ChatCompletionsフォーマット

会話履歴に基づいてモデル応答を作成します。ストリーミングおよび非ストリーミング応答をサポートしています。

OpenAI Chat Completions APIと互換性があります。

Authorization

BearerAuth

AuthorizationBearer <token>

使用 Bearer Token 认证。格式: Authorization: Bearer sk-xxxxxx

In: header

Request Body

application/json

model*string

模型 ID

messages*array<object>

对话消息列表

Array Item (object)

role*string

消息角色

Value in"system" | "user" | "assistant" | "tool" | "developer"

content*string | array<object>

消息内容

Option #1: string

Option #2: array<object>

Array Item (object)

type?string

Value in"text" | "image_url" | "input_audio" | "file" | "video_url"

text?string

image_url?object

url?string

图片 URL 或 base64

detail?string

Value in"low" | "high" | "auto"

input_audio?object

data?string

Base64 编码的音频数据

format?string

Value in"wav" | "mp3"

file?object

filename?string

file_data?string

file_id?string

video_url?object

url?string

name?string

发送者名称

tool_calls?array<object>

Array Item (object)

id?string

type?string

function?object

name?string

arguments?string

tool_call_id?string

工具调用 ID（用于 tool 角色消息）

reasoning_content?string

推理内容

temperature?number

采样温度

Default1

Range0 <= value <= 2

top_p?number

核采样参数

Default1

Range0 <= value <= 1

n?integer

生成数量

Default1

Range1 <= value

stream?boolean

是否流式响应

Defaultfalse

stream_options?object

include_usage?boolean

stop?string | array<string>

停止序列

Option #1: string

Option #2: array<string>

max_tokens?integer

最大生成 Token 数

max_completion_tokens?integer

最大补全 Token 数

presence_penalty?number

Default0

Range-2 <= value <= 2

frequency_penalty?number

Default0

Range-2 <= value <= 2

logit_bias?object

[key: string]?number

user?string

tools?array<object>

Array Item (object)

type?string

function?object

name?string

description?string

parameters?object

JSON Schema 格式的参数定义

tool_choice?string | object

Option #1: string

Option #2: object

type?string

function?object

name?string

response_format?object

type?string

Value in"text" | "json_object" | "json_schema"

json_schema?object

JSON Schema 定义

seed?integer

reasoning_effort?string

推理强度 (用于支持推理的模型)

Value in"low" | "medium" | "high"

modalities?array<string>

audio?object

voice?string

format?string

Response Body

application/json

curl -X POST "https://loading/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4",
    "messages": [
      {
        "role": "system",
        "content": "string"
      }
    ]
  }'

curl -X POST "https://loading/v1/chat/completions" \  -H "Content-Type: application/json" \  -d '{    "model": "gpt-4",    "messages": [      {        "role": "system",        "content": "string"      }    ]  }'

{
  "id": "string",
  "object": "chat.completion",
  "created": 0,
  "model": "string",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "system",
        "content": "string",
        "name": "string",
        "tool_calls": [
          {
            "id": "string",
            "type": "function",
            "function": {
              "name": "string",
              "arguments": "string"
            }
          }
        ],
        "tool_call_id": "string",
        "reasoning_content": "string"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 0,
    "completion_tokens": 0,
    "total_tokens": 0,
    "prompt_tokens_details": {
      "cached_tokens": 0,
      "text_tokens": 0,
      "audio_tokens": 0,
      "image_tokens": 0
    },
    "completion_tokens_details": {
      "text_tokens": 0,
      "audio_tokens": 0,
      "reasoning_tokens": 0
    }
  },
  "system_fingerprint": "string"
}

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

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

ChatCompletionsフォーマット

Authorization

Request Body

Response Body

200application/json

400application/json

429application/json

application/json

application/json

application/json