What is Firebase AI Logic?
Firebase AI Logic enables developers to build AI-powered mobile and web applications by providing client SDKs for direct access to Google’s Gemini models from apps rather than server-side only.
Core Features
- Multimodal input and output for text, images, PDFs, video and audio
- Multi-turn conversational experiences
- Generation of text, code, images and speech (text-to-speech)
- Structured output in JSON format
- Function calling for tool integration
- Grounding through Google Search and Google Maps integrations
- Live API for real-time bidirectional streaming including audio
- Hybrid inference with on-device and cloud model fallback
Typical Use Cases
In-app assistance: Users ask questions in the context of the application and receive answers from a Gemini model.
Processing uploaded content: Images, PDFs or audio recordings are analyzed directly from the app.
Voice dialogues: Voice interactions with bidirectional streaming are implemented through the Live API.
Benefits
- No dedicated backend service required for model access
- Protection via Firebase App Check and per-user rate limits
- Consistent SDKs for Apple, Android, web, Flutter and Unity applications
- Choice between the Gemini Developer API and the Agent Platform Gemini API
Integration with innFactory
As a certified Google Cloud Partner, innFactory supports you with Firebase AI Logic: choosing the right model provider, securing calls via App Check and rate limits, and integrating it into existing app architectures.
Typical Use Cases
Technical Specifications
Frequently Asked Questions
What is Firebase AI Logic?
Firebase AI Logic provides client SDKs that let mobile and web applications access Google's Gemini models directly from the app rather than server-side only.
Which platforms are supported?
According to the documentation, SDKs are available for Swift (Apple), Kotlin and Java (Android), JavaScript (Web), Dart (Flutter) and Unity.
How is access secured?
Firebase AI Logic can be protected with Firebase App Check to block calls from unauthorized clients. Per-user rate limits are configurable, and Gemini Developer API keys remain server-side via a proxy service.
Which model providers are available?
According to the documentation, the Gemini Developer API and the Agent Platform Gemini API (formerly Vertex AI) are supported.
What features does Firebase AI Logic offer?
Documented features include multimodal input and output for text, images, PDFs, video and audio, multi-turn chat, text, code, image and speech generation, structured JSON output, function calling, grounding with Google Search and Google Maps, a Live API for bidirectional streaming, and hybrid inference with on-device and cloud fallback.
Note: All product information on this page has been compiled with care, but is provided without guarantee and may be outdated or incomplete. Cloud services evolve rapidly — features, pricing, SLAs, and availability change frequently. Authoritative and up-to-date information can only be found on the official product page of Google Cloud (official documentation). This page does not represent an offer by Google Cloud.
