Skip to main content
POST
/
v1
/
chat
/
completions
对话补全
curl --request POST \
  --url https://api.seeoneapi.com/v1/chat/completions

Documentation Index

Fetch the complete documentation index at: https://docs.seeoneapi.com/llms.txt

Use this file to discover all available pages before exploring further.

​
请求参数

参数类型必填说明
modelstring是模型 ID，如 claude-sonnet-4-20250514
messagesarray是消息数组
max_tokensinteger否最大输出 Token 数
temperaturenumber否采样温度，0-2，默认 1
top_pnumber否核采样参数，0-1
streamboolean否是否流式输出，默认 false
stopstring/array否停止生成的标记

​
消息格式

{
  "messages": [
    {"role": "system", "content": "你是一个有帮助的助手"},
    {"role": "user", "content": "你好"},
    {"role": "assistant", "content": "你好！有什么可以帮助你的？"},
    {"role": "user", "content": "帮我写一段代码"}
  ]
}
支持的角色：system、user、assistant。

​
请求示例

curl https://api.seeoneapi.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-你的API密钥" \
  -d '{
    "model": "claude-sonnet-4-20250514",
    "messages": [
      {"role": "user", "content": "用一句话解释递归"}
    ],
    "max_tokens": 256
  }'

​
响应示例

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1716000000,
  "model": "claude-sonnet-4-20250514",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "递归就是函数调用自身来解决问题的方法——要理解递归，请先理解递归。"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 35,
    "total_tokens": 47
  }
}

​
流式输出

设置 stream: true 后，响应通过 Server-Sent Events (SSE) 返回： 
data: {"id":"chatcmpl-abc123","choices":[{"delta":{"content":"递归"},"index":0}]}

data: {"id":"chatcmpl-abc123","choices":[{"delta":{"content":"就是"},"index":0}]}

data: [DONE]