MiniMax: MiniMax M3

MiniMax-M3 is MiniMax’s latest M-series multimodal foundation model for agent reasoning, tool use, coding, and long-context tasks. It supports text, image, and video inputs with text output, a 1M-token context window, thinking content, function calling, and structured outputs.

Why It Looks Great

• Latest MiniMax M-series language model for agent reasoning, tools, coding, and long-context work
• Native multimodal support for text, image, and video understanding
• 1M-token context window for long prompts, large documents, videos, codebases, and multi-turn workflows
• Up to 512K output tokens for unusually long responses, extended reasoning, and structured generation
• Strong fit for long-horizon agentic work, coding workflows, document analysis, and multimodal assistants
• Thinking content support for transparent multi-step reasoning workflows
• Function calling and tool-use support for agentic application workflows
• Structured output support for JSON responses and schema-constrained generation
• Efficient pricing for large-context multimodal production use cases

Key Features

• Context Window: 1,048,576 tokens
• Max Input: 536,576 tokens
• Max Output: 512,000 tokens
• Input: Text, Image, Video
• Output: Text
• Vision: Supported
• Video Input: Supported
• Function Calling: Supported
• Structured Outputs: Supported
• Thinking Mode: Supported
• Image Generation: Not listed
• Audio Input: Not listed
• Supported Parameters: include_reasoning, max_tokens, reasoning, response_format, temperature, tool_choice, tools, top_p

Specifications

How to Use

1. Write your prompt - describe the task, provide context, and specify the desired output format.
2. Submit - the model processes your request and returns the response.

API Integration

Base URL: https://llm.wavespeed.ai/v1
API Endpoint: chat/completions
Model ID: minimax/minimax-m3

API Usage

Python SDK

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://llm.wavespeed.ai/v1"
)

response = client.chat.completions.create(
    model="minimax/minimax-m3",
    messages=[{"role": "user", "content": "Hello!"}]
)

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

cURL

curl https://llm.wavespeed.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "minimax/minimax-m3",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Notes

• Model: minimax/minimax-m3
• Provider: minimax
• Best suited for long-horizon agents, coding, tool use, long-context document analysis, multimodal understanding, and structured output workflows
• Image input supports common image formats such as JPEG, PNG, GIF, and WEBP
• Video input is supported through URL, base64, or uploaded file references where available