GPTech API
Developer Examples · OpenAI Compatible API

GPTech API 示例代码

这里集中展示 GPTech API 的聊天补全（Chat Completions）、音频转写（Audio Transcription）、文本嵌入（Embeddings）、图片生成（Image Generation）、视频生成（Video Generation / Sora）等多模态与扩展 API 示例，覆盖 curl、Python（openai SDK 与 requests）、Node.js（openai SDK）、JavaScript（fetch）、Go（net/http）、Java（OkHttp）、PHP（cURL）等多语言调用方式。所有示例基于 OpenAI 兼容 API 规范，将 Base URL 设为 https://api.tpz.pub/v1 即可直接复制运行。

返回首页 聊天补全示例 多模态与扩展示例
Chat Completions

聊天补全 API 示例

将 Base URL 设置为 https://api.tpz.pub/v1，并使用你的 API Key 即可按 OpenAI 兼容方式调用。

curl
curl -X POST https://api.tpz.pub/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
  "model": "gpt-4o-mini",
  "messages": [
    {"role": "user", "content": "你好"}
  ]
}'
Python（openai）
from openai import OpenAI
client = OpenAI(base_url="https://api.tpz.pub/v1", api_key="YOUR_API_KEY")
resp = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role":"user","content":"你好"}]
)
print(resp.choices[0].message.content)
Node.js（openai）
import OpenAI from "openai";
const client = new OpenAI({
  baseURL: "https://api.tpz.pub/v1",
  apiKey: process.env.OPENAI_API_KEY
});
const resp = await client.chat.completions.create({
  model: "gpt-4o-mini",
  messages: [{ role: "user", content: "你好" }]
});
console.log(resp.choices[0].message.content);
JavaScript（fetch）
const resp = await fetch("https://api.tpz.pub/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer " + YOUR_API_KEY,
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    model: "gpt-4o-mini",
    messages: [{ role: "user", content: "你好" }]
  })
});
const data = await resp.json();
console.log(data.choices[0].message.content);
Python（requests）
import requests
url = "https://api.tpz.pub/v1/chat/completions"
headers = {
  "Authorization": "Bearer YOUR_API_KEY",
  "Content-Type": "application/json"
}
payload = {
  "model": "gpt-4o-mini",
  "messages": [{"role": "user", "content": "你好"}]
}
r = requests.post(url, json=payload, headers=headers)
print(r.json()["choices"][0]["message"]["content"])
Go（net/http）
package main
import (
  "bytes"
  "encoding/json"
  "fmt"
  "net/http"
)
func main() {
  body := map[string]interface{}{
    "model": "gpt-4o-mini",
    "messages": []map[string]string{{"role":"user","content":"你好"}},
  }
  b, _ := json.Marshal(body)
  req, _ := http.NewRequest("POST", "https://api.tpz.pub/v1/chat/completions", bytes.NewBuffer(b))
  req.Header.Set("Authorization", "Bearer YOUR_API_KEY")
  req.Header.Set("Content-Type", "application/json")
  resp, _ := http.DefaultClient.Do(req)
  defer resp.Body.Close()
  var out map[string]interface{}
  json.NewDecoder(resp.Body).Decode(&out)
  fmt.Println(out["choices"].([]interface{})[0].(map[string]interface{})["message"].(map[string]interface{})["content"])
}
Java（OkHttp）
import okhttp3.*;
public class Demo {
  public static void main(String[] args) throws Exception {
    OkHttpClient client = new OkHttpClient();
    String json = "{\"model\":\"gpt-4o-mini\",\"messages\":[{\"role\":\"user\",\"content\":\"你好\"}]}";
    Request req = new Request.Builder()
      .url("https://api.tpz.pub/v1/chat/completions")
      .addHeader("Authorization", "Bearer YOUR_API_KEY")
      .post(RequestBody.create(json, MediaType.parse("application/json")))
      .build();
    Response resp = client.newCall(req).execute();
    System.out.println(resp.body().string());
  }
}
PHP（cURL）
$ch = curl_init("https://api.tpz.pub/v1/chat/completions");
curl_setopt_array($ch, [
  CURLOPT_POST => true,
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer YOUR_API_KEY",
    "Content-Type: application/json"
  ],
  CURLOPT_POSTFIELDS => json_encode([
    "model" => "gpt-4o-mini",
    "messages" => [["role" => "user", "content" => "你好"]]
  ]),
  CURLOPT_RETURNTRANSFER => true
]);
$resp = curl_exec($ch);
echo $resp;
Multimodal & Extended APIs

多模态与扩展 API 示例

适合音频转写、向量检索、图片生成与视频生成等场景，可按需直接复制到项目中测试。

音频转写（curl）
curl -X POST "https://api.tpz.pub/v1/audio/transcriptions" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F "file=@./meeting.mp3" \
  -F "model=gpt-4o-mini-transcribe"
文本嵌入（Python / openai）
from openai import OpenAI

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

resp = client.embeddings.create(
    model="text-embedding-3-large",
    input=["GPTech API 支持多模型聚合调用"]
)

print(len(resp.data[0].embedding))
图片生成（JavaScript / fetch）
const resp = await fetch("https://api.tpz.pub/v1/images/generations", {
  method: "POST",
  headers: {
    "Authorization": "Bearer " + YOUR_API_KEY,
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    model: "gpt-image-1",
    prompt: "生成一张未来感 AI 控制台界面海报",
    size: "1024x1024"
  })
});

const data = await resp.json();
console.log(data.data[0].url || data.data[0].b64_json);
视频生成（curl / Sora）
curl -X POST "https://sora.tpz.pub/v1/video/generations" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "sora",
    "prompt": "生成一段 10 秒的无人机俯拍稻田视频，清晨阳光，电影感镜头",
    "duration": 10,
    "size": "1280x720"
  }'