MiniMax M2 API

MiniMax-M2 is an advanced large language model with 1M token context for extended reasoning and generation.

Modalities: TextText
In / Out price: $0.3/$1.2per 1M
Context window: 1M tokens
Released: Nov 4, 2025

MiniMax M2 overview

MiniMax M2 by MiniMax

The model is designed for easy integration into existing AI ecosystems requiring fast, intelligent decision-making capabilities.

MiniMax M2 specs

Model ID: minimax/m2
Developer: MiniMax
Context window: 1,000,000 tokens
Max output: 40,960 tokens
Input: Text
Output: Text
API: OpenAI-compatible, base URL https://api.aimlapi.com/v1

MiniMax M2 API Overview

MiniMax M2 is a state-of-the-art agent-based reasoner designed for high efficiency and advanced autonomous capabilities. It leverages a Mixture of Experts (MoE) architecture with 230 billion total parameters, activating 10 billion parameters per inference for optimal performance. This model excels in latency reduction and throughput, making it suitable for demanding AI applications.

Technical Specifications

Architecture: Mixture of Experts (MoE)
Active Parameters: 10 billion (per inference)
Latency: Low latency optimized for real-time use
Throughput: High throughput supporting large-scale deployments
Model Type: Agent-based reasoner

Performance Benchmarks

Outperforms leading open models including Claude Opus and Gemini 2.5 in independent benchmark tests.
Ranked in the Top 5 smartest AI models globally by Artificial Intelligence rankings.
Demonstrates superior reasoning, coding, and prompt generation capabilities in diverse evaluation scenarios.

Key Features

Agent-based reasoning drives autonomous and context-aware decision making.
Writes, debugs code, and crafts effective prompts for autonomous AI agents.
Efficient MoE design enables low-latency responses despite large parameter count.
Robust scalability and performance balance allow deployment across various cloud and edge environments.
Supports integration with autonomous systems requiring complex reasoning workflows.

Comparison with Other Models

vs Claude Opus: MiniMax M2 emphasizes swift, scalable agent reasoning with coding-centered capabilities, whereas Claude Opus targets maximal reasoning depth and complex multi-step problem solving with robust tool and memory integration.

vs Gemini 2.5: MiniMax M2 surpasses Gemini 2.5 Pro in overall intelligence scores, placing it among the top five models globally, and exceeds it in efficiency due to its MoE architecture activating only a small subset of parameters. Gemini 2.5 excels in multimodal creativity, generating images, art, and audio, whereas MiniMax M2 is more focused on reasoning, coding, and autonomous agent tasks.

vs PaLM 2: PaLM 2 is renowned for its multilingual, coding, and research capabilities, but MiniMax M2 outperforms it in open intelligence rankings and autonomous reasoning benchmarks. PaLM 2’s versatility makes it suitable for a wide range of applications, whereas MiniMax M2’s strength lies in cost-efficient, high-performance agent reasoning for specialized tasks.

vs GPT-4: GPT-4 remains the industry leader for multilingual understanding and a wide array of domains beyond coding and reasoning, while MiniMax M2 specifically optimizes those domains tied to autonomous agent reasoning, coding, and deep search functions.

Use cases

Autonomous AI agent orchestration and control.
Automated coding assistance and bug fixing for software developers.
Generation of advanced prompts for AI-driven workflows and task automation.
Real-time decision support systems in dynamic environments.
Research and development in multi-agent systems and AI reasoning.

Capabilities

Function calling
Streaming
Structured outputs
Reasoning

MiniMax M2 benchmarks by Artificial Analysis

See how MiniMax M2 compares in generation speed and latency. Data retrieved Nov 3, 2026.

Speed#91 / 219121Output tokens / second Latency#105 / 2161.36Seconds to first token Humanity's Last Exam#177 / 45813.7%Score GPQA Diamond#153 / 43977.7%Score

Speed

Output tokens / second

Benchmark results

Compare 12 models available on AI/ML API across 5 independent benchmarks.

Humanity's Last Exam

Expert-written questions across academic subjects.

MiniMax M2 API pricing

MiniMax M2 pricing in US dollars
Usage	Price	Unit
Input	$0.3	1M tokens
Output	$1.2	1M tokens

Prices from the AI/ML API price list, checked on Nov 4, 2026.

MiniMax M2 vs other models: token prices

AI/ML API input and output rates for 5 models, per million tokens.

AI/ML API model prices in USD per million tokens
Model	Input	Output
MiniMax M2	$0.3	$1.2
MiniMax M3.1 Flash	$0.15	$0.6
MiniMax M3	$0.3	$1.2
MiniMax M2.1 Highspeed	$0.6	$2.4
MiniMax M2.7 Highspeed	$0.6	$2.4

How to use the MiniMax M2 API

View docs

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl 'https://api.aimlapi.com/v1/chat/completions' \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "minimax/m2",
  "messages": [
    {
      "role": "user",
      "content": "Write a haiku about the ocean."
    }
  ]
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "minimax/m2",
    "messages": [
        {
            "role": "user",
            "content": "Write a haiku about the ocean."
        }
    ]
}

response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())

const response = await fetch("https://api.aimlapi.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "minimax/m2",
    "messages": [
      {
        "role": "user",
        "content": "Write a haiku about the ocean."
      }
    ]
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

All posts

MiniMax M2 FAQ

What is the context window of MiniMax M2?

MiniMax M2 has a 1,000,000 tokens context window and can return up to 40,960 tokens.

What inputs and outputs does MiniMax M2 support?

MiniMax M2 takes text as input and returns text.

What is the model ID for MiniMax M2?

Use minimax/m2 as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.

How much does MiniMax M2 cost?

MiniMax M2 costs $0.3 input and $1.2 output per 1M tokens on AI/ML API, billed as you go with no subscription.

Does MiniMax M2 support streaming?

Yes, MiniMax M2 can stream responses as they are generated.

Who created MiniMax M2?

MiniMax M2 was built by MiniMax.

Start building with MiniMax M2

Get API key

MiniMax M2 API

minimax/m2

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl 'https://api.aimlapi.com/v1/chat/completions' \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "minimax/m2",
  "messages": [
    {
      "role": "user",
      "content": "Write a haiku about the ocean."
    }
  ]
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "minimax/m2",
    "messages": [
        {
            "role": "user",
            "content": "Write a haiku about the ocean."
        }
    ]
}

response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())

const response = await fetch("https://api.aimlapi.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "minimax/m2",
    "messages": [
      {
        "role": "user",
        "content": "Write a haiku about the ocean."
      }
    ]
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

Docs for AI agents Plain-text index · llms.txt API documentation API reference and examples

Talk to our sales team

Thanks for reaching out

MiniMax M2 API

MiniMax M2 overview

MiniMax M2 by MiniMax

MiniMax M2 specs

MiniMax M2 API Overview

Technical Specifications

Performance Benchmarks

Key Features

Comparison with Other Models

Use cases

Capabilities

MiniMax M2 benchmarks by Artificial Analysis

Speed

Benchmark results

Humanity's Last Exam

GPQA Diamond

AA-LCR

IFBench

τ²-Bench Telecom

MiniMax M2 API pricing

MiniMax M2 vs other models: token prices

How to use the MiniMax M2 API

Build with your agent

1Get your API key

2Make your first request

Related articles

MiniMax M2 FAQ

Start building with MiniMax M2

MiniMax M2 API

Build with your agent

1Get your API key

2Make your first request

MiniMax M2 API

MiniMax M2 overview

MiniMax M2 by MiniMax

MiniMax M2 specs

MiniMax M2 API Overview

Technical Specifications

Performance Benchmarks

Key Features

Comparison with Other Models

Use cases

Capabilities

Speed

Benchmark results

Humanity's Last Exam

GPQA Diamond

AA-LCR

IFBench

τ²-Bench Telecom

MiniMax M2 API pricing

MiniMax M2 vs other models: token prices

How to use the MiniMax M2 API

Build with your agent

1Get your API key

2Make your first request

Models similar to MiniMax M2

MiniMax M3.1 Flash

MiniMax M3

MiniMax M2.1 Highspeed

DeepSeek Chat (V4.1 Flash)

DeepSeek V4.1 Flash

Gemini 3.5 Flash Lite

Related articles

Best AI Models for Agentic Workflows and Tool Use in 2026

Best LLMs for Long-Context & Multimodal Tasks in 2026

MiniMax M2 FAQ

Start building with MiniMax M2