Chat Completions API

OpenAI-compatible interface for MiniMax-M2 chat.

Chat Completions API

The chat completions endpoint mirrors OpenAI’s v1/chat/completions contract. Use it to stream or fetch MiniMax-M2 responses with minimal code changes.

Endpoint: POST https://minimax-m2.com/api/v1/chat/completions
Auth: Authorization: Bearer <api-key>
Models: MiniMax-M2 (default for API compatibility), MiniMax-M2.1, MiniMax-M2.5, MiniMax-M2.7, MiniMax-M3 → See model comparison to choose the right one for your workflow

💡 Model Selection: Examples below use MiniMax-M2.1 for enhanced multi-language and native mobile capabilities. If model is omitted, the API defaults to MiniMax-M2 for backward compatibility. To use MiniMax-M2 for faster Python/JavaScript agent workflows, change the model field:

{ "model": "MiniMax-M2", ... }

All models share the same API parameters. Pricing may differ by model (especially deployment-specific models such as MiniMax-M2.7); use GET /api/v1/models for the effective rates in your environment. For M2.7 alias, pricing, and fallback behavior, see MiniMax-M2.7 Guide. For M3 multimodal input, max_completion_tokens, and thinking controls, see MiniMax M3 API Guide.

Request Example (JSON)

POST /api/v1/chat/completions HTTP/1.1
Host: minimax-m2.com
Authorization: Bearer sk-live-...
Content-Type: application/json

{
  "model": "MiniMax-M2.1",
  "messages": [
    { "role": "system", "content": "You are a precise financial analyst." },
    { "role": "user", "content": "Summarize Q4 revenue trends for APAC." }
  ],
  "stream": false,
  "reasoning_split": true
}

cURL

curl https://minimax-m2.com/api/v1/chat/completions \
  -H "content-type: application/json" \
  -H "authorization: Bearer $MINIMAX_API_KEY" \
  -d '{
    "model": "MiniMax-M2.1",
    "messages": [
      { "role": "system", "content": "You are a precise financial analyst." },
      { "role": "user", "content": "Summarize Q4 revenue trends for APAC." }
    ],
    "reasoning_split": true
  }'

Node.js (TypeScript)

import fetch from 'node-fetch';

const response = await fetch('https://minimax-m2.com/api/v1/chat/completions', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    Authorization: `Bearer ${process.env.MINIMAX_API_KEY}`,
  },
  body: JSON.stringify({
    model: 'MiniMax-M2.1',
    messages: [
      { role: 'system', content: 'You are a precise financial analyst.' },
      { role: 'user', content: 'Summarize Q4 revenue trends for APAC.' },
    ],
    reasoning_split: true,
  }),
});

const data = await response.json();
console.log(data.choices[0].message?.content);

Python

import requests

headers = {
    "Authorization": f"Bearer {API_KEY}",
    "Content-Type": "application/json",
}

payload = {
    "model": "MiniMax-M2.1",
    "messages": [
        {"role": "system", "content": "You are a precise financial analyst."},
        {"role": "user", "content": "Summarize Q4 revenue trends for APAC."}
    ],
    "reasoning_split": True
}

resp = requests.post("https://minimax-m2.com/api/v1/chat/completions", json=payload, headers=headers)
resp.raise_for_status()
print(resp.json()["choices"][0]["message"]["reasoning_details"][0]['text'])
print(resp.json()["choices"][0]["message"]["content"])

Python (OpenAI SDK)

from openai import OpenAI

client = OpenAI(
    base_url="https://minimax-m2.com/api/v1/",
    api_key="MINIMAX_API_KEY",
)

response = client.chat.completions.create(
    model="MiniMax-M2.1",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Hi, how are you?"},
    ],
    extra_body={"reasoning_split": True},
)

print(f"Thinking:\\n{response.choices[0].message.reasoning_details[0]['text']}\\n")
print(f"Text:\\n{response.choices[0].message.content}\\n")

Python with MiniMax-M2 (Fast Agent Workflows)

import requests

headers = {
    "Authorization": f"Bearer {API_KEY}",
    "Content-Type": "application/json",
}

payload = {
    "model": "MiniMax-M2",  # Fast inference for Python/JavaScript agents
    "messages": [
        {"role": "system", "content": "You are a DevOps automation expert."},
        {"role": "user", "content": "Write a Python script to monitor disk usage and send Slack alerts"}
    ],
    "reasoning_split": True,
    "temperature": 0.7
}

resp = requests.post("https://minimax-m2.com/api/v1/chat/completions", json=payload, headers=headers)
resp.raise_for_status()
print("Thinking:", resp.json()["choices"][0]["message"]["reasoning_details"][0]['text'])
print("\nCode:", resp.json()["choices"][0]["message"]["content"])

Why M2 here? Optimized for Python agent workflows with fast inference speed (~100 tokens/s).

Streaming Responses

Set stream: true to receive Server-Sent Events (SSE). The data format matches OpenAI’s, enabling drop-in use of existing clients.

data: {"id":"chatcmpl-...","object":"chat.completion.chunk","choices":[{"index":0,"delta":{"content":"你好"}}],"model":"minimax-m2.1"}
data: {"id":"chatcmpl-...","object":"chat.completion.chunk","choices":[{"index":0,"delta":{"content":"你好"}}],"model":"minimax-m2.1"}

...
data: [DONE]

Usage Metrics

Responses include token usage in the OpenAI schema (usage.prompt_tokens, usage.completion_tokens). These values feed billing and are visible in the dashboard usage explorer.