Google Launches Gemini Agent Video Understanding Feature, Reducing Token Consumption by Up to 88%

DeepTech TechFlow reports that on September 2, Google DeepMind released the Gemini agent video understanding feature, now available for Gemini 3.7 Flash, 3.6 Flash, and 3.5 Flash-Lite models. This feature enhances the efficiency and accuracy of long video analysis through dynamic searching, scanning, and inspecting video clips. Compared to traditional fixed frame rate processing methods, it can reduce token consumption by up to 88%, lower analysis costs by 66%, and improve accuracy by up to 7%. The feature is now accessible via the Gemini API on Google AI Studio and the Gemini Enterprise Agent Platform, and will be applied to Gemini applications and YouTube's "Ask YouTube" feature in the future.