聊天补全 API

请求示例

curl https://gpuaihub.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "gpt-5.6-sol",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Hello!"}
    ],
    "temperature": 0.7,
    "max_tokens": 1000
  }'

请求参数

参数	类型	必填	说明
model	string	是	模型 ID，如 gpt-5.6-sol、claude-sonnet-4-6
messages	array	是	消息列表，包含 role 和 content
temperature	number	否	采样温度，0-2，默认 1
max_tokens	number	否	最大生成 token 数
stream	boolean	否	是否流式输出，默认 false
top_p	number	否	核采样参数，默认 1
frequency_penalty	number	否	频率惩罚，-2 到 2，默认 0
presence_penalty	number	否	存在惩罚，-2 到 2，默认 0

响应示例

{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "created": 1677652288,
  "model": "gpt-5.6-sol",
  "choices": [{
    "index": 0,
    "message": {
      "role": "assistant",
      "content": "Hello! How can I help you today?"
    },
    "finish_reason": "stop"
  }],
  "usage": {
    "prompt_tokens": 9,
    "completion_tokens": 12,
    "total_tokens": 21
  }
}