Gemini + RevenueCat + Firebase in a React Native boilerplate
Does AI Mobile Launcher support this combo?
Gemini ships in AI Pro out of the box. RevenueCat ships in both tiers. Firebase Auth + Firestore are not the default data layer (Supabase is), you swap them in. Firebase Analytics + Crashlytics + Remote Config + FCM are already wired. If you want a fully Google-aligned stack with one billing account, this is the combo to target.
The stack
- React Native 0.83.6 + Expo SDK 55.0.17
- Gemini: REST client at
src/features/gen-ui/api/gemini.api.ts.gemini-2.0-flashdefault,gemini-2.0-profor harder reasoning - Firebase Auth + Firestore: you add the packages. Analytics + Crashlytics + Remote Config + FCM already wired
- RevenueCat: pre-wired
- Optional: Vertex AI in Firebase as the Gemini gateway (one project, one bill)
Setup in five steps
1. Clone AI Pro
git clone <ai-pro-tier-repo>
cd ai-mobile-launcher
pnpm install2. Gemini key (two paths)
# Path A: AI Studio key (simpler)
GOOGLE_GEMINI_API_KEY=AIza...
# Path B: Vertex AI in Firebase (unified billing)
# Use @react-native-firebase/vertexai (calls Gemini through your Firebase project)
# No separate API key; uses google-services.json identity.3. Firebase Auth + Firestore
pnpm add @react-native-firebase/auth @react-native-firebase/firestore
# Replace src/features/auth/services with Firebase versions
# google-services.json + GoogleService-Info.plist already present4. RevenueCat env
# .env
EXPO_PUBLIC_REVENUECAT_IOS_KEY=appl_...
EXPO_PUBLIC_REVENUECAT_ANDROID_KEY=goog_...5. Dev build
eas build --profile development --platform iosWhy this combo works
Single billing, single IAM, single project. Vertex AI in Firebase lets you call Gemini from the mobile SDK without managing API keys on the client, because the request is authenticated as the Firebase user. That removes the entire "ship a proxy" chapter for solo developers.
Gemini Flash + Firestore is the cheapest combo on this comparison. At 100K MAU with average usage, you can probably stay under $1000/mo infrastructure including LLM, before store fees.
The catch: you commit to a single vendor. If Google deprecates a Gemini model or changes Firestore pricing, your only escape is a full re-platform. The hedge is to write the data layer behind RTK Query so the queryFn is the only thing that has to change.
What it costs at scale
| Line item | 1K MAU | 100K MAU |
|---|---|---|
| Gemini 2.0 Flash | ~$1 | ~$100 |
| RevenueCat | $0 | ~$200 |
| Firestore | ~$0 | ~$300-600 |
| Firebase Auth | $0 | ~$50 |
| Total (excl. store fees) | ~$1 | ~$650-950 |
Cheapest combo on this page at most scales. Cost-sensitive bootstrap teams should start here.
What this combo does NOT cover
- Vendor diversification: you are all-in on Google Cloud
- pgvector / SQL: Firestore is document only
- Out-of-the-box Firestore wiring: you swap Supabase yourself
- Image generation: analysis only
Get this combo
AI Pro tier ($199) for the Gemini + RevenueCat wiring. Add Firebase data-layer yourself.
See AI Pro tier ($199)