对话生成（Chat Completions）

用于多轮对话和文本生成，是推荐使用的主入口。

接口地址

POST /v1/chat/completions

请求参数

参数	类型	必填	说明
model	string	是	模型名称（在控制台查看）
messages	array	是	对话上下文，包含 role 与 content
temperature	number	否	随机性，数值越大越发散
max_tokens	number	否	最大输出长度
stream	boolean	否	是否使用流式输出

请求示例

curl https://api.anideaai.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "MODEL_NAME",
    "messages": [
      {"role": "system", "content": "你是一个客服助手。"},
      {"role": "user", "content": "请介绍一下你们的计费方式。"}
    ],
    "temperature": 0.2,
    "max_tokens": 200
  }'

import requests

api_key = "YOUR_API_KEY"
payload = {
    "model": "MODEL_NAME",
    "messages": [
        {"role": "user", "content": "你好"}
    ],
    "temperature": 0.2,
    "max_tokens": 100
}

resp = requests.post(
    "https://api.anideaai.com/v1/chat/completions",
    headers={"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"},
    json=payload,
)
print(resp.json())

const apiKey = "YOUR_API_KEY";

const payload = {
  model: "MODEL_NAME",
  messages: [{ role: "user", content: "你好" }],
  temperature: 0.2,
  max_tokens: 100,
};

fetch("https://api.anideaai.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify(payload),
})
  .then((res) => res.json())
  .then((data) => console.log(data));

响应示例

{
  "id": "chatcmpl_xxxxx",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "我们按令牌计费，控制台会显示倍率与明细。"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 25,
    "completion_tokens": 30,
    "total_tokens": 55
  }
}

响应中的 usage 可用于统计成本。