Google adds agentic video understanding to Gemini Flash

Google just taught Gemini Flash to hunt through video the way a person would, jumping to the useful seconds instead of chewing every frame. Google DeepMind announced agentic video understanding on September 1, in a post by Rohan Doshi and Mario Lucic. The change is how the Flash models read video, not a new model.

The feature is live on Gemini 3.7 Flash, 3.6 Flash, and 3.5 Flash-Lite, for both uploaded video and YouTube links, through the Gemini API in Google AI Studio and the Gemini Enterprise Agent Platform. You turn it on by setting the processing mode to agentic in the API config. Google says it runs on standard Gemini API token pricing with no separate feature fee.

Normal video ingest is static. The model samples frames at a fixed rate, one frame per second by default, and reasons over that flattened strip. Agentic mode pairs the model's reasoning with native video tools inside a loop, so it can search, scan, and inspect specific segments across frames, audio, and transcripts.

That is what unlocks the use cases Google lists: sub-second moment retrieval, needle-in-a-haystack search across long recordings, anomaly detection that resamples at a higher frame rate where it matters, and counting actions or objects. The pitch is aimed at long footage, from ten-minute how-tos to multi-hour recordings, where fixed sampling either misses the moment or burns tokens on frames that do not matter.

Google claims agentic mode delivers up to 88% lower token consumption, up to 66% lower analysis cost, and up to 7% higher accuracy on standard video benchmarks, with the largest gains on long-form content. It says the 3.7 Flash configuration lands on the accuracy-to-cost pareto frontier among the models it tested. Those numbers come from Google's own testing on its own benchmark set, not a third-party audit, the same efficiency pitch rivals are making next to open-weight model previews.

Two things are not shipping today. Agentic understanding in the consumer Gemini app for Flash and Flash-Lite is coming "soon," and an Ask YouTube experience on the watch page is slated for "the coming months." Right now this is an API and AI Studio capability for developers and enterprise builders, not a feature in the phone app.

Some offers on this page may be paid placements or contain affiliate links.