> ## Documentation Index
> Fetch the complete documentation index at: https://docs.evolink.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Kimi K2 - Complete API Reference
> - Use OpenAI SDK format to call Kimi-K2 model
- Synchronous processing mode, real-time response
- **Text conversation**: Single or multi-turn contextual dialogue, see simple_text and multi_turn examples
- **System prompts**: Customize AI role and behavior, see system_prompt example
- **Multimodal input**: Supports text + image mixed input, see vision example
- **Tool calling**: Supports Function Calling, see tool_use example
- **Partial Mode**: Supports prefill mode, see partial_mode example
**BaseURL**: The default BaseURL is `https://direct.evolink.ai`, which has better support for text models and long-lived connections. `https://api.evolink.ai` is the primary endpoint for multimodal services and serves as a fallback address for text models.
## OpenAPI
````yaml /en/api-manual/language-series/kimi-k2/Kimi-K2-api.json POST /v1/chat/completions
openapi: 3.1.0
info:
title: Kimi-K2 Complete API Reference
description: >-
Complete API reference for Kimi-K2 chat interface, including all parameters
and advanced features
license:
name: MIT
version: 1.0.0
servers:
- url: https://direct.evolink.ai
description: Production (recommended)
- url: https://api.evolink.ai
description: Alternative URL
security:
- bearerAuth: []
tags:
- name: Chat Completion
description: AI chat completion related endpoints
paths:
/v1/chat/completions:
post:
tags:
- Chat Completion
summary: Kimi-K2 Chat Interface
description: >-
- Use OpenAI SDK format to call Kimi-K2 model
- Synchronous processing mode, real-time response
- **Text conversation**: Single or multi-turn contextual dialogue, see
simple_text and multi_turn examples
- **System prompts**: Customize AI role and behavior, see system_prompt
example
- **Multimodal input**: Supports text + image mixed input, see vision
example
- **Tool calling**: Supports Function Calling, see tool_use example
- **Partial Mode**: Supports prefill mode, see partial_mode example
operationId: createChatCompletion
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/ChatCompletionRequest'
examples:
simple_text:
summary: Single-turn text conversation
value:
model: kimi-k2-thinking
messages:
- role: user
content: Please introduce yourself
temperature: 1
multi_turn:
summary: Multi-turn conversation (context understanding)
value:
model: kimi-k2-thinking
messages:
- role: user
content: What is Python?
- role: assistant
content: Python is a high-level programming language...
- role: user
content: What are its advantages?
temperature: 1
system_prompt:
summary: Using system prompts
value:
model: kimi-k2-thinking
messages:
- role: system
content: >-
You are Kimi, an AI assistant provided by Moonshot AI.
You excel at conversations in both Chinese and English.
You provide safe, helpful, and accurate answers. You
will reject any questions involving terrorism, racial
discrimination, or violence.
- role: user
content: What is 1+1?
temperature: 1
vision:
summary: Multimodal input (text + image)
value:
model: kimi-k2-thinking
messages:
- role: user
content:
- type: text
text: >-
Please describe the scene and main elements in this
image in detail.
- type: image_url
image_url:
url: >-
data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR42mNk+M9QDwADhgGAWjR9awAAAABJRU5ErkJggg==
temperature: 1
tool_use:
summary: Tool calling (Function Calling)
value:
model: kimi-k2-thinking
messages:
- role: user
content: Write code to determine if 3214567 is a prime number.
tools:
- type: function
function:
name: CodeRunner
description: >-
Code executor that supports running python and
javascript code
parameters:
type: object
properties:
language:
type: string
enum:
- python
- javascript
code:
type: string
description: Write your code here
temperature: 1
partial_mode:
summary: Partial Mode (prefill mode)
value:
model: kimi-k2-thinking
messages:
- role: system
content: >-
Extract name, size, price and colors from the product
description and output as a JSON object.
- role: user
content: >-
The SmartHome Mini is a compact smart home assistant,
available in black and silver, priced at $149, with
dimensions of 256 x 128 x 128mm.
- role: assistant
content: '{'
partial: true
temperature: 1
responses:
'200':
description: Chat completion successful
content:
application/json:
schema:
$ref: '#/components/schemas/ChatCompletionResponse'
'400':
description: Invalid request parameters
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
example:
error:
code: 400
message: Invalid request parameters
type: invalid_request_error
'401':
description: Unauthorized, invalid or expired token
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
example:
error:
code: 401
message: Invalid or expired token
type: authentication_error
'402':
description: Insufficient quota, recharge required
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
example:
error:
code: 402
message: Insufficient quota
type: insufficient_quota_error
fallback_suggestion: https://evolink.ai/dashboard/billing
'403':
description: Access denied
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
example:
error:
code: 403
message: Access denied for this model
type: permission_error
param: model
'404':
description: Resource not found
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
example:
error:
code: 404
message: Specified model not found
type: not_found_error
param: model
fallback_suggestion: kimi-k2-thinking
'413':
description: Request payload too large
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
example:
error:
code: 413
message: Image file too large
type: request_too_large_error
param: content
fallback_suggestion: compress image to under 10MB
'429':
description: Rate limit exceeded
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
example:
error:
code: 429
message: Rate limit exceeded
type: rate_limit_error
fallback_suggestion: retry after 60 seconds
'500':
description: Internal server error
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
example:
error:
code: 500
message: Internal server error
type: internal_server_error
fallback_suggestion: try again later
'502':
description: Upstream service error
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
example:
error:
code: 502
message: Upstream AI service unavailable
type: upstream_error
fallback_suggestion: try different model
'503':
description: Service temporarily unavailable
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
example:
error:
code: 503
message: Service temporarily unavailable
type: service_unavailable_error
fallback_suggestion: retry after 30 seconds
components:
schemas:
ChatCompletionRequest:
type: object
required:
- model
- messages
properties:
model:
type: string
description: Model name for chat completion
enum:
- kimi-k2-thinking
- kimi-k2-thinking-turbo
example: kimi-k2-thinking
messages:
type: array
description: >-
List of messages for the conversation, supports multi-turn dialogue
and multimodal input
items:
$ref: '#/components/schemas/Message'
minItems: 1
stream:
type: boolean
description: >-
Whether to stream the response
- `true`: Stream response, returns content chunk by chunk in
real-time
- `false`: Wait for complete response and return all at once
default: false
example: false
max_tokens:
type: integer
description: >-
Maximum number of tokens to generate in the response
**Note**:
- Too small value may cause truncated response
- If max tokens is reached, finish_reason will be "length",
otherwise "stop"
minimum: 1
example: 2000
temperature:
type: number
description: |-
Sampling temperature, controls randomness of output
**Note**:
- Lower values (e.g., 0.2): More deterministic and focused output
- Higher values (e.g., 1.5): More random and creative output
- **Recommended value for kimi-k2-thinking series: 1.0**
minimum: 0
maximum: 2
default: 1
example: 1
top_p:
type: number
description: >-
Nucleus sampling parameter
**Note**:
- Controls sampling from tokens with cumulative probability
- For example, 0.9 means sampling from tokens with top 90%
cumulative probability
- Default: 1.0 (considers all tokens)
**Suggestion**: Do not adjust both temperature and top_p
simultaneously
minimum: 0
maximum: 1
default: 1
example: 0.9
top_k:
type: integer
description: >-
Top-K sampling parameter
**Note**:
- For example, 10 limits sampling to the top 10 highest probability
tokens
- Smaller values make output more focused
- Default: no limit
minimum: 1
example: 40
'n':
type: integer
description: |-
Number of completions to generate for each input message
**Note**:
- Default: 1, maximum: 5
- When temperature is very close to 0, only 1 result can be returned
minimum: 1
maximum: 5
default: 1
example: 1
presence_penalty:
type: number
description: >-
Presence penalty, number between -2.0 and 2.0
**Note**:
- Positive values penalize new tokens based on whether they appear
in the text, increasing likelihood of discussing new topics
minimum: -2
maximum: 2
default: 0
example: 0
frequency_penalty:
type: number
description: >-
Frequency penalty, number between -2.0 and 2.0
**Note**:
- Positive values penalize new tokens based on their frequency in
the text, decreasing likelihood of repeating same phrases verbatim
minimum: -2
maximum: 2
default: 0
example: 0
response_format:
type: object
description: >-
Response format settings
**Note**:
- Set to {"type": "json_object"} to enable JSON mode, ensuring model
generates valid JSON
- When using response_format with {"type": "json_object"},
explicitly guide the model to output JSON format in your prompt
- Default: {"type": "text"}
- **Warning**: Do not mix partial mode with
response_format=json_object
properties:
type:
type: string
enum:
- text
- json_object
description: Response format type
default: text
stop:
oneOf:
- type: string
description: Single stop word
- type: array
description: List of stop words, maximum 5
items:
type: string
maxItems: 5
description: |-
Stop sequences, generation stops when these sequences are matched
**Note**:
- The stop sequences themselves will not be included in the output
- Maximum 5 strings, each no longer than 32 bytes
tools:
type: array
description: >-
List of tools for Tool Use or Function Calling
**Note**:
- Each tool must include a type
- The function structure must include name, description, and
parameters
- Maximum 128 functions in tools array
items:
$ref: '#/components/schemas/Tool'
maxItems: 128
ChatCompletionResponse:
type: object
properties:
id:
type: string
description: Unique identifier for the chat completion
example: cmpl-04ea926191a14749b7f2c7a48a68abc6
model:
type: string
description: The model used for completion
example: kimi-k2-thinking
object:
type: string
enum:
- chat.completion
description: Response type
example: chat.completion
created:
type: integer
description: Unix timestamp when the completion was created
example: 1698999496
choices:
type: array
description: List of completion choices
items:
$ref: '#/components/schemas/Choice'
usage:
$ref: '#/components/schemas/Usage'
ErrorResponse:
type: object
properties:
error:
type: object
properties:
code:
type: integer
description: HTTP status error code
message:
type: string
description: Error message
type:
type: string
description: Error type
param:
type: string
description: Related parameter name
fallback_suggestion:
type: string
description: Suggestion for handling the error
Message:
type: object
required:
- role
- content
properties:
role:
type: string
description: |-
Message role
- `user`: User message
- `assistant`: AI assistant message (for multi-turn conversation)
- `system`: System prompt (defines AI's role and behavior)
enum:
- user
- assistant
- system
example: user
content:
oneOf:
- type: string
description: Plain text message content
example: Please introduce yourself
- type: array
description: Multimodal message content, supports text and image mixed input
items:
$ref: '#/components/schemas/ContentPart'
description: >-
Message content. Supports two formats:
**1. Plain text string**: Can directly pass a string, e.g.,
`"content":"Please introduce yourself"`
**2. Object array** (supports multimodal input): See ContentPart
definition below
name:
type: string
description: >-
Message name
**Note**:
- Used for role-playing scenarios, the name field can be viewed as
part of the output prefix
example: Kal'tsit
partial:
type: boolean
description: >-
Whether to enable Partial Mode
**Note**:
- Only set in the last message with role=assistant
- Set to true to enable partial mode (prefill mode)
- **Warning**: Do not mix partial mode with
response_format=json_object
default: false
Tool:
type: object
required:
- type
- function
properties:
type:
type: string
enum:
- function
description: Tool type
function:
type: object
required:
- name
- description
- parameters
properties:
name:
type: string
description: |-
Function name
**Note**:
- Must follow regex pattern: ^[a-zA-Z_][a-zA-Z0-9-_]{0,63}$
- Using clear English names will be better accepted by the model
pattern: ^[a-zA-Z_][a-zA-Z0-9-_]{0,63}$
example: CodeRunner
description:
type: string
description: >-
Function description, explains what the function does to help
the model judge and select
example: Code executor that supports running python and javascript code
parameters:
type: object
description: |-
Function parameter definition
**Note**:
- The root of parameters must be an object
- Content is a subset of JSON Schema
Choice:
type: object
properties:
index:
type: integer
description: Index of this choice
example: 0
message:
$ref: '#/components/schemas/AssistantMessage'
finish_reason:
type: string
description: |-
Reason why the completion finished
- `stop`: Natural completion
- `length`: Reached maximum token limit
- `content_filter`: Content was filtered
enum:
- stop
- length
- content_filter
example: stop
Usage:
type: object
description: Token usage statistics
properties:
prompt_tokens:
type: integer
description: Number of tokens in the input
example: 8
completion_tokens:
type: integer
description: Number of tokens in the output
example: 292
total_tokens:
type: integer
description: Total number of tokens used
example: 300
prompt_tokens_details:
type: object
description: Detailed breakdown of input tokens
properties:
cached_tokens:
type: integer
description: Number of cached tokens
example: 8
ContentPart:
oneOf:
- $ref: '#/components/schemas/TextContent'
- $ref: '#/components/schemas/ImageContent'
AssistantMessage:
type: object
properties:
role:
type: string
description: Role of the message sender
enum:
- assistant
example: assistant
content:
type: string
description: AI's response content
example: Hi there! How can I help you?
reasoning_content:
type: string
description: >-
Reasoning process content (only returned by kimi-k2-thinking series
models)
**Note**:
- Signature feature of Kimi K2 thinking series models
- Shows the model's thinking and reasoning process
- Helps understand how the model arrives at its final answer
example: >-
The user just said "hi". This is a very simple greeting. I should be
friendly, helpful, and professional in my response...
TextContent:
title: Text content
type: object
required:
- type
- text
properties:
type:
type: string
enum:
- text
description: Content type
text:
type: string
description: Text content
example: Please describe this image in detail
ImageContent:
title: Image content
type: object
required:
- type
- image_url
properties:
type:
type: string
enum:
- image_url
description: Content type
image_url:
type: object
required:
- url
properties:
url:
type: string
format: uri
description: >-
Image URL or Base64 encoding
**Format**:
- URL format: `https://example.com/image.png`
- Base64 format: `data:image/;base64,`
(format must be lowercase, e.g., png, jpg, jpeg, webp)
**Limits**:
- Maximum image size: `10MB`
- Supported formats: `.jpeg`, `.jpg`, `.png`, `.webp`
example: data:image/png;base64,iVBORw0KGgo...
securitySchemes:
bearerAuth:
type: http
scheme: bearer
description: >-
##All APIs require Bearer Token authentication##
**Get API Key:**
Visit [API Key Management Page](https://evolink.ai/dashboard/keys) to
get your API Key
**Add to request header:**
```
Authorization: Bearer YOUR_API_KEY
```
````