xaio
  1. 聊天(Chat)
xaio
  • 聊天(Chat)
    • Chat Completions 普通响应对象
    • Chat Completions 流式响应对象块
    • Create Chat Completions
      POST
  • 嵌入(Embeddings)
    • 嵌入对象
    • Create Embeddings
      POST
  • 模型(Models)
    • 模型对象
    • Show Available Models
      GET
    • Show Specific Model
      GET
  • 重排序(Rerank)
    • Do Rerank
      POST
    • Do Rerank V1
      POST
    • Do Rerank V2
      POST
  • 数据模型
    • Schemas
      • XAIO通用响应模型
  1. 聊天(Chat)

Create Chat Completions

POST
http://38.179.66.24:8088/v1/chat/completions
该接口用于根据用户提供的对话上下文,调用语言模型生成一个或多个聊天回复。它是实现问答、对话、内容创作等功能的核心端点。支持流式(逐字返回)和非流式(一次性返回)两种模式。

请求参数

Authorization
在 Header 添加参数
Authorization
,其值为在 Bearer 之后拼接 Token
示例:
Authorization: Bearer ********************
Header 参数

Body 参数application/json

示例
{
    "model": "Qwen3-30B-A3B-Instruct-2507",
    "messages": [
      {
        "role": "system",
        "content": "You are a helpful assistant."
      },
      {
        "role": "user",
        "content": "Hello!"
      }
    ],
    "top_k": 0,
    "min_p": 0,
    "stream":true
  }

请求示例代码

Shell
JavaScript
Java
Swift
Go
PHP
Python
HTTP
C
C#
Objective-C
Ruby
OCaml
Dart
R
请求示例请求示例
Shell
JavaScript
Java
Swift
curl --location --request POST 'http://38.179.66.24:8088/v1/chat/completions' \
--header 'Accept: application/json' \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "Qwen3-30B-A3B-Instruct-2507",
    "messages": [
      {
        "role": "system",
        "content": "You are a helpful assistant."
      },
      {
        "role": "user",
        "content": "Hello!"
      }
    ],
    "top_k": 0,
    "min_p": 0,
    "stream":true
  }'

返回响应

🟢200OK
application/json
Body

示例
{
    "id": "chatcmpl-123",
    "object": "chat.completion",
    "created": 1677652288,
    "choices": [
        {
            "index": 0,
            "message": {
                "role": "assistant",
                "content": "\n\nHello there, how may I assist you today?"
            },
            "finish_reason": "stop"
        }
    ],
    "usage": {
        "prompt_tokens": 9,
        "completion_tokens": 12,
        "total_tokens": 21
    }
}
🟢200OK
修改于 2025-09-09 03:24:35
上一页
Chat Completions 流式响应对象块
下一页
嵌入对象
Built with