Model Information

Display Name: MiniMax M3

API Model ID: minimax/minimax-m3

Category: Image To Text

Description: MiniMax-M3 is MiniMax's native multimodal foundation model. It takes text, image and video input and produces text, with a very large context window and a Mixture-of-Experts architecture (~428B total parameters, ~23B activated), aimed at long-horizon agentic work and coding. **Key Features:** - 524,288-token context window - Up to 131K output tokens - Native multimodal input: text, image and video - Mixture-of-Experts: ~428B total / ~23B activated parameters - Controllable reasoning (can be turned off) - Function/tool calling for agentic workflows - Cache-read pricing for repeated context **Best For:** - Long-horizon agentic tasks and tool use - Coding and multi-step engineering work - Image and video understanding combined with reasoning - Long-document and large-codebase analysis

Context Window: 524,288 tokens

Max Output: 131,072 tokens

How to Use This Model

To use MiniMax M3 via the HInow.ai API, use the model ID: minimax/minimax-m3

API Request Example (Chat/Text)

POST https://api.hinow.ai/v1/chat/completions
Authorization: Bearer YOUR_API_KEY
Content-Type: application/json

{
  "model": "minimax/minimax-m3",
  "messages": [
    {"role": "user", "content": "Your message here"}
  ]
}
              

API Request Example (Image Generation)

POST https://api.hinow.ai/v1/images
Authorization: Bearer YOUR_API_KEY
Content-Type: application/json

{
  "model": "minimax/minimax-m3",
  "prompt": "Your image description here"
}
              

Pricing

• input: $0.405
• output: $1.62
• cached: $0.081

Available Parameters

• temperature: Controls randomness (0-2). Default: 0.7 (Options: 0, 0.3, 0.5, 0.7, 1.0)
• top_p: Nucleus sampling (0-1). Default: 0.95 (Options: 0.1, 0.5, 0.8, 0.9, 0.95, 1.0)
• max_tokens: Max tokens to generate (1-131072). Default: 8192 (Options: 512, 1024, 2048, 4096, 8192, 16384, 32768, 65536, 131072)
• tools: Function/tool definitions for agentic workflows
• response_format: Output format (Options: text, json_object)
• stop: Sequences where the API stops generating further tokens
• frequency_penalty: Penalizes token frequency (-2 to 2). Default: 0 (Options: 0, 0.5, 1.0)
• presence_penalty: Penalizes repeated topics (-2 to 2). Default: 0 (Options: 0, 0.5, 1.0)

Quick Reference

To use this model, set: "model": "minimax/minimax-m3"

Featured: No

Documentation: https://hinow.ai/models/minimax/minimax-m3

API Endpoint: https://api.hinow.ai/v1