创建聊天补全（流式）

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

向聊天模型发送一组消息，并以流式方式接收模型生成的回复。启用流式输出时，接口会逐步返回增量内容，适合需要边生成边展示的对话场景。

要使用流式响应，请在请求体中设置 stream: true。

请求头

名称	必填	说明
Content-Type	是	请求体格式，通常为 application/json
Accept	是	建议设置为 text/event-stream 以接收流式数据
Authorization	否	API Key 鉴权信息，格式为 Bearer sk-***
X-Forwarded-Host	否	可选的转发主机信息

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 Vortap。"
      }
    ],
    "stream": true
  }'

流式响应示例

启用 stream: true 后，服务会以 Server-Sent Events（SSE）的形式连续返回数据片段：

data: {
  "id": "chatcmpl-123",
  "object": "chat.completion.chunk",
  "created": 1677652288,
  "model": "gpt-4o-mini",
  "choices": [
    {
      "index": 0,
      "delta": {
        "role": "assistant"
      },
      "finish_reason": null
    }
  ]
}

data: {
  "id": "chatcmpl-123",
  "object": "chat.completion.chunk",
  "created": 1677652288,
  "model": "gpt-4o-mini",
  "choices": [
    {
      "index": 0,
      "delta": {
        "content": "你好"
      },
      "finish_reason": null
    }
  ]
}

data: {
  "id": "chatcmpl-123",
  "object": "chat.completion.chunk",
  "created": 1677652288,
  "model": "gpt-4o-mini",
  "choices": [
    {
      "index": 0,
      "delta": {
        "content": "，有什么可以帮你？"
      },
      "finish_reason": null
    }
  ]
}

data: [DONE]

非流式响应示例

如果未设置 stream: true，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
  }
}