DeepMind adds agentic video understanding to Gemini, 88% fewer tokens

Google DeepMind launched agentic video understanding across Gemini 3.7 Flash, 3.6 Flash and 3.5 Flash-Lite. This new capability improves accuracy while dramatically reducing token usage and costs for video analysis. Unlike current 'static' processing, where the model ingests the video at a fixed frames-per-second rate, agentic video understanding pairs the model's core reasoning with native video tools to dynamically search, scan, and inspect target video segments across visual frames, audio, and transcripts. Across standard video analysis benchmarks, Gemini models with agentic video understanding reduce analysis costs by up to 66% and token consumption by up to 88%, while improving accuracy by up to 7%. These efficiency gains are especially pronounced on long-form video (from 10-minute how-to guides to 90-minute lectures and multi-hour recordings), where static processing forces developers to choose between high token costs or techniques that drop critical details. Instead of static processing where the model ingests media streams at a fixed frame rate, agentic video understanding enables Gemini to take an active, goal-directed role in determining what to watch, at what speed, and through which modality (frames, audio, or transcript), fetching only the moments and signals needed. The feature is available today for video uploads and YouTube videos via the Gemini API. Gemini 3.7 Flash with agentic understanding offers the best possible quality overall and the best combination of quality and cost efficiency.