MiniMax M3

MiniMax-M3 is MiniMax’s latest M-series multimodal foundation model, built for agentic reasoning, tool use, coding, and long-context tasks. It supports text, image, and video inputs with text output, offering a 1M-token context window, extended thinking, function calling, and structured outputs. With strong capabilities in long-horizon agent workflows, software development, multimodal understanding, and extended response generation, MiniMax-M3 is ideal for autonomous agents, coding assistants, document and video analysis, and production-grade applications that require massive context at a competitive cost.

MiniMax M3

MiniMax-M3 is MiniMax's latest M-series multimodal foundation model, built for agentic reasoning, tool use, coding, and long-context tasks. It supports text, image, and video inputs with text output, offering a 1M-token context window, configurable thinking, function calling, and structured outputs—ideal for autonomous agents, coding assistants, document and video analysis, and production applications that require massive context at a competitive cost.

Base URL

https://api.icreat.ai/llm/openai/v1

Authentication

All API requests must be authenticated with an API Key. You can obtain an 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,
}

Protect your API Key

Never expose your API Key in client-side code or public repositories. Use environment variables or a backend proxy.

Code Examples

This model is invoked via the OpenAI-compatible Chat Completions API and supports both streaming and non-streaming modes. With stream: false (default), the server returns the full JSON response at once. With stream: true, partial deltas are pushed as Server-Sent Events (SSE), suitable for real-time display.

POST/chat/completions

curl --fail-with-body --connect-timeout 10 --max-time 60 \
  -X POST https://api.icreat.ai/llm/openai/v1/chat/completions \
  -H "Authorization: Bearer ${ICREAT_API_KEY}" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "MiniMax-M3",
  "messages": [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Coffee or tea? Which is healthier?"}
  ],
  "thinking": {"type": "enabled"},
  "reasoning_effort": "low",
  "stream": false
}'

Input Schema

The following parameters are accepted in the request body.

Total: 6 Required: 2 Optional: 4

modelstringrequired

The model ID to use for the completion. Must be the iCreat model_code for this model (MiniMax-M3), not the vendor's original model name.

Example: "MiniMax-M3"

messagesarray[object]required

A list of messages comprising the conversation so far. content may be a plain string or a multimodal array of text, image, and video parts.

thinkingobject

Configures extended thinking mode. type controls whether reasoning runs; use with reasoning_effort to set the reasoning budget.

reasoning_effortstring

Reasoning effort budget. Works with thinking.type; set thinking.type to disabled for lower-latency direct responses.

lowmediumhigh

max_tokensinteger

Maximum number of tokens to generate. MiniMax recommends staying below 128K for typical requests; up to 512K is supported.

Min: 1 Max: 524288

streamboolean

If true, partial message deltas are sent as server-sent events.

Default"false"

Output Schema

The API returns a response compatible with OpenAI Chat Completions.

Total: 6 Required: 6 Optional: 0

idstring

Unique identifier for the completion.

objectstring

Object type, always chat.completion.

createdinteger

Unix timestamp of when the completion was created.

modelstring

The model used for the completion.

choicesarray[object]

List of completion choices.

usageobject

Token usage statistics.

LLM-friendly prompt

Below is an LLM-friendly Markdown prompt you can copy into Cursor, ChatGPT, or other AI assistants to help them understand this model's API integration, call flow, and key parameters.

# MiniMax-M3

> MiniMax-M3 is MiniMax's latest M-series multimodal foundation model, built for agentic reasoning, tool use, coding, and long-context tasks.

## Overview

Call via iCreat OpenAI-compatible Chat Completions API; supports streaming and non-streaming and extended thinking.

## API Info

- **Base URL**: `https://api.icreat.ai/llm/openai/v1`
- **Endpoint (POST)**: `/chat/completions`
- **Model ID**: `MiniMax-M3`
- **Auth**: `Authorization: Bearer ${ICREAT_API_KEY}`

## Call Flow

Single POST; `stream: false` returns full JSON, `stream: true` streams via SSE.

### Input

- `model` (required): iCreat model_code `MiniMax-M3`
- `messages` (required): conversation messages
- Common optional: `max_tokens`, `stream`, `thinking`, `reasoning_effort`
- `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

- Read reply from `choices[0].message.content`

## Notes

- `model` must be the iCreat model_code
- Other fields follow the OpenAI Chat Completions protocol