57%
Coding
  • Multi-SWE-Bench
    resolved_rate·MiniMax · 2026-03-18setup not fully disclosed
    52.7%
  • SWE-Bench Pro
    resolved_rate·MiniMax · 2026-03-18setup not fully disclosed
    56.22%
Knowledge work
  • GDPval-AA
    elo·MiniMax · 2026-03-18setup not fully disclosed
    1495
Tool use
  • Toolathlon
    score·MiniMax · 2026-03-18setup not fully disclosed
    46.3%

Vendor-reported numbers, not CrossModel measurements. Scores are only comparable when the benchmark version, metric and evaluation setup match, so nothing here is averaged or ranked.

Use it in your tools

Point the base URL at CrossModel and paste this model ID — every tool below has a setup guide.

Claude Code
Anthropic's official command-line coding assistant
Cursor
AI-first code editor
Cline
Open-source AI coding agent for VS Code
Codex
OpenAI's coding agent for ChatGPT desktop and the terminal
OpenCode
Open-source terminal coding assistant
Zed
High-performance, AI-native code editor
Open WebUI
Open-source, self-hosted AI chat interface
Continue
Open-source AI coding assistant for VS Code & JetBrains
See all integration guides →

Frequently asked questions

What is MiniMax M2.7?
MiniMax M2.7 is available on CrossModel as minimax/minimax-m2.7. It has a 205K-token context window and can return up to 131K tokens per request.
How much does MiniMax M2.7 cost?
Currently $ 0.33 per 1M input tokens and $ 1.32 per 1M output tokens. Cached input is billed at $ 0.066 per 1M.
Does MiniMax M2.7 support tool calling and structured output?
Tool calling: Supported · Structured output (JSON): Supported · Image input: Not supported · Streaming: Supported · Thinking mode: Supported
Which endpoint do I call?
For text models, OpenAI Chat Completions (/v1/chat/completions), OpenAI Responses (/v1/responses) and Anthropic Messages (/v1/messages) all work — pick whichever your SDK already speaks.
Can I try it without writing code?
Yes. Sign in and open the Playground on this page to chat with the model directly — no API key needed. Usage is billed from your wallet at the normal rate.

Chat first, integrate later

Chat first, then wire it in once you like the answers.