Google DeepMind adds agentic video understanding to Gemini Flash models, using up to 88% fewer tokens

Google DeepMind has launched agentic video understanding on Gemini 3.7 Flash, Gemini 3.6 Flash, and Gemini 3.5 Flash-Lite, so the models can search a video on demand instead of ingesting it at a fixed frame rate. Google says the change uses up to 88% fewer tokens, cuts analysis costs by up to 66%, and raises accuracy by up to 7% on standard video benchmarks.