DeepMind ships agentic video understanding for Gemini Flash

DeepMind published that agentic video understanding is live on Gemini 3.7 Flash, 3.6 Flash, and 3.5 Flash-Lite — a loop that searches the tape instead of reading every frame at a fixed rate.

DeepMind put a search-the-tape video loop on three Flash models, so you pay for the frames that matter instead of every frame.

DeepMind published “Introducing agentic video understanding with Gemini.” The lab says the feature launched on Gemini 3.7 Flash, 3.6 Flash, and 3.5 Flash-Lite. That post is the primary.

DeepMind contrasts it with static processing, where the model reads video at a fixed frames-per-second rate (default 1 FPS). Agentic mode, it says, pairs Gemini’s reasoning with built-in video tools in a loop that searches, scans, and inspects target segments across frames, audio, and transcripts — fetching only what the query needs.

DeepMind’s figures on the same page: up to 88% fewer tokens, up to 66% lower cost, and up to 7% better accuracy versus static ingest on “standard video analysis benchmarks.” Those are DeepMind benches.

It is available for video uploads and YouTube URLs via the Gemini API in Google AI Studio and the Gemini Enterprise Agent Platform. Enable it by setting processing to “agentic” in the API config.

Pricing, per DeepMind, is standard Gemini API token rates. The lab says there is no extra feature fee.

The same page, not today’s ship, sketches a roadmap: DeepMind says the feature will roll out in the Gemini app on Flash and Flash-Lite “soon,” and that in the coming months it will power YouTube’s Ask YouTube on the watch page. Treat those as company plans.