Last updated: 2026-04-20

Google Gemini Integration

Route Google Gemini API calls through SpendLil.

SpendLil proxies Google's Generative AI API. Swap generativelanguage.googleapis.com for google.gateway.spendlil.ai and add X-SpendLil-Key. Your existing x-goog-api-key header passes through unchanged.

URL Pattern

diff Before → After 
- POST https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:generateContent
+ POST https://google.gateway.spendlil.ai/v1beta/models/gemini-2.0-flash:generateContent
ℹ Google SDK base URL

Google's official SDKs don't currently expose a base URL override. Use the REST API directly (shown below) or set up an HTTP client that supports custom base URLs.

cURL

bash Direct HTTP request 
curl https://google.gateway.spendlil.ai/v1beta/models/gemini-2.0-flash:generateContent \
  -H "x-goog-api-key: $GOOGLE_API_KEY" \
  -H "X-SpendLil-Key: $SPENDLIL_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [{"parts": [{"text": "Hello"}]}]
  }'

Python (httpx)

python Direct REST call 
import os
import httpx

response = httpx.post(
    'https://google.gateway.spendlil.ai/v1beta/models/gemini-2.0-flash:generateContent',
    headers={
        'x-goog-api-key': os.environ['GOOGLE_API_KEY'],
        'X-SpendLil-Key': os.environ['SPENDLIL_KEY'],
    },
    json={'contents': [{'parts': [{'text': 'Hello'}]}]},
)
data = response.json()
print(data['candidates'][0]['content']['parts'][0]['text'])

Node.js (fetch)

javascript Direct REST call 
const response = await fetch(
  'https://google.gateway.spendlil.ai/v1beta/models/gemini-2.0-flash:generateContent',
  {
    method: 'POST',
    headers: {
      'x-goog-api-key': process.env.GOOGLE_API_KEY,
      'X-SpendLil-Key': process.env.SPENDLIL_KEY,
      'Content-Type': 'application/json',
    },
    body: JSON.stringify({
      contents: [{ parts: [{ text: 'Hello' }] }],
    }),
  }
);

const data = await response.json();
console.log(data.candidates[0].content.parts[0].text);

Cost Tracking

SpendLil extracts usageMetadata.promptTokenCount and usageMetadata.candidatesTokenCount from Google's response and calculates cost using current model pricing.

ModelInput (per 1M tokens)Output (per 1M tokens)
gemini-2.0-flash$0.10$0.40
gemini-2.0-pro$1.25$10.00