kimi-k3.1-pro / kimi-k3.1-pro-highspeed

curl --request POST \
  --url https://www.anyfast.ai/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "kimi-k3.1-pro",
  "reasoning_effort": "high",
  "messages": [
    {
      "role": "user",
      "content": "请说明如何安全审查一个大型代码库。"
    }
  ]
}
'

{
  "id": "<string>",
  "object": "chat.completion",
  "model": "<string>",
  "choices": [
    {
      "index": 123,
      "message": {
        "role": "system",
        "content": "<string>",
        "name": "<string>",
        "partial": true,
        "reasoning_content": "<string>",
        "tool_calls": [
          {
            "id": "<string>",
            "type": "function",
            "function": {
              "name": "<string>",
              "arguments": "<string>"
            }
          }
        ],
        "tool_call_id": "<string>"
      },
      "finish_reason": "<string>"
    }
  ],
  "created": 123,
  "usage": {}
}

{
  "error": {}
}

{
  "error": {}
}

{
  "error": {}
}

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-k3.1-pro",
  "reasoning_effort": "high",
  "messages": [
    {
      "role": "user",
      "content": "请说明如何安全审查一个大型代码库。"
    }
  ]
}
'

{
  "id": "<string>",
  "object": "chat.completion",
  "model": "<string>",
  "choices": [
    {
      "index": 123,
      "message": {
        "role": "system",
        "content": "<string>",
        "name": "<string>",
        "partial": true,
        "reasoning_content": "<string>",
        "tool_calls": [
          {
            "id": "<string>",
            "type": "function",
            "function": {
              "name": "<string>",
              "arguments": "<string>"
            }
          }
        ],
        "tool_call_id": "<string>"
      },
      "finish_reason": "<string>"
    }
  ],
  "created": 123,
  "usage": {}
}

{
  "error": {}
}

{
  "error": {}
}

{
  "error": {}
}

Kimi K3.1 Pro 和 Kimi K3.1 Pro Highspeed 使用相同的 OpenAI 兼容 Chat Completions 请求。两个模型均提供 1,048,576 token 上下文、始终开启的推理、多模态输入、流式输出、结构化输出、Partial Mode 和函数工具。

在顶层设置 reasoning_effort，可选 low、high 或 max。K3.1 系列不使用 K2.x 的 thinking 对象。采样参数为固定值，请省略 temperature、top_p、n、presence_penalty 和 frequency_penalty。

授权

Authorization

string

header

必填

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

请求体

application/json

model

enum<string>

必填

可用选项:

kimi-k3.1-pro,

kimi-k3.1-pro-highspeed

messages

object[]

必填

Minimum array length: 1

Show child attributes

reasoning_effort

enum<string>

默认值:max

可用选项:

low,

high,

max

max_completion_tokens

integer

默认值:131072

必填范围: 1 <= x <= 1048576

stream

boolean

默认值:false

stream_options

object

Show child attributes

response_format

object

Show child attributes

stop

tools

object[]

Show child attributes

tool_choice

enum<string>

默认值:auto

可用选项:

auto,

none,

required

prompt_cache_key

string

safety_identifier

string

响应

对话补全成功。

string

必填

object

enum<string>

必填

可用选项:

chat.completion

model

string

必填

choices

object[]

必填

Show child attributes

created

integer

usage

object

概览

原生兼容端点

模型 API

kimi-k3.1-pro / kimi-k3.1-pro-highspeed

授权

请求体

响应