curl --request POST \
  --url https://direct.evolink.ai/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "kimi-k3.1-pro",
  "messages": [
    {
      "role": "user",
      "content": "Explain context caching in one sentence."
    }
  ]
}
'

{
  "id": "chatcmpl-6adc72a2823cc13b156bf863",
  "object": "chat.completion",
  "created": 1792832163,
  "model": "kimi-k3.1-pro",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Context caching stores repeated prefix content from requests so that later cache hits can be processed faster and at lower cost.",
        "reasoning_content": "The user wants a one-sentence explanation of context caching, including what it stores and its benefits."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 24,
    "completion_tokens": 96,
    "total_tokens": 120,
    "prompt_tokens_details": {
      "cached_tokens": 0
    },
    "completion_tokens_details": {
      "reasoning_tokens": 62
    }
  }
}

{
  "error": {
    "message": "<string>",
    "type": "<string>",
    "code": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "<string>",
    "code": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "<string>",
    "code": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "<string>",
    "code": "<string>"
  }
}

Chat Completions API

Kimi API (All Models) - Chat Completions Quickstart

Call Kimi models through the OpenAI Chat Completions protocol and select a model with model
Only model and messages are required
All three models have a context window of 1,048,576 tokens and a default maximum output of 131,072 tokens
Reasoning is always enabled for all three models and returned in reasoning_content; reasoning tokens count toward output
For tool calling, web search, structured output, image input, or cache settings, see the full reference

POST

chat

completions

curl --request POST \
  --url https://direct.evolink.ai/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "kimi-k3.1-pro",
  "messages": [
    {
      "role": "user",
      "content": "Explain context caching in one sentence."
    }
  ]
}
'

{
  "id": "chatcmpl-6adc72a2823cc13b156bf863",
  "object": "chat.completion",
  "created": 1792832163,
  "model": "kimi-k3.1-pro",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Context caching stores repeated prefix content from requests so that later cache hits can be processed faster and at lower cost.",
        "reasoning_content": "The user wants a one-sentence explanation of context caching, including what it stores and its benefits."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 24,
    "completion_tokens": 96,
    "total_tokens": 120,
    "prompt_tokens_details": {
      "cached_tokens": 0
    },
    "completion_tokens_details": {
      "reasoning_tokens": 62
    }
  }
}

{
  "error": {
    "message": "<string>",
    "type": "<string>",
    "code": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "<string>",
    "code": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "<string>",
    "code": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "<string>",
    "code": "<string>"
  }
}

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.

Reasoning is always enabled for Kimi models and returned in reasoning_content. Reasoning tokens count toward output. Avoid setting max_completion_tokens too low: reasoning may exhaust the output budget before any answer text is produced.

Authorizations

Authorization

string

header

required

##All APIs require Bearer Token authentication##

Get API Key:

Visit API Key Management Page to get your API Key

Add to request header:

Authorization: Bearer YOUR_API_KEY

Body

application/json

model

enum<string>

default:kimi-k3.1-pro

required

Model to call:

Model ID	Positioning
`kimi-k3.1-pro`	Latest-generation model (recommended)
`kimi-k3.1-pro-highspeed`	Same parameters as Pro, faster generation
`kimi-k3`	Previous-generation model

All three models have a context window of 1,048,576 tokens and always have reasoning enabled.

Available options:

kimi-k3.1-pro,

kimi-k3.1-pro-highspeed,

kimi-k3

messages

object[]

required

Conversation messages. Include historical messages in order for multi-turn conversations; see the full reference for how to return reasoning and tool-call history.

Minimum array length: 1

Show child attributes

reasoning_effort

enum<string>

default:max

Reasoning effort, default max. kimi-k3 supports only max; see the full reference for other compatible values.

Available options:

low,

high,

max

max_completion_tokens

integer

default:131072

Maximum generated tokens, including reasoning and the final answer; default 131072, maximum 1048576.

Required range: 1 <= x <= 1048576

stream

boolean

default:false

Whether to return the response as an SSE stream.

Response

Conversation generated successfully; streaming requests return an SSE event stream

string

Response ID.

Example:

"chatcmpl-6adc72a2823cc13b156bf863"

object

enum<string>

Available options:

chat.completion

Example:

"chat.completion"

created

integer

Creation time as a Unix timestamp in seconds.

Example:

1792832163

model

string

Model used for this call.

Example:

"kimi-k3.1-pro"

choices

object[]

Show child attributes

usage

object

Show child attributes

Image Series

Video Series

Audio Series

Text Series

Account Management

Task Management

File Management

Kimi API (All Models) - Chat Completions Quickstart

Authorizations

Body

Response