> ## Documentation Index
> Fetch the complete documentation index at: https://platform.minimax.io/docs/llms.txt
> Use this file to discover all available pages before exploring further.
# Chat Completions API (OpenAI-compatible)
> Use the OpenAI API compatible Chat Completions format to call MiniMax models.
✨ **New model — `MiniMax-M3`**
**Core 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
## OpenAPI
````yaml /api-reference/text/api/openapi-chat-openai.json POST /v1/chat/completions
openapi: 3.1.0
info:
title: MiniMax Text API OpenAI
description: >
MiniMax text generation API with support for chat completion and streaming
output.
> ⚡ **`MiniMax-M3` highlights** — **Coding/Agentic SOTA**, **1M long
context**, and **multimodal**.
license:
name: MIT
version: 1.0.0
servers:
- url: https://api.minimax.io
security:
- bearerAuth: []
paths:
/v1/chat/completions:
post:
tags:
- Text Generation
summary: Text Generation OpenAI
operationId: chatCompletionOpenAI
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: >-
The user is asking me to describe an image. Let me
look at it carefully and provide a description.
The 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.
This image is a warm, softly-lit portrait photograph
of a young girl, likely a child around 4-6 years
old. Key features include:
- **Hair**: Wavy/curly brown hair with bangs, with
some strands pulled back or styled on top
- **Eyes**: Large, expressive amber/brown eyes
looking directly at the camera
- **Expression**: A gentle, sweet smile
- **Clothing**: A cream or off-white dress with
delicate lace trim and ruffled cap sleeves
- **Lighting**: Soft, warm, golden lighting that
gives the image a dreamy, classic portrait quality
- **Background**: A neutral, muted grayish-brown
backdrop, blurred to keep focus on the subject
The 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: >-
The user wants me to describe the action in the
video.
1. **Analyze the video:**
* The video shows an AI-generated scene (indicated by the "MINIMAX" and "Hailuo AI" watermarks).
* 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).
* 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.
* The cat is walking on a diving board. It starts on the left side and walks towards the right.
* Around 0.2 seconds, the cat reaches the end of the diving board and leaps off.
* The cat is airborne for a brief moment, performing what looks like a basic jump, not a complex dive.
* It falls towards the water below.
* It hits the water and splashes.
* The camera follows the cat's trajectory.
* The background shows a crowd of spectators sitting in the stands, watching the event.
* A person is standing on the pool deck, observing.
2. **Synthesize the description:**
* Start with the main subject and action: A cat is walking on a diving board.
* Describe the progression: It walks to the end.
* Describe the climax: It jumps off the board.
* Describe the conclusion: It falls into the water below.
* Keep it concise and objective.
3. **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).
A 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: >-
The user is asking which is bigger, 9.11 or 9.9.
This is a comparison of two decimal numbers.
9.11 vs 9.9
Let me think carefully:
- 9.11 = 9 + 0.11
- 9.9 = 9 + 0.90
0.90 > 0.11, so 9.9 > 9.11.
Alternatively, I can compare them as if they were
both decimals to the same place:
- 9.11
- 9.90
Comparing the tenths place: 1 vs 9. Since 9 > 1, 9.9
is bigger.
So 9.9 is bigger than 9.11.
**9.9 is bigger than 9.11.**
It 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:
- **9.11** = 9 + **0.11** (eleven hundredths)
- **9.9** = 9 + **0.90** (ninety hundredths)
Since 0.90 > 0.11, **9.9 is greater**. ✅
**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: |-
The 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: |2-
is asking what the image shows. I should describe the image in detail.
This 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: |2+
a close-up portrait of a young girl, likely a toddler or preschool-aged child. Key details include:
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: |2-
with large, expressive hazel/light brown eyes.
- **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: >2-
natural.
- **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.
- **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: >2-
on her face.
- **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: >2-
blurs the background.
The 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: >
The user is asking about the weather in San
Francisco. I'll use the get_weather tool to retrieve
this information.
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: |-
The 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: |2-
is asking what the image shows. I should describe the image in detail.
This 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: |2+
a close-up portrait of a young girl, likely a toddler or preschool-aged child. Key details include:
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: |2-
with large, expressive hazel/light brown eyes.
- **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: >2-
natural.
- **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.
- **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: >2-
on her face.
- **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: >2-
blurs the background.
The 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
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 deep thinking.
properties:
type:
type: string
enum:
- disabled
- adaptive
default: adaptive
description: >-
Deep-thinking mode.
- `disabled`: Skip thinking and answer directly.
- `adaptive`: Let the model decide whether to think (recommended
default).
reasoning_split:
type: boolean
description: >-
When enabled, separates thinking content into the
`reasoning_content` and `reasoning_details` fields.
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
- `1000`: Unknown error
- `1001`: Request timeout
- `1002`: Rate limit triggered
- `1004`: Authentication failed
- `1008`: Insufficient balance
- `1013`: Internal server error
- `1027`: Output content error
- `1039`: Token limit exceeded
- `2013`: Parameter error
For more details, see [Error Code
Reference](/api-reference/errorcode)
status_msg:
type: string
description: Error details
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
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.
**File size and request limits**
- URL or Base64 input: video file ≤ 50 MB, image file ≤ 10 MB,
request body ≤ 64 MB.
- 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.
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.
Usage:
type: object
description: Token usage statistics for this request
properties:
total_tokens:
type: integer
description: Total number of tokens consumed
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:
- `text`: Text part
- `image_url`: Image input
- `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.
**Supported image formats**
| Format | Common extensions | MIME Type |
| :-- | :-- | :-- |
| JPEG | .jpg, .jpeg | image/jpeg |
| PNG | .png | image/png |
| GIF | .gif | image/gif |
| 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.
Rough single-image token usage heuristic:
| detail | Rough token usage |
| :-- | :-- |
| low | Usually a few hundred tokens, up to ~600 |
| default | Often ~1k-3k tokens, up to ~5k |
| high | Often several thousand tokens, up to ~15k+ |
Actual 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`).
**Supported video formats**
| Format | Common extensions | MIME Type |
| :-- | :-- | :-- |
| MP4 | .mp4 | video/mp4 |
| AVI | .avi | video/avi or video/x-msvideo |
| MOV | .mov | URL input: set the object storage Content-Type to
video/quicktime; base64 input: use video/mov, i.e.
data:video/mov;base64, |
| 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].
- Higher values: more sensitive to scene changes, but higher
token cost and slower response.
- 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.
securitySchemes:
bearerAuth:
type: http
scheme: bearer
bearerFormat: JWT
description: |-
`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](https://platform.minimax.io/user-center/basic-information/interface-key)
````