Google is adding agent-based video analysis to several Gemini models. Instead of scanning a video frame by frame at a fixed rate, the model hunts for relevant sections on its own, which Google says cuts token usage and costs by a wide margin.
The latest models, Gemini 3.7 Flash, 3.6 Flash, and 3.5 Flash-Lite, can pick up moments shorter than one second, including state changes or cuts that would slip through at one frame per second. Google says this makes automated video editing far more precise.
The system can also track down individual scenes in hours of footage without burning through millions of tokens. It spots anomalies by resampling suspicious time windows at a higher frame rate and accurately counts repeated movements and individual objects over time.
On 1H-VideoQA and LVBench, token usage drops by 88 percent while accuracy goes up slightly. | Image: Google
Until now, Gemini relied on static processing, sampling video at a fixed frame rate of one frame per second by default and adjustable through the API. Since native video analysis launched in 2025, Gemini has been transcribing the audio track and analyzing frames on a per-second basis.
