Chat Completions

创建对话补全请求，支持流式响应和函数调用

请求参数

参数	类型	必填	说明
model	string	是	模型 ID，如 openai/gpt-4o
messages	array	是	消息数组
temperature	number	否	采样温度，范围 0-2默认: 0.7
max_tokens	integer	否	最大响应 token 数
stream	boolean	否	是否使用流式响应默认: false
tools	array	否	函数工具定义数组
tool_choice	string/object	否	工具选择策略可选值: auto, none, required
response_format	object	否	输出格式规范

Message 格式说明

messages 数组中的每个消息对象包含以下字段：

system系统提示，用于设置助手行为

user用户消息

assistant助手消息

content 字段支持两种格式：

字符串：纯文本消息
内容数组：支持文本和图片混合（多模态模型）

请求示例

cURL

curl https://api.mintcloud.ai/v1/chat/completions \
  -H "Authorization: Bearer $MINTCLOUD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-4o",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from openai import OpenAI

client = OpenAI(
    base_url="https://api.mintcloud.ai/v1",
    api_key="<your API key>"
)

response = client.chat.completions.create(
    model="openai/gpt-4o",
    messages=[{"role": "user", "content": "Hello!"}]
)

print(response.choices[0].message.content)

响应格式

标准 OpenAI Chat Completions 响应格式：

{
  "id": "chatcmpl-xxxxxxxxxxxx",
  "object": "chat.completion",
  "created": 1677652288,
  "model": "openai/gpt-4o",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 10,
    "completion_tokens": 12,
    "total_tokens": 22
  }
}

流式响应

设置 stream: true 启用 SSE 流式响应，每个 Chunk 格式如下：

data: {"id":"chatcmpl-xxx","object":"chat.completion.chunk","created":1234567890,"model":"openai/gpt-4o","choices":[{"index":0,"delta":{"content":"Hello"},"finish_reason":null}]}

data: {"id":"chatcmpl-xxx","object":"chat.completion.chunk","created":1234567890,"model":"openai/gpt-4o","choices":[{"index":0,"delta":{"content":"!"},"finish_reason":null}]}

data: {"id":"chatcmpl-xxx","object":"chat.completion.chunk","created":1234567890,"model":"openai/gpt-4o","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}

data: [DONE]

流式响应特点

每个数据块以 data: 开头
最后一块为 data: [DONE]
delta.content 包含增量文本
finish_reason 出现时表示流结束