Google AI Studio

Route your Google AI Studio / Gemini API calls through AI SpendOps for automatic usage tracking and cost attribution.

Configuration

Setting	Value
Route	/v1/google/*
Upstream	https://generativelanguage.googleapis.com
Auth header	Authorization: Bearer ... or x-goog-api-key: ...
Streaming usage	Auto-injected (stream_options.include_usage)

SDK base URL

https://proxy.aispendops.com/v1/google

Example

curl https://proxy.aispendops.com/v1/google/v1beta/openai/chat/completions \
  -H "Authorization: Bearer your-google-api-key" \
  -H "X-ASO-API-Key: aso_k_yourkey.secret" \
  -H "Content-Type: application/json" \
  -d '{"model":"gemini-2.0-flash","messages":[{"role":"user","content":"Hello"}]}'

Python SDK

from openai import OpenAI

client = OpenAI(
    api_key="your-google-api-key",
    base_url="https://proxy.aispendops.com/v1/google/v1beta/openai",
    default_headers={"X-ASO-API-Key": "aso_k_yourkey.secret"},
)

response = client.chat.completions.create(
    model="gemini-2.0-flash",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Usage fields

Field	Description
promptTokenCount	Input tokens
candidatesTokenCount	Output tokens
totalTokenCount	Total tokens
cachedContentTokenCount	Tokens served from cached content
thoughtsTokenCount	Tokens used for thinking (via usageMetadata)

Notes

• Google AI Studio supports both Authorization: Bearer and x-goog-api-key for authentication.
• The proxy auto-injects stream_options: { include_usage: true } for streaming requests via the OpenAI-compatible endpoint.
• Usage metadata is returned in a usageMetadata object in Google's native response format.