Google AI Studio API 中繼

對應 Google Generative Language API 規格 (Gemini / Veo / Lyria)。認證用 x-goog-api-key: YOUR_API_KEY 或 Authorization: Bearer YOUR_API_KEY 標頭（金鑰不可放在網址查詢參數；?key= query 已停用——Google 官方 SDK 預設即用 header）。

POST /stu/api/google/v1beta/models/{model}:generateContent

Gemini 文字對話 (non-streaming)。

curl "https://www.myai168.com/stu/api/google/v1beta/models/gemini-3.1-pro-preview:generateContent" \
  -H "x-goog-api-key: YOUR_DEV_KEY" \
  -H "Content-Type: application/json" \
  -d '{"contents":[{"parts":[{"text":"Hello"}]}]}'

import requests

r = requests.post(
    "https://www.myai168.com/stu/api/google/v1beta/models/gemini-3.1-pro-preview:generateContent",
    headers={"x-goog-api-key": "YOUR_DEV_KEY"},
    json={"contents": [{"parts": [{"text": "Hello"}]}]},
)
print(r.json())

POST /stu/api/google/v1beta/models/{model}:streamGenerateContent

Gemini 文字對話 (SSE streaming)。

curl "https://www.myai168.com/stu/api/google/v1beta/models/gemini-3.1-pro-preview:streamGenerateContent" \
  -H "x-goog-api-key: YOUR_DEV_KEY" \
  -H "Content-Type: application/json" \
  -d '{"contents":[{"parts":[{"text":"Hello"}]}]}'

import requests

r = requests.post(
    "https://www.myai168.com/stu/api/google/v1beta/models/gemini-3.1-pro-preview:streamGenerateContent",
    headers={"x-goog-api-key": "YOUR_DEV_KEY"},
    json={"contents": [{"parts": [{"text": "Hello"}]}]},
    stream=True,
)
for line in r.iter_lines():
    if line:
        print(line.decode("utf-8"))

POST /stu/api/google/v1beta/models/gemini-3-pro-image-preview:generateContent

Nano Banana Pro 文字生圖（Gemini 多模態，回 inline_data base64 image）。

curl "https://www.myai168.com/stu/api/google/v1beta/models/gemini-3-pro-image-preview:generateContent" \
  -H "x-goog-api-key: YOUR_DEV_KEY" \
  -H "Content-Type: application/json" \
  -d '{"contents":[{"parts":[{"text":"A cat"}]}],"generationConfig":{"responseModalities":["TEXT","IMAGE"]}}'

import requests

r = requests.post(
    "https://www.myai168.com/stu/api/google/v1beta/models/gemini-3-pro-image-preview:generateContent",
    headers={"x-goog-api-key": "YOUR_DEV_KEY"},
    json={"contents": [{"parts": [{"text": "A cat"}]}], "generationConfig": {"responseModalities": ["TEXT", "IMAGE"]}},
)
print(r.json())

POST /stu/api/google/v1beta/models/veo-{ver}:predictLongRunning

Veo 影片生成 (LRO; 第一次回 operation name，後續 poll 取結果)。

curl "https://www.myai168.com/stu/api/google/v1beta/models/veo-3.1-generate-preview:predictLongRunning" \
  -H "x-goog-api-key: YOUR_DEV_KEY" \
  -H "Content-Type: application/json" \
  -d '{"instances":[{"prompt":"A cat dancing"}],"parameters":{"durationSeconds":8}}'

import requests

r = requests.post(
    "https://www.myai168.com/stu/api/google/v1beta/models/veo-3.1-generate-preview:predictLongRunning",
    headers={"x-goog-api-key": "YOUR_DEV_KEY"},
    json={"instances": [{"prompt": "A cat dancing"}], "parameters": {"durationSeconds": 8}},
)
print(r.json())

POST /stu/api/google/v1beta/models/lyria-{ver}:predict

Lyria 音樂生成 (回 base64 audio)。

curl "https://www.myai168.com/stu/api/google/v1beta/models/lyria-002:predict" \
  -H "x-goog-api-key: YOUR_DEV_KEY" \
  -H "Content-Type: application/json" \
  -d '{"instances":[{"prompt":"Upbeat jazz"}],"parameters":{"sampleCount":1}}'

import requests

r = requests.post(
    "https://www.myai168.com/stu/api/google/v1beta/models/lyria-002:predict",
    headers={"x-goog-api-key": "YOUR_DEV_KEY"},
    json={"instances": [{"prompt": "Upbeat jazz"}], "parameters": {"sampleCount": 1}},
)
print(r.json())

GET /stu/api/google/v1beta/operations/{name}

查詢 LRO 操作狀態 (Veo poll 用，查詢類不扣點)。

curl "https://www.myai168.com/stu/api/google/v1beta/operations/OP_NAME" \
  -H "x-goog-api-key: YOUR_DEV_KEY"

import requests

r = requests.get(
    "https://www.myai168.com/stu/api/google/v1beta/operations/OP_NAME",
    headers={"x-goog-api-key": "YOUR_DEV_KEY"},
)
print(r.json())

請求參數（generateContent／streamGenerateContent）

請求本體為 JSON，與 Google 官方規格相同。認證帶 x-goog-api-key 或 Authorization: Bearer 標頭。

模型代號放在網址路徑（models/{model}:generateContent）；不在計價表內的模型回 "No pricing info! Please use other models!"。Veo 用 instances＋parameters（durationSeconds／numberOfVideos／resolution），Lyria 用 instances＋parameters.sampleCount（見上一題範例）。

回應格式

非串流：官方 JSON——文字在 candidates[0].content.parts[]、用量在 usageMetadata；回應標頭另帶 X-Cost-Points（本次扣點）與 X-Credits-Remaining（扣後餘額）。串流（:streamGenerateContent）為 SSE 逐段，無法帶扣點標頭，餘額請改查 GET /stu/api/user/get_credits。

錯誤碼

任何錯誤（含供應商未回用量資訊）一律不扣點；查詢 LRO 狀態（operations）免費。