CrossModel
MiniMax-M3
minimax/minimax-m3
Back to model catalog

MiniMax · Model guide

MiniMax-M3

Compare
minimax/minimax-m3

MiniMax's flagship native-multimodal agent model, with 428B total and 23B active parameters, a 1M-token context window and text, image and video understanding. It targets coding, computer use, research and long-running cowork workflows.

Modalities
TextImageVideoText
Context
1M
Max output
512K
Price / 1M tokens
$ 0.33in$ 1.32out
StreamingTool callingJSON outputImage inputThinking mode · can be turned off

What this model is good at

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

VendorA native-multimodal, million-context model for coding agents, computer use and professional cowork tasks.source

Best for

  • Multimodal agents · M3 natively handles text, images and video while using tools over long contexts.(vendor claim)source

  • Computer use and cowork · The model is positioned for real computer interaction and professional cowork workflows.(vendor claim)source

  • Long-context research · A 1M-token context window supports large repositories and long-running tasks.(vendor claim)source

Neighbouring models
Compare them side by side →

Pricing and billing

Tiered pricing: the rate changes once the input passes the threshold.

Price / 1M tokens by input sizeInput < 512.0KInput ≥ 512.0K
Input$ 0.33$ 0.66
Output$ 1.32$ 2.63
Cache read$ 0.066$ 0.13
Cache write$ 0.33$ 0.66
Estimate a request

At this input size you are on the Input < 512.0K tier.

$ 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
1.0M tokens
Max output
512.0K tokens
Input / output modalities
Text + Image + Video → Text
Streaming
Supported
Tool calling
Supported
Structured output (JSON)
Supported
Image input
Supported
Thinking mode
Supported· can be turned off
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 2.1
    pass_rate·MiniMax · 2026-06-01Terminus 2setup not fully disclosed
    66%
Coding
  • SWE-Bench Pro
    resolved_rate·MiniMax · 2026-06-01Claude Codesetup not fully disclosed
    59%
  • SWE-Bench Verified
    resolved_rate·MiniMax · 2026-06-01setup not fully disclosed
    80.5%
Multimodal reasoning
  • MMMU Pro (no tools)
    accuracy·MiniMax · 2026-06-01setup not fully disclosed
    78.1%
Tool use
  • MCP Atlas Public
    score·MiniMax · 2026-06-01setup not fully disclosed
    74.2%

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-M3?
MiniMax-M3 is available on CrossModel as minimax/minimax-m3. It has a 1M-token context window and can return up to 512K tokens per request.
How much does MiniMax-M3 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-M3 support tool calling and structured output?
Tool calling: Supported · Structured output (JSON): Supported · Image input: Supported · Streaming: Supported · Thinking mode: Supported
Which endpoint do I call?
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.