kimi-k3

curl --request POST \
  --url https://www.anyfast.ai/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "kimi-k3",
  "messages": [
    {
      "role": "user",
      "content": "Explain Kimi K3 in one sentence."
    }
  ],
  "reasoning_effort": "max"
}
'

{
  "id": "cmpl-kimi-k3-example",
  "object": "chat.completion",
  "created": 1784736000,
  "model": "moonshotai/kimi-k3",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "reasoning": "The user requested a concise introduction.",
        "reasoning_details": [
          {
            "type": "reasoning.text",
            "text": "The user requested a concise introduction.",
            "format": "unknown",
            "index": 0
          }
        ],
        "content": "Kimi K3 is Moonshot AI's flagship multimodal reasoning model with a 1M-token context window."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 18,
    "completion_tokens": 32,
    "total_tokens": 50,
    "prompt_tokens_details": {
      "cached_tokens": 0
    }
  }
}

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

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

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

POST

chat

completions

curl --request POST \
  --url https://www.anyfast.ai/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "kimi-k3",
  "messages": [
    {
      "role": "user",
      "content": "Explain Kimi K3 in one sentence."
    }
  ],
  "reasoning_effort": "max"
}
'

{
  "id": "cmpl-kimi-k3-example",
  "object": "chat.completion",
  "created": 1784736000,
  "model": "moonshotai/kimi-k3",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "reasoning": "The user requested a concise introduction.",
        "reasoning_details": [
          {
            "type": "reasoning.text",
            "text": "The user requested a concise introduction.",
            "format": "unknown",
            "index": 0
          }
        ],
        "content": "Kimi K3 is Moonshot AI's flagship multimodal reasoning model with a 1M-token context window."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 18,
    "completion_tokens": 32,
    "total_tokens": 50,
    "prompt_tokens_details": {
      "cached_tokens": 0
    }
  }
}

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

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

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

Kimi K3 supports a 1M-token context window, text/image input, always-on reasoning with configurable effort, streaming, structured output, Partial Mode, and function tools.

Use top-level reasoning_effort; the K2.x thinking object has no effect. Sampling values are fixed, so omit temperature, top_p, n, presence_penalty, and frequency_penalty.

Authorizations

Authorization

string

header

required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json

model

enum<string>

default:kimi-k3

required

Model ID. Must be kimi-k3.

Available options:

kimi-k3

messages

object[]

required

Conversation history. Return complete assistant messages, including reasoning, reasoning_details, and tool_calls, in later turns.

Minimum array length: 1

Show child attributes

reasoning_effort

enum<string>

default:max

Controls reasoning effort. K3 always reasons with Preserved Thinking enabled; reasoning cannot be disabled.

Available options:

low,

high,

max

max_completion_tokens

integer

default:131072

Maximum output tokens. Input plus output must fit the 1M-token context window. max_tokens is deprecated.

Required range: 1 <= x <= 1048576

response_format

object

Show child attributes

stop

Up to 5 stop strings; each string must not exceed 32 bytes. A stop string can terminate reasoning before final content is produced.

stream

boolean

default:false

Stream partial deltas using Server-Sent Events.

stream_options

object

Options for streaming responses.

Show child attributes

tools

object[]

Function tools available to the model.

Show child attributes

tool_choice

enum<string>

default:auto

Let the model decide, disable tool calls, or require at least one tool call.

Available options:

auto,

none,

required

prompt_cache_key

string

Stable session or task ID used to improve prefix-cache hit rates.

safety_identifier

string

Stable identifier for the end user. Use a hash instead of directly identifying information.

Response

Completion generated successfully. When stream is true, the endpoint returns chat.completion.chunk objects using SSE and ends with data: [DONE].

string

required

object

enum<string>

required

Available options:

chat.completion

created

integer

required

Unix timestamp.

model

string

required

The response may use the upstream canonical model ID.

Example:

"moonshotai/kimi-k3"

choices

object[]

required

Show child attributes

provider

string

Example:

"Moonshot AI"

system_fingerprint

string | null

service_tier

string | null

usage

object

Show child attributes

Overview

Native Compatible Endpoints

Model APIs

Authorizations

Body

Response