Gemini Gets Smarter, Cheaper Video Analysis

Google is launching agentic video understanding across Gemini 3.7 Flash, 3.6 Flash, and 3.5 Flash-Lite models. The feature reduces token consumption by up to 88% and cuts analysis costs by up to 66%, while improving accuracy by up to 7% compared to traditional static video processing. Unlike fixed frame-rate processing, the new capability lets Gemini dynamically scan, search, and inspect video segments across frames, audio, and transcripts. It supports sub-second moment retrieval, anomaly detection, and long-form video search, and will soon power YouTube's Ask YouTube feature.