MiniMax M3.1 Flash
MiniMax M3.1 Flash is a next-generation flagship multimodal MoE model engineered for high-performance agentic automation, complex code synthesis, and deep reasoning. Built on a massive 428B parameter Mixture-of-Experts architecture and accelerated by MiniMax Sparse Attention (MSA), it accelerates inference speeds while expanding context throughput up to 1 million tokens.
MiniMax M3.1 Flash
MiniMax M3.1 Flash is the latest high-throughput, low-latency multimodal model developed by MiniMax, engineered for ultra-fast agent responses, code generation and analysis, massive long-context throughput, and high-concurrency multimodal tasks. Supporting text, image, and video inputs with text outputs, it natively provides a 1-million-token context window, configurable Thinking Mode, Function Calling, and Structured Outputs. It delivers robust multimodal comprehension and logical reasoning while maintaining ultra-fast inference speeds and exceptional cost efficiency.
Base URL
https://api.icreat.ai/v1
Model Code
minimax-m3-1-flash
Authentication
All API requests require authentication via an API Key. You can obtain your API Key from the console.
export ICREAT_API_KEY="your-api-key-here"
HTTP Request Headers
import os
API_KEY = os.environ.get("ICREAT_API_KEY")
headers = {
"Content-Type": "application/json",
"Authorization": "Bearer " + API_KEY,
}
Keep Your API Key Secure Never expose your API Key in client-side code or public repositories. Use environment variables or a backend proxy.
Code Examples
This model is accessed via an OpenAI-compatible Chat Completions endpoint and supports both streaming and non-streaming modes. Setting stream to false (default) in the request body causes the server to return the complete JSON response at once; setting it to true streams incremental chunks using Server-Sent Events (SSE), suitable for real-time output display.
Input Parameters
The following parameters are accepted in the request body.
Total: 6 Required: 2 Optional: 4
The model ID used for completion. Must be the iCreat model_code (minimax-m3-1-flash for this model, not the original provider model name).
Example: "minimax-m3-1-flash"
The list of messages comprising the conversation. content can be a plain text string or an array of multimodal content parts including text, images, and videos.
Configuration for extended thinking mode. type controls whether reasoning is enabled; reasoning_effort configures the reasoning budget.
Reasoning effort budget. Used in conjunction with thinking.type; setting thinking.type to disabled reduces latency.
The maximum number of tokens to generate. Typically recommended to be below 128K; upper limit is 512K.
Min: 1 Max: 524288
If set to true, streams message increments via Server-Sent Events (SSE).
Output Parameters
The API returns a response format compatible with OpenAI Chat Completions.
Total: 6
A unique identifier for the completion.
The object type, always chat.completion.
The Unix timestamp of when the completion was created.
The model ID used for the completion.
A list of completion choices.
Token usage statistics.
LLM-Friendly Prompt
Below is an LLM-friendly Markdown prompt that can be copied into AI assistants such as Cursor or ChatGPT to help the AI understand this model's API integration method, invocation workflow, and key parameters. Click the "Copy LLM Prompt" button or copy the full text from the code block below.
# minimax-m3-1-flash
> MiniMax M3.1 Flash is the latest high-throughput, low-latency multimodal model developed by MiniMax, engineered for ultra-fast agent responses, code generation and analysis, massive long-context throughput, and high-concurrency multimodal tasks.
## Overview
Use iCreat's OpenAI-compatible Chat Completions API for conversational completions, supporting streaming, non-streaming, and extended thinking modes.
## API Information
- **Base URL**: `https://api.icreat.ai/v1`
- **Endpoint (POST)**: `/chat/completions`
- **Model ID**: `minimax-m3-1-flash`
- **Authentication**: `Authorization: Bearer ${ICREAT_API_KEY}`
## Invocation Workflow
Single POST request; `stream: false` returns a complete JSON response, and `stream: true` streams via SSE.
### Input Notes
- `model` (required): iCreat model_code `minimax-m3-1-flash`
- `messages` (required): List of conversation messages
- Common optional fields: `max_tokens` (maximum output tokens), `stream` (streaming toggle), `thinking` (extended thinking mode), `reasoning_effort` (reasoning intensity)
- `image_url` (optional): Image URL object when `type` is `image_url`
- `url` (required): HTTPS URL of the image
- `video_url` (optional): Video URL object when `type` is `video_url`
- `url` (required): HTTPS URL of the video
### Output Notes
- Read the completion content from `choices[0].message.content`
## Important Notes
- `model` must strictly match the iCreat model_code
- All other fields follow standard OpenAI Chat Completions protocol specifications