Introducing agentic video understanding with Gemini
Google DeepMind launches agentic video understanding for Gemini 3.7 Flash, 3.6 Flash, and 3.5 Flash-Lite, cutting video-analysis tokens up to 88%.
Google DeepMind launched agentic video understanding across Gemini 3.7 Flash, 3.6 Flash, and 3.5 Flash-Lite via the Gemini API in Google AI Studio and the Gemini Enterprise Agent Platform. The feature replaces static fixed-FPS ingestion with an agentic loop that dynamically searches frames, audio, and transcripts, cutting token consumption by up to 88%, reducing costs by up to 66%, and improving accuracy by up to 7%. Gemini 3.7 Flash with the feature sits at the accuracy-to-cost Pareto frontier on tested video benchmarks, and the capability will later power YouTube's Ask YouTube feature.
- Available via Gemini API by setting processing to agentic with no extra fee
- Enables sub-second moment retrieval, long-video search, anomaly detection, and counting
- Gains are largest on 10-minute to multi-hour long-form video
- Feature will roll out to Gemini app users and power YouTube Ask YouTube
- Vendors
- Google DeepMindGoogle
From the original article
4 min read at deepmind.google
Our new agentic feature for video analysis cuts token consumption by up to 88%, reduces costs by up to 66%, and boosts quality by up to 7%. This content is generated by Google AI. Generative AI is experimental Today, we’re launching agentic video understanding across our latest models: Gemini 3.
deepmind.google
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.