{
"openapi": "3.1.0",
"info": {
"title": "MiniMax Text API OpenAI",
"description": "MiniMax text generation API with support for chat completion and streaming output.\n\n> ⚡ **`MiniMax-M3` highlights** — **Coding/Agentic SOTA**, **1M long context**, and **multimodal**.\n",
"license": {
"name": "MIT"
},
"version": "1.0.0"
},
"servers": [
{
"url": "https://api.minimax.io"
}
],
"security": [
{
"bearerAuth": []
}
],
"paths": {
"/v1/chat/completions": {
"post": {
"summary": "Text Generation OpenAI",
"operationId": "chatCompletionOpenAI",
"tags": [
"Text Generation"
],
"parameters": [
{
"name": "Content-Type",
"in": "header",
"required": true,
"description": "Media type of the request body, should be set to `application/json` to ensure JSON format",
"schema": {
"type": "string",
"enum": [
"application/json"
],
"default": "application/json"
}
}
],
"requestBody": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/ChatCompletionReq"
},
"examples": {
"Image Understanding": {
"value": {
"model": "MiniMax-M3",
"thinking": {
"type": "adaptive"
},
"messages": [
{
"role": "user",
"content": [
{
"type": "text",
"text": "What does this image show?"
},
{
"type": "image_url",
"image_url": {
"url": "https://filecdn.minimax.chat/public/fe9d04da-f60e-444d-a2e0-18ae743add33.jpeg"
}
}
]
}
],
"max_completion_tokens": 500
}
},
"Video Understanding": {
"value": {
"model": "MiniMax-M3",
"thinking": {
"type": "adaptive"
},
"messages": [
{
"role": "user",
"content": [
{
"type": "text",
"text": "What is happening in this video?"
},
{
"type": "video_url",
"video_url": {
"url": "https://filecdn.minimax.chat/public/ee8c1648-21f1-41b7-8397-65022d22ffe5.mp4"
}
}
]
}
],
"max_completion_tokens": 500
}
},
"Deep Thinking": {
"value": {
"model": "MiniMax-M3",
"thinking": {
"type": "adaptive"
},
"messages": [
{
"role": "user",
"content": "Which is bigger, 9.11 or 9.9?"
}
],
"max_completion_tokens": 500
}
},
"Stream": {
"value": {
"model": "MiniMax-M3",
"thinking": {
"type": "adaptive"
},
"messages": [
{
"role": "user",
"content": [
{
"type": "text",
"text": "What does this image show?"
},
{
"type": "image_url",
"image_url": {
"url": "https://filecdn.minimax.chat/public/fe9d04da-f60e-444d-a2e0-18ae743add33.jpeg"
}
}
]
}
],
"stream": true,
"max_completion_tokens": 500
}
},
"Tool Use": {
"value": {
"model": "MiniMax-M3",
"messages": [
{
"role": "user",
"content": "How's the weather in San Francisco?"
}
],
"tools": [
{
"type": "function",
"function": {
"name": "get_weather",
"description": "Get the current weather for a given location.",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city and state/country, e.g. San Francisco, US"
}
},
"required": [
"location"
]
}
}
}
]
}
}
}
}
},
"required": true
},
"responses": {
"200": {
"description": "",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/ChatCompletionResp"
},
"examples": {
"Image Understanding": {
"value": {
"id": "066a33a7d290378f8a9e57a055812afa",
"choices": [
{
"finish_reason": "stop",
"index": 0,
"message": {
"content": "\nThe user is asking me to describe an image. Let me look at it carefully and provide a description.\n\nThe image shows a young girl, likely a child, with curly/wavy brown hair that has bangs. She has large brown/amber eyes and is smiling gently. She's wearing what appears to be a cream or off-white dress with lace/ruffled details. The lighting is soft and warm, suggesting this is a portrait-style photograph with a blurred neutral background.\n\nThis image is a warm, softly-lit portrait photograph of a young girl, likely a child around 4-6 years old. Key features include:\n\n- **Hair**: Wavy/curly brown hair with bangs, with some strands pulled back or styled on top\n- **Eyes**: Large, expressive amber/brown eyes looking directly at the camera\n- **Expression**: A gentle, sweet smile\n- **Clothing**: A cream or off-white dress with delicate lace trim and ruffled cap sleeves\n- **Lighting**: Soft, warm, golden lighting that gives the image a dreamy, classic portrait quality\n- **Background**: A neutral, muted grayish-brown backdrop, blurred to keep focus on the subject\n\nThe overall aesthetic resembles a professional studio portrait or a finely-tuned AI-generated image, with attention to detail in features like the catchlights in her eyes, the texture of her hair, and the soft focus on the background. It has a timeless, painterly quality.",
"role": "assistant",
"name": "MiniMax AI",
"audio_content": ""
}
}
],
"created": 1780154535,
"model": "MiniMax-M3",
"object": "chat.completion",
"usage": {
"total_tokens": 1659,
"total_characters": 0,
"prompt_tokens": 1366,
"completion_tokens": 293,
"prompt_tokens_details": {
"cached_tokens": 114
}
},
"input_sensitive": false,
"output_sensitive": false,
"input_sensitive_type": 0,
"output_sensitive_type": 0,
"output_sensitive_int": 0,
"base_resp": {
"status_code": 0,
"status_msg": ""
}
}
},
"Video Understanding": {
"value": {
"id": "066b4564af67dda4130e1db289c2ba25",
"choices": [
{
"finish_reason": "stop",
"index": 0,
"message": {
"content": "\nThe user wants me to describe the action in the video.\n\n1. **Analyze the video:**\n * The video shows an AI-generated scene (indicated by the \"MINIMAX\" and \"Hailuo AI\" watermarks).\n * The setting is a large indoor arena, likely an Olympic pool venue, given the Olympic rings logo and the \"Lausanne 2020\" text (which is anachronistic, but it's a generated video).\n * The main subject is a domestic cat, specifically a spotted breed like a Bengal or Savannah, but it looks a bit distorted in the generated style.\n * The cat is walking on a diving board. It starts on the left side and walks towards the right.\n * Around 0.2 seconds, the cat reaches the end of the diving board and leaps off.\n * The cat is airborne for a brief moment, performing what looks like a basic jump, not a complex dive.\n * It falls towards the water below.\n * It hits the water and splashes.\n * The camera follows the cat's trajectory.\n * The background shows a crowd of spectators sitting in the stands, watching the event.\n * A person is standing on the pool deck, observing.\n\n2. **Synthesize the description:**\n * Start with the main subject and action: A cat is walking on a diving board.\n * Describe the progression: It walks to the end.\n * Describe the climax: It jumps off the board.\n * Describe the conclusion: It falls into the water below.\n * Keep it concise and objective.\n\n3. **Draft the final sentence:** \"A cat is seen walking on a diving board and then jumping into a pool of water.\" This accurately and concisely captures the entire sequence of events in the video. It covers the initial state (walking), the action (jumping), and the final state (in the pool).\n\nA cat is seen walking on a diving board and then jumping into a pool of water.",
"role": "assistant",
"name": "MiniMax AI",
"audio_content": ""
}
}
],
"created": 1780224612,
"model": "MiniMax-M3",
"object": "chat.completion",
"usage": {
"total_tokens": 2672,
"total_characters": 0,
"prompt_tokens": 2245,
"completion_tokens": 427,
"prompt_tokens_details": {
"cached_tokens": 114
}
},
"input_sensitive": false,
"output_sensitive": false,
"input_sensitive_type": 0,
"output_sensitive_type": 0,
"output_sensitive_int": 0,
"base_resp": {
"status_code": 0,
"status_msg": ""
}
}
},
"Deep Thinking": {
"value": {
"id": "066b366b8e8beeafd3b8b49f89e00648",
"choices": [
{
"finish_reason": "stop",
"index": 0,
"message": {
"content": "\nThe user is asking which is bigger, 9.11 or 9.9. This is a comparison of two decimal numbers.\n\n9.11 vs 9.9\n\nLet me think carefully:\n- 9.11 = 9 + 0.11\n- 9.9 = 9 + 0.90\n\n0.90 > 0.11, so 9.9 > 9.11.\n\nAlternatively, I can compare them as if they were both decimals to the same place:\n- 9.11\n- 9.90\n\nComparing the tenths place: 1 vs 9. Since 9 > 1, 9.9 is bigger.\n\nSo 9.9 is bigger than 9.11.\n\n**9.9 is bigger than 9.11.**\n\nIt can be tempting to think 9.11 > 9.9 because \"11\" looks larger than \"9,\" but decimals don't work that way. Here's why:\n\n- **9.11** = 9 + **0.11** (eleven hundredths)\n- **9.9** = 9 + **0.90** (ninety hundredths)\n\nSince 0.90 > 0.11, **9.9 is greater**. ✅\n\n**Tip:** When comparing decimals, compare them to the same number of decimal places. Write 9.9 as 9.90 — now it's easy to see that 9.90 > 9.11.",
"role": "assistant",
"name": "MiniMax AI",
"audio_content": ""
}
}
],
"created": 1780220779,
"model": "MiniMax-M3",
"object": "chat.completion",
"usage": {
"total_tokens": 484,
"total_characters": 0,
"prompt_tokens": 172,
"completion_tokens": 312,
"prompt_tokens_details": {
"cached_tokens": 159
}
},
"input_sensitive": false,
"output_sensitive": false,
"input_sensitive_type": 0,
"output_sensitive_type": 0,
"output_sensitive_int": 0,
"base_resp": {
"status_code": 0,
"status_msg": ""
}
}
},
"Stream": {
"value": [
{
"id": "066a34c738d29f6687fbf54ab6c98c34",
"choices": [
{
"index": 0,
"delta": {
"content": "\nThe user",
"role": "assistant",
"name": "MiniMax AI",
"audio_content": ""
}
}
],
"created": 1780154823,
"model": "MiniMax-M3",
"object": "chat.completion.chunk",
"usage": null,
"input_sensitive": false,
"output_sensitive": false,
"input_sensitive_type": 0,
"output_sensitive_type": 0,
"output_sensitive_int": 0
},
{
"id": "066a34c738d29f6687fbf54ab6c98c34",
"choices": [
{
"index": 0,
"delta": {
"content": " is asking what the image shows. I should describe the image in detail.\n\nThis image is",
"role": "assistant",
"name": "MiniMax AI",
"audio_content": ""
}
}
],
"created": 1780154823,
"model": "MiniMax-M3",
"object": "chat.completion.chunk",
"usage": null,
"input_sensitive": false,
"output_sensitive": false,
"input_sensitive_type": 0,
"output_sensitive_type": 0,
"output_sensitive_int": 0
},
{
"id": "066a34c738d29f6687fbf54ab6c98c34",
"choices": [
{
"index": 0,
"delta": {
"content": " a close-up portrait of a young girl, likely a toddler or preschool-aged child. Key details include:\n\n",
"role": "assistant",
"name": "MiniMax AI",
"audio_content": ""
}
}
],
"created": 1780154823,
"model": "MiniMax-M3",
"object": "chat.completion.chunk",
"usage": null,
"input_sensitive": false,
"output_sensitive": false,
"input_sensitive_type": 0,
"output_sensitive_type": 0,
"output_sensitive_int": 0
},
{
"id": "066a34c738d29f6687fbf54ab6c98c34",
"choices": [
{
"index": 0,
"delta": {
"content": "- **Facial expression**: She has a sweet, subtle smile and is looking directly at the camera",
"role": "assistant",
"name": "MiniMax AI",
"audio_content": ""
}
}
],
"created": 1780154823,
"model": "MiniMax-M3",
"object": "chat.completion.chunk",
"usage": null,
"input_sensitive": false,
"output_sensitive": false,
"input_sensitive_type": 0,
"output_sensitive_type": 0,
"output_sensitive_int": 0
},
{
"id": "066a34c738d29f6687fbf54ab6c98c34",
"choices": [
{
"index": 0,
"delta": {
"content": " with large, expressive hazel/light brown eyes.\n- **Hair**: She has tousled, wavy",
"role": "assistant",
"name": "MiniMax AI",
"audio_content": ""
}
}
],
"created": 1780154823,
"model": "MiniMax-M3",
"object": "chat.completion.chunk",
"usage": null,
"input_sensitive": false,
"output_sensitive": false,
"input_sensitive_type": 0,
"output_sensitive_type": 0,
"output_sensitive_int": 0
},
{
"id": "066a34c738d29f6687fbf54ab6c98c34",
"choices": [
{
"index": 0,
"delta": {
"content": " light brown/auburn hair with wispy bangs that frame her face, appearing somewhat wild and",
"role": "assistant",
"name": "MiniMax AI",
"audio_content": ""
}
}
],
"created": 1780154823,
"model": "MiniMax-M3",
"object": "chat.completion.chunk",
"usage": null,
"input_sensitive": false,
"output_sensitive": false,
"input_sensitive_type": 0,
"output_sensitive_type": 0,
"output_sensitive_int": 0
},
{
"id": "066a34c738d29f6687fbf54ab6c98c34",
"choices": [
{
"index": 0,
"delta": {
"content": " natural.\n- **Clothing**: She's wearing a cream or off-white top with delicate lace or ruff",
"role": "assistant",
"name": "MiniMax AI",
"audio_content": ""
}
}
],
"created": 1780154823,
"model": "MiniMax-M3",
"object": "chat.completion.chunk",
"usage": null,
"input_sensitive": false,
"output_sensitive": false,
"input_sensitive_type": 0,
"output_sensitive_type": 0,
"output_sensitive_int": 0
},
{
"id": "066a34c738d29f6687fbf54ab6c98c34",
"choices": [
{
"index": 0,
"delta": {
"content": "led detailing around the neckline, giving it a vintage or romantic feel.\n- **Lighting and mood",
"role": "assistant",
"name": "MiniMax AI",
"audio_content": ""
}
}
],
"created": 1780154823,
"model": "MiniMax-M3",
"object": "chat.completion.chunk",
"usage": null,
"input_sensitive": false,
"output_sensitive": false,
"input_sensitive_type": 0,
"output_sensitive_type": 0,
"output_sensitive_int": 0
},
{
"id": "066a34c738d29f6687fbf54ab6c98c34",
"choices": [
{
"index": 0,
"delta": {
"content": "**: The photo uses soft, warm lighting that highlights her features and creates a gentle, painter",
"role": "assistant",
"name": "MiniMax AI",
"audio_content": ""
}
}
],
"created": 1780154823,
"model": "MiniMax-M3",
"object": "chat.completion.chunk",
"usage": null,
"input_sensitive": false,
"output_sensitive": false,
"input_sensitive_type": 0,
"output_sensitive_type": 0,
"output_sensitive_int": 0
},
{
"id": "066a34c738d29f6687fbf54ab6c98c34",
"choices": [
{
"index": 0,
"delta": {
"content": "ly quality. The background is a neutral, muted olive-gray tone, which keeps the focus",
"role": "assistant",
"name": "MiniMax AI",
"audio_content": ""
}
}
],
"created": 1780154823,
"model": "MiniMax-M3",
"object": "chat.completion.chunk",
"usage": null,
"input_sensitive": false,
"output_sensitive": false,
"input_sensitive_type": 0,
"output_sensitive_type": 0,
"output_sensitive_int": 0
},
{
"id": "066a34c738d29f6687fbf54ab6c98c34",
"choices": [
{
"index": 0,
"delta": {
"content": " on her face.\n- **Style**: The overall aesthetic has an artistic, portrait-ph",
"role": "assistant",
"name": "MiniMax AI",
"audio_content": ""
}
}
],
"created": 1780154823,
"model": "MiniMax-M3",
"object": "chat.completion.chunk",
"usage": null,
"input_sensitive": false,
"output_sensitive": false,
"input_sensitive_type": 0,
"output_sensitive_type": 0,
"output_sensitive_int": 0
},
{
"id": "066a34c738d29f6687fbf54ab6c98c34",
"choices": [
{
"index": 0,
"delta": {
"content": "otography quality, reminiscent of fine art children's portraiture, with shallow depth of field that softly",
"role": "assistant",
"name": "MiniMax AI",
"audio_content": ""
}
}
],
"created": 1780154823,
"model": "MiniMax-M3",
"object": "chat.completion.chunk",
"usage": null,
"input_sensitive": false,
"output_sensitive": false,
"input_sensitive_type": 0,
"output_sensitive_type": 0,
"output_sensitive_int": 0
},
{
"id": "066a34c738d29f6687fbf54ab6c98c34",
"choices": [
{
"finish_reason": "stop",
"index": 0,
"delta": {
"content": " blurs the background.\n\nThe image evokes a sense of innocence, warmth, and charm.",
"role": "assistant",
"name": "MiniMax AI",
"audio_content": ""
}
}
],
"created": 1780154823,
"model": "MiniMax-M3",
"object": "chat.completion.chunk",
"usage": null,
"input_sensitive": false,
"output_sensitive": false,
"input_sensitive_type": 0,
"output_sensitive_type": 0,
"output_sensitive_int": 0
}
]
},
"Tool Use": {
"value": {
"id": "066b13237d4accbb697b81f696876915",
"choices": [
{
"finish_reason": "tool_calls",
"index": 0,
"message": {
"content": "\nThe user is asking about the weather in San Francisco. I'll use the get_weather tool to retrieve this information.\n\n",
"role": "assistant",
"name": "MiniMax AI",
"tool_calls": [
{
"id": "call_function_a1nrtksph4pi_1",
"type": "function",
"function": {
"name": "get_weather",
"arguments": "{\"location\": \"San Francisco, US\"}"
},
"index": 0
}
],
"audio_content": ""
}
}
],
"created": 1780211747,
"model": "MiniMax-M3",
"object": "chat.completion",
"usage": {
"total_tokens": 473,
"total_characters": 0,
"prompt_tokens": 418,
"completion_tokens": 55,
"prompt_tokens_details": {
"cached_tokens": 114
}
},
"input_sensitive": false,
"output_sensitive": false,
"input_sensitive_type": 0,
"output_sensitive_type": 0,
"output_sensitive_int": 0,
"base_resp": {
"status_code": 0,
"status_msg": ""
}
}
}
}
},
"text/event-stream": {
"schema": {
"$ref": "#/components/schemas/ChatCompletionChunk"
},
"examples": {
"Stream": {
"value": [
{
"id": "066a34c738d29f6687fbf54ab6c98c34",
"choices": [
{
"index": 0,
"delta": {
"content": "\nThe user",
"role": "assistant",
"name": "MiniMax AI",
"audio_content": ""
}
}
],
"created": 1780154823,
"model": "MiniMax-M3",
"object": "chat.completion.chunk",
"usage": null,
"input_sensitive": false,
"output_sensitive": false,
"input_sensitive_type": 0,
"output_sensitive_type": 0,
"output_sensitive_int": 0
},
{
"id": "066a34c738d29f6687fbf54ab6c98c34",
"choices": [
{
"index": 0,
"delta": {
"content": " is asking what the image shows. I should describe the image in detail.\n\nThis image is",
"role": "assistant",
"name": "MiniMax AI",
"audio_content": ""
}
}
],
"created": 1780154823,
"model": "MiniMax-M3",
"object": "chat.completion.chunk",
"usage": null,
"input_sensitive": false,
"output_sensitive": false,
"input_sensitive_type": 0,
"output_sensitive_type": 0,
"output_sensitive_int": 0
},
{
"id": "066a34c738d29f6687fbf54ab6c98c34",
"choices": [
{
"index": 0,
"delta": {
"content": " a close-up portrait of a young girl, likely a toddler or preschool-aged child. Key details include:\n\n",
"role": "assistant",
"name": "MiniMax AI",
"audio_content": ""
}
}
],
"created": 1780154823,
"model": "MiniMax-M3",
"object": "chat.completion.chunk",
"usage": null,
"input_sensitive": false,
"output_sensitive": false,
"input_sensitive_type": 0,
"output_sensitive_type": 0,
"output_sensitive_int": 0
},
{
"id": "066a34c738d29f6687fbf54ab6c98c34",
"choices": [
{
"index": 0,
"delta": {
"content": "- **Facial expression**: She has a sweet, subtle smile and is looking directly at the camera",
"role": "assistant",
"name": "MiniMax AI",
"audio_content": ""
}
}
],
"created": 1780154823,
"model": "MiniMax-M3",
"object": "chat.completion.chunk",
"usage": null,
"input_sensitive": false,
"output_sensitive": false,
"input_sensitive_type": 0,
"output_sensitive_type": 0,
"output_sensitive_int": 0
},
{
"id": "066a34c738d29f6687fbf54ab6c98c34",
"choices": [
{
"index": 0,
"delta": {
"content": " with large, expressive hazel/light brown eyes.\n- **Hair**: She has tousled, wavy",
"role": "assistant",
"name": "MiniMax AI",
"audio_content": ""
}
}
],
"created": 1780154823,
"model": "MiniMax-M3",
"object": "chat.completion.chunk",
"usage": null,
"input_sensitive": false,
"output_sensitive": false,
"input_sensitive_type": 0,
"output_sensitive_type": 0,
"output_sensitive_int": 0
},
{
"id": "066a34c738d29f6687fbf54ab6c98c34",
"choices": [
{
"index": 0,
"delta": {
"content": " light brown/auburn hair with wispy bangs that frame her face, appearing somewhat wild and",
"role": "assistant",
"name": "MiniMax AI",
"audio_content": ""
}
}
],
"created": 1780154823,
"model": "MiniMax-M3",
"object": "chat.completion.chunk",
"usage": null,
"input_sensitive": false,
"output_sensitive": false,
"input_sensitive_type": 0,
"output_sensitive_type": 0,
"output_sensitive_int": 0
},
{
"id": "066a34c738d29f6687fbf54ab6c98c34",
"choices": [
{
"index": 0,
"delta": {
"content": " natural.\n- **Clothing**: She's wearing a cream or off-white top with delicate lace or ruff",
"role": "assistant",
"name": "MiniMax AI",
"audio_content": ""
}
}
],
"created": 1780154823,
"model": "MiniMax-M3",
"object": "chat.completion.chunk",
"usage": null,
"input_sensitive": false,
"output_sensitive": false,
"input_sensitive_type": 0,
"output_sensitive_type": 0,
"output_sensitive_int": 0
},
{
"id": "066a34c738d29f6687fbf54ab6c98c34",
"choices": [
{
"index": 0,
"delta": {
"content": "led detailing around the neckline, giving it a vintage or romantic feel.\n- **Lighting and mood",
"role": "assistant",
"name": "MiniMax AI",
"audio_content": ""
}
}
],
"created": 1780154823,
"model": "MiniMax-M3",
"object": "chat.completion.chunk",
"usage": null,
"input_sensitive": false,
"output_sensitive": false,
"input_sensitive_type": 0,
"output_sensitive_type": 0,
"output_sensitive_int": 0
},
{
"id": "066a34c738d29f6687fbf54ab6c98c34",
"choices": [
{
"index": 0,
"delta": {
"content": "**: The photo uses soft, warm lighting that highlights her features and creates a gentle, painter",
"role": "assistant",
"name": "MiniMax AI",
"audio_content": ""
}
}
],
"created": 1780154823,
"model": "MiniMax-M3",
"object": "chat.completion.chunk",
"usage": null,
"input_sensitive": false,
"output_sensitive": false,
"input_sensitive_type": 0,
"output_sensitive_type": 0,
"output_sensitive_int": 0
},
{
"id": "066a34c738d29f6687fbf54ab6c98c34",
"choices": [
{
"index": 0,
"delta": {
"content": "ly quality. The background is a neutral, muted olive-gray tone, which keeps the focus",
"role": "assistant",
"name": "MiniMax AI",
"audio_content": ""
}
}
],
"created": 1780154823,
"model": "MiniMax-M3",
"object": "chat.completion.chunk",
"usage": null,
"input_sensitive": false,
"output_sensitive": false,
"input_sensitive_type": 0,
"output_sensitive_type": 0,
"output_sensitive_int": 0
},
{
"id": "066a34c738d29f6687fbf54ab6c98c34",
"choices": [
{
"index": 0,
"delta": {
"content": " on her face.\n- **Style**: The overall aesthetic has an artistic, portrait-ph",
"role": "assistant",
"name": "MiniMax AI",
"audio_content": ""
}
}
],
"created": 1780154823,
"model": "MiniMax-M3",
"object": "chat.completion.chunk",
"usage": null,
"input_sensitive": false,
"output_sensitive": false,
"input_sensitive_type": 0,
"output_sensitive_type": 0,
"output_sensitive_int": 0
},
{
"id": "066a34c738d29f6687fbf54ab6c98c34",
"choices": [
{
"index": 0,
"delta": {
"content": "otography quality, reminiscent of fine art children's portraiture, with shallow depth of field that softly",
"role": "assistant",
"name": "MiniMax AI",
"audio_content": ""
}
}
],
"created": 1780154823,
"model": "MiniMax-M3",
"object": "chat.completion.chunk",
"usage": null,
"input_sensitive": false,
"output_sensitive": false,
"input_sensitive_type": 0,
"output_sensitive_type": 0,
"output_sensitive_int": 0
},
{
"id": "066a34c738d29f6687fbf54ab6c98c34",
"choices": [
{
"finish_reason": "stop",
"index": 0,
"delta": {
"content": " blurs the background.\n\nThe image evokes a sense of innocence, warmth, and charm.",
"role": "assistant",
"name": "MiniMax AI",
"audio_content": ""
}
}
],
"created": 1780154823,
"model": "MiniMax-M3",
"object": "chat.completion.chunk",
"usage": null,
"input_sensitive": false,
"output_sensitive": false,
"input_sensitive_type": 0,
"output_sensitive_type": 0,
"output_sensitive_int": 0
}
]
}
}
}
}
}
}
}
}
},
"components": {
"schemas": {
"ChatCompletionReq": {
"type": "object",
"required": [
"model",
"messages"
],
"properties": {
"model": {
"type": "string",
"description": "Model ID",
"enum": [
"MiniMax-M3",
"MiniMax-M2.7",
"MiniMax-M2.7-highspeed",
"MiniMax-M2.5",
"MiniMax-M2.5-highspeed",
"MiniMax-M2.1",
"MiniMax-M2.1-highspeed",
"MiniMax-M2"
]
},
"service_tier": {
"type": "string",
"description": "Service tier for request admission. Supported values are `standard` and `priority`. If omitted, the request uses the `standard` tier. The `priority` [price](/guides/pricing-paygo) is 1.5 times the `standard` price and ensures priority admission so the request is processed ahead of other requests, leading to faster responses and fewer failures.",
"enum": [
"standard",
"priority"
],
"default": "standard"
},
"messages": {
"type": "array",
"description": "A list of messages containing the conversation history. Supports text, image, video, and tool call content.",
"items": {
"$ref": "#/components/schemas/Message"
}
},
"thinking": {
"type": "object",
"description": "Controls MiniMax-M3 thinking. When omitted, adaptive thinking is enabled by default and responses include thinking content. For M2.x models, thinking cannot be disabled.",
"properties": {
"type": {
"type": "string",
"enum": [
"disabled",
"adaptive"
],
"default": "adaptive",
"description": "Thinking control type.\n- `disabled`: Skip thinking for MiniMax-M3 and answer directly. For M2.x models, thinking remains on.\n- `adaptive`: Enable adaptive thinking for MiniMax-M3. This is the default when `thinking` is omitted."
}
},
"required": []
},
"reasoning_split": {
"type": "boolean",
"description": "Output-format switch. When enabled, separates thinking content into the `reasoning_content` and `reasoning_details` fields. This does not enable or disable thinking."
},
"stream": {
"type": "boolean",
"description": "Whether to use streaming output, defaults to `false`. When set to `true`, the response will be returned in chunks.",
"default": false
},
"stream_options": {
"type": "object",
"description": "Streaming response options.",
"properties": {
"include_usage": {
"type": "boolean",
"default": false,
"description": "Whether to include token usage in the streaming response."
}
}
},
"max_completion_tokens": {
"type": "integer",
"format": "int64",
"description": "Specifies the upper limit for generated content length, in tokens. For MiniMax-M3 the recommended value is 131072 (128K) and the maximum is 524288 (512K); for other models the recommended value is 65536 (64K) and the maximum is 204800 (200K). If generation stops due to `length`, try increasing this value.",
"minimum": 1
},
"temperature": {
"type": "number",
"format": "double",
"description": "Temperature coefficient, affects output randomness. Range [0, 2], default 1. Higher values produce more random output; lower values produce more deterministic output.",
"minimum": 0,
"maximum": 2,
"default": 1
},
"top_p": {
"type": "number",
"format": "double",
"description": "Nucleus sampling parameter. Range [0, 1]. Default is 0.95 for MiniMax-M3 and 0.9 for M2.x models.",
"minimum": 0,
"maximum": 1,
"default": 0.95
},
"tools": {
"type": "array",
"description": "Tool definition list. Function tools are supported.",
"items": {
"type": "object",
"properties": {
"type": {
"type": "string",
"enum": [
"function"
],
"description": "Tool type, always function."
},
"function": {
"type": "object",
"properties": {
"name": {
"type": "string",
"description": "Function name."
},
"description": {
"type": "string",
"description": "Function description."
},
"parameters": {
"type": "object",
"description": "Function parameters JSON Schema."
}
},
"required": [
"name",
"parameters"
]
}
},
"required": [
"type",
"function"
]
}
},
"max_tokens": {
"type": "integer",
"format": "int64",
"deprecated": true,
"description": "Legacy generation length limit parameter. Deprecated; use `max_completion_tokens` instead.",
"minimum": 1
}
}
},
"ChatCompletionResp": {
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "Unique ID of this response"
},
"choices": {
"type": "array",
"description": "List of response choices",
"items": {
"type": "object",
"properties": {
"finish_reason": {
"type": "string",
"description": "Reason for stopping generation: `stop`, `length`, `content_filter`, or `tool_calls`.",
"enum": [
"stop",
"length",
"content_filter",
"tool_calls"
]
},
"index": {
"type": "integer",
"description": "Index of the choice, starting from 0"
},
"message": {
"type": "object",
"description": "Complete reply generated by the model",
"required": [
"content",
"role"
],
"properties": {
"content": {
"type": "string",
"description": "Text reply content"
},
"reasoning_content": {
"type": "string",
"description": "Thinking content. Returned only when reasoning_split is enabled."
},
"reasoning_details": {
"type": "array",
"description": "Structured thinking content. Returned only when reasoning_split is enabled.",
"items": {
"type": "object",
"properties": {
"type": {
"type": "string",
"description": "Reasoning detail type, for example `reasoning.text`."
},
"id": {
"type": "string",
"description": "Identifier of the reasoning segment."
},
"format": {
"type": "string",
"description": "Format identifier of the reasoning content, for example `MiniMax-response-v1`."
},
"index": {
"type": "integer",
"description": "Order index of the reasoning segment."
},
"text": {
"type": "string",
"description": "Thinking text of this segment."
}
}
}
},
"role": {
"type": "string",
"description": "Role, fixed as `assistant`",
"enum": [
"assistant"
]
},
"tool_calls": {
"type": "array",
"description": "Tool calls generated by the model. Returned only when `finish_reason` is `tool_calls`. Echo each entry back as part of the next-turn assistant message and pair it with a `role: tool` message whose `tool_call_id` equals the entry's `id`.",
"items": {
"$ref": "#/components/schemas/ToolCall"
}
}
}
}
}
}
},
"created": {
"type": "integer",
"format": "int64",
"description": "Unix timestamp (seconds) when the response was created"
},
"model": {
"type": "string",
"description": "Model ID used for this request"
},
"object": {
"type": "string",
"description": "Object type. `chat.completion` for non-streaming, `chat.completion.chunk` for streaming",
"enum": [
"chat.completion",
"chat.completion.chunk"
]
},
"usage": {
"$ref": "#/components/schemas/Usage"
},
"input_sensitive": {
"type": "boolean",
"description": "Whether the input content triggered sensitive word detection. If the input content is severely inappropriate, the API will return a content violation error message with empty reply content"
},
"input_sensitive_type": {
"type": "integer",
"format": "int64",
"description": "Type of sensitive word triggered by input, returned when input_sensitive is true. Values: 1 Severe violation; 2 Pornography; 3 Advertising; 4 Prohibited; 5 Abuse; 6 Violence/Terrorism; 7 Other"
},
"output_sensitive": {
"type": "boolean",
"description": "Whether the output content triggered sensitive word detection. If the output content is severely inappropriate, the API will return a content violation error message with empty reply content"
},
"output_sensitive_type": {
"type": "integer",
"format": "int64",
"description": "Type of sensitive word triggered by output"
},
"base_resp": {
"type": "object",
"description": "Error status code and details",
"properties": {
"status_code": {
"type": "integer",
"format": "int64",
"description": "Status code\n\n- `1000`: Unknown error\n- `1001`: Request timeout\n- `1002`: Rate limit triggered\n- `1004`: Authentication failed\n- `1008`: Insufficient balance\n- `1013`: Internal server error\n- `1027`: Output content error\n- `1039`: Token limit exceeded\n- `2013`: Parameter error\n\nFor more details, see [Error Code Reference](/api-reference/errorcode)"
},
"status_msg": {
"type": "string",
"description": "Error details"
}
}
}
}
},
"Message": {
"type": "object",
"required": [
"role"
],
"properties": {
"role": {
"type": "string",
"enum": [
"system",
"user",
"assistant",
"tool"
],
"description": "Role of the message sender."
},
"name": {
"type": "string",
"description": "Name of the sender. If there are multiple roles of the same type, a specific name must be provided to distinguish them"
},
"content": {
"oneOf": [
{
"type": "string",
"description": "Text message content"
},
{
"type": "array",
"description": "Multimodal message content parts. MiniMax-M3 supports text, image, and video input.\n\n**File size and request limits**\n- URL or Base64 input: video file ≤ 50 MB, image file ≤ 10 MB, request body ≤ 64 MB.\n- Files API upload: referenced in `content` as `mm_file://{file_id}`, with a single video up to 512 MB.",
"items": {
"$ref": "#/components/schemas/MessageContentPart"
}
}
],
"description": "Message content. MiniMax-M3 supports text, image, and video content parts."
},
"tool_calls": {
"type": "array",
"description": "Tool call list in an assistant message.",
"items": {
"$ref": "#/components/schemas/ToolCall"
}
},
"tool_call_id": {
"type": "string",
"description": "Tool call ID. Required when `role` is `tool`. Set this to the `id` of the corresponding entry in the assistant message's `tool_calls` so the model can match the tool result with the originating call. Ignored for other roles."
}
}
},
"MessageContentPart": {
"type": "object",
"required": [
"type"
],
"description": "Multimodal message content part. Each part declares its kind via `type`, and only the field matching that type should be populated.",
"properties": {
"type": {
"type": "string",
"enum": [
"text",
"image_url",
"video_url"
],
"description": "Content part type:\n- `text`: Text part\n- `image_url`: Image input\n- `video_url`: Video input"
},
"text": {
"type": "string",
"description": "Text content (when `type` is `text`)."
},
"image_url": {
"type": "object",
"description": "Image input (when `type` is `image_url`). Each image can be up to 10 MB.\n\n**Supported image formats**\n\n| Format | Common extensions | MIME Type |\n| :-- | :-- | :-- |\n| JPEG | .jpg, .jpeg | image/jpeg |\n| PNG | .png | image/png |\n| GIF | .gif | image/gif |\n| WEBP | .webp | image/webp |",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"description": "Image URL or Base64 data URL."
},
"detail": {
"type": "string",
"enum": [
"low",
"default",
"high"
],
"default": "default",
"description": "Controls image resolution. Defaults to default.\n\nRough single-image token usage heuristic:\n\n| detail | Rough token usage |\n| :-- | :-- |\n| low | Usually a few hundred tokens, up to ~600 |\n| default | Often ~1k-3k tokens, up to ~5k |\n| high | Often several thousand tokens, up to ~15k+ |\n\nActual usage depends on image size and content; check response usage or token counting where available."
},
"max_long_side_pixel": {
"type": "integer",
"minimum": 1,
"description": "Longest-side pixel limit for the image."
}
}
},
"video_url": {
"type": "object",
"description": "Video input (when `type` is `video_url`).\n\n**Supported video formats**\n\n| Format | Common extensions | MIME Type |\n| :-- | :-- | :-- |\n| MP4 | .mp4 | video/mp4 |\n| AVI | .avi | video/avi or video/x-msvideo |\n| MOV | .mov | URL input: set the object storage Content-Type to video/quicktime; base64 input: use video/mov, i.e. data:video/mov;base64, |\n| MKV | .mkv | video/x-matroska |",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"description": "Video URL, Base64 data URL, or Files API reference in the form `mm_file://{file_id}`. To obtain a `file_id`, first upload the video via the [Upload File](/api-reference/file-management-upload) API. URL or Base64 videos can be up to 50 MB; Files API videos can be up to 512 MB."
},
"detail": {
"type": "string",
"enum": [
"low",
"default",
"high"
],
"default": "default",
"description": "Controls per-frame video resolution. Defaults to default."
},
"fps": {
"type": "number",
"minimum": 0.2,
"maximum": 5,
"default": 1,
"description": "Video frame sampling rate. Defaults to 1. Range [0.2, 5].\n- Higher values: more sensitive to scene changes, but higher token cost and slower response.\n- Lower values: lower token cost and faster response, but less sensitive to scene changes."
},
"max_long_side_pixel": {
"type": "integer",
"minimum": 1,
"description": "Longest-side pixel limit for video frames."
}
}
}
}
},
"ToolCall": {
"type": "object",
"required": [
"id",
"type",
"function"
],
"description": "Tool call generated by the model in an assistant message.",
"properties": {
"id": {
"type": "string",
"description": "Tool call ID, generated by the model."
},
"type": {
"type": "string",
"enum": [
"function"
],
"description": "Tool call type. Currently only `function` is supported."
},
"function": {
"type": "object",
"required": [
"name",
"arguments"
],
"properties": {
"name": {
"type": "string",
"description": "Name of the function to call."
},
"arguments": {
"type": "string",
"description": "Function arguments as a JSON-formatted string."
}
}
}
}
},
"Choice": {
"type": "object",
"properties": {
"index": {
"type": "integer",
"description": "Index of the choice"
},
"message": {
"$ref": "#/components/schemas/Message"
},
"finish_reason": {
"type": "string",
"enum": [
"stop",
"length",
"content_filter",
"tool_calls"
],
"description": "Reason for completion."
}
}
},
"Usage": {
"type": "object",
"description": "Token usage statistics for this request",
"properties": {
"total_tokens": {
"type": "integer",
"description": "Total number of tokens consumed"
}
}
},
"ChatCompletionChunk": {
"type": "object",
"description": "",
"properties": {
"id": {
"type": "string",
"description": "Unique ID of this response"
},
"choices": {
"type": "array",
"description": "List of streaming response choices",
"items": {
"type": "object",
"properties": {
"index": {
"type": "integer",
"description": "Index of the choice, starting from 0"
},
"delta": {
"type": "object",
"description": "Incremental content",
"properties": {
"role": {
"type": "string",
"description": "Role, fixed as `assistant`",
"enum": [
"assistant"
]
},
"content": {
"type": "string",
"description": "Incremental text content"
}
}
},
"finish_reason": {
"type": "string",
"nullable": true,
"description": "Reason for stopping generation, null when not finished: `stop` (natural ending), `length` (reached `max_completion_tokens` limit)",
"enum": [
"stop",
"length"
]
}
}
}
},
"created": {
"type": "integer",
"format": "int64",
"description": "Unix timestamp (seconds) when the response was created"
},
"model": {
"type": "string",
"description": "Model ID used for this request"
},
"object": {
"type": "string",
"description": "Object type, fixed as `chat.completion.chunk`",
"enum": [
"chat.completion.chunk"
]
},
"usage": {
"$ref": "#/components/schemas/Usage",
"description": "Token usage (only returned in the last chunk)"
},
"input_sensitive_type": {
"type": "integer",
"format": "int64",
"description": "Type of sensitive word triggered by input"
},
"output_sensitive": {
"type": "boolean",
"description": "Whether the output content triggered sensitive word detection"
},
"output_sensitive_type": {
"type": "integer",
"format": "int64",
"description": "Type of sensitive word triggered by output"
}
}
}
},
"securitySchemes": {
"bearerAuth": {
"type": "http",
"scheme": "bearer",
"bearerFormat": "JWT",
"description": "`HTTP: Bearer Auth`\n - Security Scheme Type: http\n - HTTP Authorization Scheme: Bearer API_key, used for account verification, can be viewed in [Account Management > API Keys](https://platform.minimax.io/user-center/basic-information/interface-key)"
}
}
}
}