API Documentation

https://api.minimax.villamarket.ai/v1

curl https://api.minimax.villamarket.ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "minimax-m2.5",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'

from openai import OpenAI

client = OpenAI(
    base_url="https://api.minimax.villamarket.ai/v1",
    api_key="YOUR_API_KEY",
)

response = client.chat.completions.create(
    model="minimax-m2.5",
    messages=[{"role": "user", "content": "Write a quicksort in Python"}],
)

print(response.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.minimax.villamarket.ai/v1",
  apiKey: "YOUR_API_KEY",
});

const response = await client.chat.completions.create({
  model: "minimax-m2.5",
  messages: [{ role: "user", content: "Hello!" }],
});

console.log(response.choices[0].message.content);

Authorization: Bearer sk-...

POST /v1/chat/completions

stream = client.chat.completions.create(
    model="minimax-m2.5",
    messages=[{"role": "user", "content": "Explain MoE"}],
    stream=True,
)

for chunk in stream:
    delta = chunk.choices[0].delta
    if delta.content:
        print(delta.content, end="", flush=True)
    # Think blocks appear in delta.reasoning_content (custom field)

response = client.chat.completions.create(
    model="minimax-m2.5",
    messages=[{"role": "user", "content": "What's the weather in Tokyo?"}],
    tools=[{
        "type": "function",
        "function": {
            "name": "get_weather",
            "description": "Get weather for a city",
            "parameters": {
                "type": "object",
                "properties": {
                    "city": {"type": "string", "description": "City name"}
                },
                "required": ["city"]
            }
        }
    }],
)

tool_call = response.choices[0].message.tool_calls[0]
print(tool_call.function.name)       # "get_weather"
print(tool_call.function.arguments)  # '{"city": "Tokyo"}'

# The model automatically uses <think>...</think> blocks
# vLLM separates these into reasoning_content and content

for chunk in stream:
    delta = chunk.choices[0].delta

    # Internal reasoning (optional, may be empty)
    if hasattr(delta, 'reasoning_content') and delta.reasoning_content:
        print(f"[thinking] {delta.reasoning_content}", end="")

    # Final response
    if delta.content:
        print(delta.content, end="")

# Authenticate
mm auth login --key YOUR_API_KEY

# Interactive chat
mm run

# Launch Nori TUI (multi-provider AI agent)
mm term

# Launch coding tools pre-configured for MiniMax
mm launch claude
mm launch aider
mm launch nori

# Run a skill
mm skills run code-review "Review my code for bugs"

# Ralph Loop — iterative development
mm loop "Fix all failing tests" -n 50 -p "ALL_TESTS_PASS"

# Option 1: Use mm launch (recommended)
mm launch claude

# Option 2: Manual setup
export ANTHROPIC_BASE_URL=https://api.minimax.villamarket.ai
export ANTHROPIC_API_KEY=YOUR_API_KEY
export ANTHROPIC_AUTH_TOKEN=YOUR_API_KEY
claude --model minimax-m2.5

# Option 1: Use mm (recommended)
mm term

# Option 2: Use mm launch
mm launch nori

# Option 3: Manual
npm install -g nori-ai-cli
export ANTHROPIC_BASE_URL=https://api.minimax.villamarket.ai
export ANTHROPIC_API_KEY=YOUR_API_KEY
nori

Base URL: https://api.minimax.villamarket.ai/v1
API Key: YOUR_API_KEY
Model: minimax-m2.5

# Option 1: Use mm launch
mm launch aider

# Option 2: Manual
aider --openai-api-base https://api.minimax.villamarket.ai/v1 \
      --openai-api-key YOUR_API_KEY \
      --model openai/minimax-m2.5

# Option 1: Use mm launch
mm launch codex

# Option 2: Manual
export OPENAI_BASE_URL=https://api.minimax.villamarket.ai/v1
export OPENAI_API_KEY=YOUR_API_KEY
codex --model minimax-m2.5

# Option 1: Use mm launch
mm launch opencode

# Option 2: Manual
export OPENAI_BASE_URL=https://api.minimax.villamarket.ai/v1
export OPENAI_API_KEY=YOUR_API_KEY
opencode

{
  "models": [{
    "title": "MiniMax-M2.5",
    "provider": "openai",
    "model": "minimax-m2.5",
    "apiBase": "https://api.minimax.villamarket.ai/v1",
    "apiKey": "YOUR_API_KEY"
  }]
}

API Type: Chat Completion (OpenAI)
Custom Endpoint: https://api.minimax.villamarket.ai/v1
API Key: YOUR_API_KEY
Model: minimax-m2.5