Skip to main content
POST
/
v1
/
chat
/
completions
curl --request POST \
  --url https://api.minimax.io/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: <content-type>' \
  --data '
{
  "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
}
'
{
  "id": "066a33a7d290378f8a9e57a055812afa",
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "message": {
        "content": "<think>\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</think>\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": ""
  }
}
✨ New model — MiniMax-M3Core capabilities: Coding/Agentic SOTA, 1M long context, multimodal.
What’s new in MiniMax-M3:
  1. Image and video understanding — see the example code on the right
  2. Control thinking via the thinking parameter

Authorizations

​
Authorization
string
header
required

HTTP: Bearer Auth

  • Security Scheme Type: http
  • HTTP Authorization Scheme: Bearer API_key, used for account verification, can be viewed in Account Management > API Keys

Headers

​
Content-Type
enum<string>
default:application/json
required

Media type of the request body, should be set to application/json to ensure JSON format

Available options:
application/json

Body

application/json
​
model
enum<string>
required

Model ID

Available options:
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
​
messages
object[]
required

A list of messages containing the conversation history. Supports text, image, video, and tool call content.

​
service_tier
enum<string>
default:standard

Service tier for request admission. Supported values are standard and priority. If omitted, the request uses the standard tier. The priority price 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.

Available options:
standard,
priority
​
thinking
object

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.

​
reasoning_split
boolean

Output-format switch. When enabled, separates thinking content into the reasoning_content and reasoning_details fields. This does not enable or disable thinking.

​
stream
boolean
default:false

Whether to use streaming output, defaults to false. When set to true, the response will be returned in chunks.

​
stream_options
object

Streaming response options.

​
max_completion_tokens
integer<int64>

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.

Required range: x >= 1
​
temperature
number<double>
default:1

Temperature coefficient, affects output randomness. Range [0, 2], default 1. Higher values produce more random output; lower values produce more deterministic output.

Required range: 0 <= x <= 2
​
top_p
number<double>
default:0.95

Nucleus sampling parameter. Range [0, 1]. Default is 0.95 for MiniMax-M3 and 0.9 for M2.x models.

Required range: 0 <= x <= 1
​
tools
object[]

Tool definition list. Function tools are supported.

​
max_tokens
integer<int64>
deprecated

Legacy generation length limit parameter. Deprecated; use max_completion_tokens instead.

Required range: x >= 1

Response

​
id
string

Unique ID of this response

​
choices
object[]

List of response choices

​
created
integer<int64>

Unix timestamp (seconds) when the response was created

​
model
string

Model ID used for this request

​
object
enum<string>

Object type. chat.completion for non-streaming, chat.completion.chunk for streaming

Available options:
chat.completion,
chat.completion.chunk
​
usage
object

Token usage statistics for this request

​
input_sensitive
boolean

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
integer<int64>

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
boolean

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
integer<int64>

Type of sensitive word triggered by output

​
base_resp
object

Error status code and details