From the source
Google DeepMind added agentic video understanding to Gemini 3.7 Flash, 3.6 Flash, and 3.5 Flash-Lite across the Interactions and GenerateContent APIs.
- The model dynamically navigates video timelines, requesting transcripts, frames, or audio tracks on demand instead of processing every frame.
- This approach uses up to 88% fewer tokens for long-form content compared to static processing, according to Google DeepMind.
- The feature is available now through the Gemini API, with a guide to get started.




