OpenRouter API 中繼

OpenRouter 是 LLM gateway，一個金鑰可呼叫數百種 model (OpenAI / Anthropic / Google / Meta / Mistral 等)，model 名格式為 vendor/model。

POST /stu/api/openrouter/v1/chat/completions

Chat Completions (相容 OpenAI 格式)。

curl https://www.myai168.com/stu/api/openrouter/v1/chat/completions \
  -H "Authorization: Bearer YOUR_DEV_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"anthropic/claude-3.5-sonnet","messages":[{"role":"user","content":"Hello"}]}'

import requests

r = requests.post(
    "https://www.myai168.com/stu/api/openrouter/v1/chat/completions",
    headers={"Authorization": "Bearer YOUR_DEV_KEY"},
    json={"model": "anthropic/claude-3.5-sonnet", "messages": [{"role": "user", "content": "Hello"}]},
)
print(r.json())

POST /stu/api/openrouter/v1/chat/responses

注意：此端點不是 OpenAI Responses API——請求與回應皆為 Chat Completions 格式（欄位同上方 completions），與 completions 的唯一差異是送出前會先檢查點數餘額，點數不足直接回 402、不轉發上游。要用 OpenAI Responses API 格式請改用 /stu/api/openai/v1/responses。

curl https://www.myai168.com/stu/api/openrouter/v1/chat/responses \
  -H "Authorization: Bearer YOUR_DEV_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"openai/gpt-4o","messages":[{"role":"user","content":"Hello"}]}'

import requests

r = requests.post(
    "https://www.myai168.com/stu/api/openrouter/v1/chat/responses",
    headers={"Authorization": "Bearer YOUR_DEV_KEY"},
    json={"model": "openai/gpt-4o", "messages": [{"role": "user", "content": "Hello"}]},
)
print(r.json())

POST /stu/api/openrouter/v1/audio/speech

文字轉語音 (透過 OpenRouter 路由到 TTS 供應商)。

curl https://www.myai168.com/stu/api/openrouter/v1/audio/speech \
  -H "Authorization: Bearer YOUR_DEV_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"openai/tts-1","input":"Hello","voice":"nova"}' \
  --output speech.mp3

import requests

r = requests.post(
    "https://www.myai168.com/stu/api/openrouter/v1/audio/speech",
    headers={"Authorization": "Bearer YOUR_DEV_KEY"},
    json={"model": "openai/tts-1", "input": "Hello", "voice": "nova"},
)
with open("speech.mp3", "wb") as f:
    f.write(r.content)

POST /stu/api/openrouter/v1/audio/transcriptions

語音轉文字 (multipart upload)。

curl https://www.myai168.com/stu/api/openrouter/v1/audio/transcriptions \
  -H "Authorization: Bearer YOUR_DEV_KEY" \
  -F file=@audio.mp3 \
  -F model=gpt-4o-transcribe

import requests

with open("audio.mp3", "rb") as f:
    r = requests.post(
        "https://www.myai168.com/stu/api/openrouter/v1/audio/transcriptions",
        headers={"Authorization": "Bearer YOUR_DEV_KEY"},
        files={"file": f},
        data={"model": "gpt-4o-transcribe"},
    )
print(r.json())

POST /stu/api/openrouter/v1/video/generations

影片生成 (依 OpenRouter 支援的 video model)。

curl https://www.myai168.com/stu/api/openrouter/v1/video/generations \
  -H "Authorization: Bearer YOUR_DEV_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"vendor/some-video-model","prompt":"A cat dancing"}'

import requests

r = requests.post(
    "https://www.myai168.com/stu/api/openrouter/v1/video/generations",
    headers={"Authorization": "Bearer YOUR_DEV_KEY"},
    json={"model": "vendor/some-video-model", "prompt": "A cat dancing"},
)
print(r.json())

請求參數（chat/completions 與 chat/responses）

兩端點的請求本體都是 Chat Completions 格式 JSON（chat/responses 只是多了點數預檢，不是 OpenAI Responses API）。認證帶 Authorization: Bearer YOUR_API_KEY 標頭（金鑰不可放在網址查詢參數）。

回應格式

與 OpenAI Chat Completions 相容：文字在 choices[0].message.content（串流增量在 choices[0].delta.content）。計費依 OpenRouter 回報的實際費用換算點數；餘額可隨時以 GET /stu/api/user/get_credits 查詢。

錯誤碼

任何錯誤（含供應商未回用量／費用資訊）一律不扣點。