通用对话接口

curl -X POST https://api.qingbo.ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.6-luna",
    "messages": [
      {
        "role": "system",
        "content": "你是一个专业的AI助手。"
      },
      {
        "role": "user",
        "content": "解释一下冒泡排序算法。"
      }
    ],
    "temperature": 0.7,
    "max_tokens": 1024
  }'

from openai import OpenAI

client = OpenAI(
    base_url="https://api.qingbo.ai/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="gpt-5.6-luna",
    messages=[
        {"role": "system", "content": "你是一个专业的AI助手。"},
        {"role": "user", "content": "解释一下冒泡排序算法。"}
    ],
    temperature=0.7,
    max_tokens=1024
)

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

import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://api.qingbo.ai/v1',
  apiKey: 'YOUR_API_KEY'
});

const response = await client.chat.completions.create({
  model: 'gpt-5.6-luna',
  messages: [
    { role: 'system', content: '你是一个专业的AI助手。' },
    { role: 'user', content: '解释一下冒泡排序算法。' }
  ],
  temperature: 0.7,
  max_tokens: 1024
});

console.log(response.choices[0].message.content);

package main

import (
    "bytes"
    "encoding/json"
    "fmt"
    "io"
    "net/http"
)

func main() {
    payload := map[string]interface{}{
        "model": "gpt-5.6-luna",
        "messages": []map[string]string{
            {"role": "system", "content": "你是一个专业的AI助手。"},
            {"role": "user", "content": "解释一下冒泡排序算法。"},
        },
        "temperature": 0.7,
        "max_tokens": 1024,
    }

    body, _ := json.Marshal(payload)
    req, _ := http.NewRequest("POST", "https://api.qingbo.ai/v1/chat/completions", bytes.NewBuffer(body))
    req.Header.Set("Authorization", "Bearer YOUR_API_KEY")
    req.Header.Set("Content-Type", "application/json")

    resp, err := http.DefaultClient.Do(req)
    if err != nil {
        panic(err)
    }
    defer resp.Body.Close()

    result, _ := io.ReadAll(resp.Body)
    fmt.Println(string(result))
}

import java.net.http.*;
import java.net.URI;

public class Main {
    public static void main(String[] args) throws Exception {
        String payload = """
        {
          "model": "gpt-5.6-luna",
          "messages": [
            {"role": "system", "content": "你是一个专业的AI助手。"},
            {"role": "user", "content": "解释一下冒泡排序算法。"}
          ],
          "temperature": 0.7,
          "max_tokens": 1024
        }
        """;

        HttpClient client = HttpClient.newHttpClient();
        HttpRequest request = HttpRequest.newBuilder()
            .uri(URI.create("https://api.qingbo.ai/v1/chat/completions"))
            .header("Authorization", "Bearer YOUR_API_KEY")
            .header("Content-Type", "application/json")
            .POST(HttpRequest.BodyPublishers.ofString(payload))
            .build();

        HttpResponse<String> response = client.send(request,
            HttpResponse.BodyHandlers.ofString());
        System.out.println(response.body());
    }
}

{
  "id": "chatcmpl-CdA8u0qPqzeN2gu8QLuQfjaP9CHU4",
  "object": "chat.completion",
  "created": 1763449816,
  "model": "gpt-5.6-luna",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "冒泡排序（Bubble Sort）是一种简单的比较交换排序。它通过重复遍历序列，比较相邻元素并把较大的“冒泡”到右侧末端，直到序列有序。\n\n核心思想\n- 每一趟从左到右比较相邻元素，若前者大于后者则交换。一次趟结束后，当前未排部分中最大的元素被放到末尾。\n- 重复多趟，直到没有发生交换或已完成 n−1 趟。\n\n流程示例（以 [5, 1, 4, 2] 为例）\n- 第1趟：比较并交换 → [1, 5, 4, 2] → [1, 4, 5, 2] → [1, 4, 2, 5]（最大元素5到末尾）\n- 第2趟：比较并交换 → [1, 4, 2, 5] → [1, 2, 4, 5]（已整体有序，可提前结束）\n\n性质\n- 时间复杂度：平均/最坏 O(n^2)，最好 O(n)（当已基本有序且使用提前退出优化）\n- 空间复杂度：O(1)（就地排序）\n- 稳定性：稳定（相等元素相对次序不变）\n- 适用场景：数据量小或序列几乎有序；不适合大规模无序数据\n\n常见优化\n- 提前退出：某趟未发生交换则已排序完成。\n- 缩短边界：记录本趟最后一次交换的位置，下一趟只需遍历到该位置。\n- 双向冒泡（鸡尾酒排序）：从左到右、再从右到左各走一遍，更快收敛。\n\n简要伪代码\nfunction bubbleSort(a):\n    n = length(a)\n    repeat\n        swapped = false\n        for j = 0 to n-2:\n            if a[j] > a[j+1]:\n                swap(a[j], a[j+1])\n                swapped = true\n        n = n - 1    // 末尾已就位，缩短范围\n    until swapped == false\n\n如需，我可以给出某种语言的实现代码或更多变体说明。",
        "refusal": null,
        "annotations": []
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 24,
    "completion_tokens": 1030,
    "total_tokens": 1054,
    "prompt_tokens_details": {
      "cached_tokens": 0,
      "audio_tokens": 0
    },
    "completion_tokens_details": {
      "reasoning_tokens": 512,
      "audio_tokens": 0,
      "accepted_prediction_tokens": 0,
      "rejected_prediction_tokens": 0
    }
  }
}

{
  "error": {
    "code": 400,
    "message": "请求参数无效",
    "type": "invalid_request_error"
  }
}

{
  "error": {
    "code": 401,
    "message": "身份验证失败，请检查您的API密钥",
    "type": "authentication_error"
  }
}

{
  "error": {
    "code": 402,
    "message": "账户余额不足，请充值后再试",
    "type": "payment_required"
  }
}

{
  "error": {
    "code": 403,
    "message": "访问被禁止，您没有权限访问此资源",
    "type": "permission_error"
  }
}

{
  "error": {
    "code": 429,
    "message": "请求过于频繁，请稍后再试",
    "type": "rate_limit_error"
  }
}

{
  "error": {
    "code": 500,
    "message": "服务器内部错误，请稍后重试",
    "type": "server_error"
  }
}

{
  "error": {
    "code": 502,
    "message": "网关错误，服务器暂时不可用",
    "type": "bad_gateway"
  }
}