Kimi K3 - Anthropic-Compatible API

curl --request POST \
  --url https://direct.evolink.ai/v1/messages \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "kimi-k3",
  "max_tokens": 1024,
  "messages": [
    {
      "role": "user",
      "content": "Introduce Kimi K3 in three sentences."
    }
  ]
}
'

{
  "id": "<string>",
  "type": "message",
  "role": "assistant",
  "model": "kimi-k3",
  "content": [
    {
      "type": "text",
      "text": "<string>"
    }
  ],
  "stop_sequence": "<string>",
  "usage": {
    "input_tokens": 123,
    "cache_creation_input_tokens": 123,
    "cache_read_input_tokens": 123,
    "output_tokens": 123,
    "output_tokens_details": {
      "thinking_tokens": 123
    }
  }
}

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

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

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

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

POST

messages

curl --request POST \
  --url https://direct.evolink.ai/v1/messages \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "kimi-k3",
  "max_tokens": 1024,
  "messages": [
    {
      "role": "user",
      "content": "Introduce Kimi K3 in three sentences."
    }
  ]
}
'

{
  "id": "<string>",
  "type": "message",
  "role": "assistant",
  "model": "kimi-k3",
  "content": [
    {
      "type": "text",
      "text": "<string>"
    }
  ],
  "stop_sequence": "<string>",
  "usage": {
    "input_tokens": 123,
    "cache_creation_input_tokens": 123,
    "cache_read_input_tokens": 123,
    "output_tokens": 123,
    "output_tokens_details": {
      "thinking_tokens": 123
    }
  }
}

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

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

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

{
  "type": "error",
  "error": {
    "type": "<string>",
    "message": "<string>"
  },
  "request_id": "<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.

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>

required

Model ID.

Available options:

kimi-k3

max_tokens

integer

required

Maximum number of tokens allowed for this generation, including thinking and final text.

Required range: x >= 1

messages

object[]

required

Anthropic Messages message list. For multi-turn conversations, return complete assistant content blocks unchanged.

Minimum array length: 1

Show child attributes

system

string

System prompt. The Messages protocol uses a top-level system field instead of a system role.

stream

boolean

default:false

Whether to return an Anthropic SSE event stream.

tools

object[]

Tools that the model may call.

Show child attributes

tool_choice

object

Show child attributes

Response

Message response; streaming requests return an Anthropic SSE event stream

string

type

enum<string>

Available options:

message

role

enum<string>

Available options:

assistant

model

string

Example:

"kimi-k3"

content

object[]

Anthropic content block for text, reasoning, tool use, or a tool result.

Option 1
Option 2
Option 3
Option 4

Show child attributes

stop_reason

enum<string>

Available options:

end_turn,

max_tokens,

tool_use

stop_sequence

string | null

usage

object

Show child attributes

Kimi K3 - OpenAI-Compatible API Claude - Messages API

Image Series

Video Series

Audio Series

Text Series

Account Management

Task Management

File Management

Kimi K3 - Anthropic-Compatible API

Authorizations

Body

Response