Source
Introducing agentic video understanding with Gemini
Google launched agentic video understanding for Gemini 3.7 Flash, 3.6 Flash, and 3.5 Flash-Lite models. This feature dynamically analyzes video content using native tools rather than static frames-per-second processing.
Why it matters
Developers can process long videos more accurately and cheaply, enabling precise automated editing and complex searches without excessive token costs.
The details
The feature is available via Gemini API in Google AI Studio and Gemini Enterprise Agent Platform. It enables capabilities like sub-second moment retrieval, anomaly detection, and precise counting. Gemini 3.7 Flash is noted as having the best balance of quality and cost efficiency.
What's next
The feature will roll out to the Gemini app and power YouTube's 'Ask YouTube' feature in the coming months.
Show entities and relationshipsHide entities and relationships
In this article
Companies
Key connections
Rohan Doshi works at Google
Mario Lučić works at Google
Get the weekly recap
The stories like this one, picked and explained — once a week, straight to your inbox.