Skip to main content
Subscribe to Token Plan to use MiniMax models of all modalities at ultra-low prices!

​
Model Overview

MiniMax offers multiple LLMs to meet different scenario requirements. MiniMax-M3 is the latest M-series language model for agentic reasoning, tool use, coding, and long-context tasks, while MiniMax-M2.7 and MiniMax-M2 remain available for existing workflows.

​
Supported Models

Model NameContext WindowDescription
MiniMax-M31,000,000Frontier multimodal coding model with 1M context window
MiniMax-M2.7204,800Beginning the journey of recursive self-improvement (output speed approximately 60 tps)
MiniMax-M2.7-highspeed204,800M2.7 Highspeed: Same performance, faster and more agile (output speed approximately 100 tps)
MiniMax-M2.5204,800Peak Performance. Ultimate Value. Master the Complex (output speed approximately 60 tps)
MiniMax-M2.5-highspeed204,800M2.5 highspeed: Same performance, faster and more agile (output speed approximately 100 tps)
MiniMax-M2.1204,800Powerful Multi-Language Programming Capabilities with Comprehensively Enhanced Programming Experience (output speed approximately 60 tps)
MiniMax-M2.1-highspeed204,800Faster and More Agile (output speed approximately 100 tps)
MiniMax-M2204,800Agentic capabilities, Advanced reasoning
M2-her64 KDesigned for dialogue scenarios, supporting role-playing and multi-turn conversations
For details on how tps (Tokens Per Second) is calculated, please refer to FAQ > About APIs.

​
MiniMax M3 Key Highlights

MiniMax-M3 supports up to a 1,000,000-token context window for long documents, codebases, and multi-step agent sessions.
MiniMax-M3 is designed for agentic reasoning, tool use, coding, and structured task execution.
OpenAI-compatible Chat Completions support text, image, and video input with image_url and video_url content parts.
For more model details, please refer to MiniMax M3.

​
URL Configuration

Before calling MiniMax models, prepare the following:
FieldValue
base_url (Anthropic-compatible, recommended)https://api.minimax.io/anthropic
base_url (OpenAI-compatible)https://api.minimax.io/v1
api_keyGet Subscription Key
modelSee Supported Models above

​
Calling Example

MiniMax accepts both Anthropic-style and OpenAI-style request formats. The two examples below are equivalent non-streaming calls; flip stream to true to switch to streaming responses. Supports thinking blocks, interleaved thinking, and other advanced features — this is the default path. 
curl https://api.minimax.io/anthropic/v1/messages \
  -H "Authorization: Bearer <MINIMAX_API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "MiniMax-M3",
    "max_tokens": 1000,
    "messages": [
      {"role": "user", "content": "Hi, how are you?"}
    ]
  }'

​
OpenAI-Compatible

Already wired up to the OpenAI SDK? Swap base_url and model for the values below and you can keep using your existing client without migrating to a new SDK. 
curl https://api.minimax.io/v1/chat/completions \
  -H "Authorization: Bearer <MINIMAX_API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "MiniMax-M3",
    "messages": [
      {"role": "user", "content": "Hi, how are you?"}
    ]
  }'

​
API Reference

Anthropic API Compatible (Recommended)

Call MiniMax models via Anthropic SDK, supporting streaming output and Interleaved Thinking

OpenAI API Compatible

Call MiniMax models via OpenAI SDK

Using M3 in AI Coding Tools

Use M3 in Claude Code, Cursor and other tools

Chat Model

M2-her chat model, designed for role-playing and multi-turn dialogue scenarios

​
Contact Us

If you encounter any issues while using MiniMax models:
  • Contact our technical support team through official channels such as email [email protected]
  • Submit an Issue on our Github repository