Monitor Gemini costsper feature.
Route your Gemini client through Spillr. Tag each call with a feature name. See exactly how much document-parser, search, or caption costs — not just a total bill.
Works with Gemini 2.5 · No prompt storage · 2-minute setup
import { GoogleGenerativeAI } from '@google/generative-ai';
const genAI = new GoogleGenerativeAI(process.env.GOOGLE_API_KEY, {
httpOptions: {
baseUrl: 'https://proxy.spillr.io/gemini/v1', // ← one line change
headers: {
'X-Spillr-Key': process.env.SPILLR_KEY,
'X-Spillr-Feature': 'document-parser', // ← tag per feature
},
},
});
const model = genAI.getGenerativeModel({ model: 'gemini-2.5-flash' });
const res = await model.generateContent(prompt);The problem
Gemini Flash is cheap — until you ship it everywhere.
Google's pricing varies by model tier and token type. When multiple features share one API key, you cannot tell which workflow drove a spike. Spillr adds per-feature visibility in two minutes.
Key-level totals only
Google's usage views aggregate by API key. Expensive features hide inside the total.
Multi-model confusion
Flash vs Pro pricing differs sharply. Spillr calculates exact cost per call from the model name.
No spend guardrails
Without budget limits, a bug in one feature can burn through your Gemini quota overnight.
Features
Everything you need to control Gemini spend.
Cost per feature
Add one header to your Gemini request. Spillr groups costs by feature in the dashboard.
Budget alerts
Set a monthly or daily spend limit per feature. Get an email alert when you hit 80%.
Hard stops
When a budget limit is reached, Spillr returns 429 before the request reaches Google.
Input + output tokens
Spillr tracks both token types and applies current Gemini pricing automatically.
Zero prompt storage
Spillr never stores your prompts or completions — only token counts and cost.
Multi-provider dashboard
Gemini, OpenAI, and Anthropic in one view. Same budgets and alerts across providers.
FAQ
Common questions about Gemini cost monitoring.
Does Spillr store my Gemini prompts or responses?
No. Spillr only records token counts, the model name, and the calculated cost. Your prompt text and model output are never stored — they pass straight through to Google.
Which Gemini models does Spillr support?
All Gemini models Spillr can route — including Gemini 2.5 Pro, 2.5 Flash, 2.0 Flash, and future releases. Pricing is looked up automatically from the model identifier in each request.
How is this different from Google AI Studio usage views?
Google's console shows aggregate usage per API key. Spillr adds per-feature cost breakdown — so you can see that document-parser costs $8/month while image-caption costs $1.
Can I monitor Gemini alongside OpenAI and Anthropic?
Yes. Spillr supports OpenAI, Anthropic, and Google Gemini from one dashboard with consistent budgets and alerts across providers.
How much does Spillr cost?
Spillr is completely free during beta. Full feature access with unlimited projects, unlimited API calls tracked, and no credit card required.
Start monitoring Gemini costs in 2 minutes.
Change one line. Add two headers. See per-feature Gemini costs immediately.
Create free account →