Google Gemini Flash 3.5, a fast model optimized for everyday dialogue, content processing, and real-time inference.

Built for everyday dialogue, content processing, and real-time inference.

Optimized for real-time interaction.

Understands and generates multiple languages.

Supports text, image, and audio inputs.

Handles long documents and workflows.
Low-latency responses.
Easy to integrate through a unified API.
Suitable for prototypes and production.

Context Window
Long Context
Knowledge Cutoff
Broad Knowledge
Modalities
Text, Image
Max Output
Flexible Output
Live prices for every group currently available to you, displayed in USD.
Real-time dialogue, content processing, and high-concurrency applications.
Get an API key and call it through the unified API.
See the console and API documentation for current limits.