接口文档

支持对话、嵌入、重排、图像、视频、语音识别、语音合成

基础信息
Base URL
https://ai.lym2394.qzz.io/v1
认证
Authorization: Bearer sk-xxx
或 x-api-key: sk-xxx
重要说明

调用时 必须使用模型别名（模型列表中显示的 id）。
计费：对话/嵌入按 元/1M tokens；图像按张；视频按秒；其他按次。

对话 (OpenAI)
POST https://ai.lym2394.qzz.io/v1/chat/completions
{
  "model": "gpt-4o",
  "messages": [{"role": "user", "content": "Hello"}],
  "stream": false
}
对话 (Claude)
POST https://ai.lym2394.qzz.io/v1/messages
{
  "model": "claude-3-5-sonnet",
  "max_tokens": 1024,
  "messages": [{"role": "user", "content": "Hello"}]
}
对话 (Gemini)
POST https://ai.lym2394.qzz.io/v1beta/models/{model}:generateContent
{
  "contents": [{"role": "user", "parts": [{"text": "Hello"}]}]
}
嵌入
POST https://ai.lym2394.qzz.io/v1/embeddings
{
  "model": "text-embedding-3-small",
  "input": "Hello world"
}
重排序
POST https://ai.lym2394.qzz.io/v1/rerank
{
  "model": "rerank-english-v3.0",
  "query": "search query",
  "documents": ["doc1", "doc2"]
}
图像生成
POST https://ai.lym2394.qzz.io/v1/images/generations
{
  "model": "dall-e-3",
  "prompt": "a cat",
  "n": 1,
  "size": "1024x1024"
}
视频生成
POST https://ai.lym2394.qzz.io/v1/videos/generations
{
  "model": "veo-3",
  "prompt": "a running cat",
  "duration": 5
}
语音识别 (STT)
POST https://ai.lym2394.qzz.io/v1/audio/transcriptions
Content-Type: multipart/form-data

file: <音频文件>
model: whisper-1
语音合成 (TTS)
POST https://ai.lym2394.qzz.io/v1/audio/speech
{
  "model": "tts-1",
  "input": "你好，世界",
  "voice": "alloy"
}
模型列表
GET https://ai.lym2394.qzz.io/v1/models

返回首页