完全兼容 OpenAI 接口

# 最小示例:把 $KEY 换成你的密钥
curl https://api.xdro.net/v1/chat/completions \
  -H "Authorization: Bearer $KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"claude-sonnet-4-6","messages":[{"role":"user","content":"你好"}]}'

完全兼容 OpenAI SDK —— Python / Node 只改 base_url 与 api_key 即可。

# 流式
curl -N https://api.xdro.net/v1/chat/completions -H "Authorization: Bearer $KEY" \
 -H "Content-Type: application/json" \
 -d '{"model":"claude-sonnet-4-6","stream":true,"messages":[{"role":"user","content":"写个快排"}]}'

# 工具调用
-d '{"model":"claude-opus-4-8","messages":[{"role":"user","content":"北京天气?"}],
     "tools":[{"type":"function","function":{"name":"get_weather",
       "parameters":{"type":"object","properties":{"city":{"type":"string"}},"required":["city"]}}}]}'

# GPT-5(注意 max_completion_tokens)
-d '{"model":"gpt-5","messages":[{"role":"user","content":"你好"}],"max_completion_tokens":256}'

{"id":"...","object":"chat.completion","model":"claude-sonnet-4-6",
 "choices":[{"index":0,"finish_reason":"stop",
   "message":{"role":"assistant","content":"..."}}],
 "usage":{"prompt_tokens":12,"completion_tokens":34,"total_tokens":46}}

用 gemini-2.5-pro / flash / flash-lite 时,把 content 写成数组,混合文本与媒体即可让模型「看图 / 听音 / 看视频」并输出文本。仍是同一个 /v1/chat/completions 端点。

# 图片理解(用 gemini-2.5 系列;content 用数组,混合 text + 媒体)
curl https://api.xdro.net/v1/chat/completions -H "Authorization: Bearer $KEY" \
 -H "Content-Type: application/json" \
 -d '{"model":"gemini-2.5-flash","messages":[{"role":"user","content":[
   {"type":"text","text":"这张图里有什么?"},
   {"type":"image_url","image_url":{"url":"https://example.com/cat.jpg"}}]}]}'

# 音频理解 / 转写(音频格式仅支持 mp3 / wav;也可用 base64)
-d '{"model":"gemini-2.5-pro","messages":[{"role":"user","content":[
   {"type":"text","text":"把这段录音转写并总结要点"},
   {"type":"input_audio","input_audio":{"data":"<base64>","format":"mp3"}}]}]}'

用 gemini-2.5-flash-image(俗称 Nano Banana)即可文生图 / 改图,走的还是同一个 /v1/chat/completions 接口,返回内嵌的 data:image 图片,前端 <img> 直接显示。按张计费。

# 图像生成(Nano Banana / Gemini)—— 同一个 chat 接口,无需专门 SDK
curl https://api.xdro.net/v1/chat/completions -H "Authorization: Bearer $KEY" \
 -H "Content-Type: application/json" \
 -d '{"model":"gemini-2.5-flash-image","messages":[{"role":"user","content":"画一只戴墨镜的柴犬,卡通风格"}]}'
# 返回 choices[0].message.content 内含 Markdown 图片:![image](data:image/png;base64,....)
# 前端把这段 data:image 直接塞进 <img src> 即可显示 / 下载。改图:把原图作为 image_url 一起传入。

用独立的 /sunoapi/* 异步接口(不是 /v1/chat/completions),同一个 sk- 密钥即可:先 generate 提交拿 clip id,再 get?ids= 轮询取音频,一次出 2 首。按次计费:生成 ¥2 / 续写 · 伴奏分离 ¥1 / 歌词 ¥0.2 / 拼接 ¥0.5,失败自动退款,查询额度免费。

# 音乐生成(Suno)—— 独立异步接口 /sunoapi/*,用同一个 sk- 密钥
# 1) 提交生成(一次出 2 首)
curl https://api.xdro.net/sunoapi/api/generate \
 -H "Authorization: Bearer $KEY" -H "Content-Type: application/json" \
 -d '{"prompt":"一首温暖的中文民谣,木吉他伴奏","make_instrumental":false}'
# → 返回 2 个 clip(含 id)

# 2) 用 id 轮询获取音频(完成后含 audio_url)
curl "https://api.xdro.net/sunoapi/api/get?ids=<clip_id>" -H "Authorization: Bearer $KEY"

# 查询剩余额度(免费,不计费)
curl https://api.xdro.net/sunoapi/api/get_limit -H "Authorization: Bearer $KEY"

curl https://api.xdro.net/v1/models -H "Authorization: Bearer $KEY"
# → {"object":"list","data":[{"id":"claude-sonnet-4-6","object":"model",...}, ...]}