创建聊天补全（流式）

POST https://www.vortapapi.com/v1/chat/completions

使用聊天消息作为输入，让模型生成回复。启用流式输出时，Vortap 会通过 Server-Sent Events（SSE）逐步返回生成内容，适合需要边生成边展示的场景。

请求头

名称	必填	说明
Content-Type	是	请求体格式，通常为 application/json
Accept	是	流式请求建议使用 text/event-stream
Authorization	否	API Key 鉴权，例如：Bearer sk-***

请求示例

curl https://www.vortapapi.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Accept: text/event-stream" \
  -H "Authorization: Bearer sk-***" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [
      {
        "role": "user",
        "content": "你好，请介绍一下你自己。"
      }
    ],
    "stream": true
  }'

请求体参数

参数	类型	必填	说明
model	string	是	要调用的模型名称
messages	array	是	对话消息列表
stream	boolean	是	设置为 true 时启用流式响应

messages 字段

每条消息通常包含以下字段：

字段	类型	必填	说明
role	string	是	消息角色，例如 system、user、assistant
content	string	是	消息内容

流式响应说明

当 stream 为 true 时，接口会持续返回多个事件片段。每个片段通常包含当前增量内容，客户端需要按顺序读取并拼接这些内容，直到收到结束标记。

流式响应示例：

data: {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1677652288,"choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}

data: {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1677652288,"choices":[{"index":0,"delta":{"content":"你好"},"finish_reason":null}]}

data: {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1677652288,"choices":[{"index":0,"delta":{"content":"，有什么可以帮你？"},"finish_reason":null}]}

data: {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1677652288,"choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}

data: [DONE]

非流式响应示例

如果未启用流式输出，接口会在生成完成后一次性返回完整结果：

{
  "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
  }
}