Client-side Gemini integration for web apps with multimodal inference, streaming, and on-device hybrid execution.
- Supports text-only and multimodal inputs (images, audio, video, PDFs); files over 20 MB route through Cloud Storage
- Includes chat sessions with automatic history, streaming responses for real-time display, and structured JSON output enforcement
- Offers hybrid on-device inference via Gemini Nano in Chrome, with automatic fallback to cloud execution
- Requires App Check for production security and supports dynamic model versioning through Remote Config to avoid redeployment
- Choose between Gemini Developer API (free tier, prototyping) or Vertex AI Gemini API (enterprise scale, requires Blaze plan)