Search
Google Launches Video Understanding Feature for Gemini Agents, Reducing Token Consumption by Up to 88%
2 day ago /
Read about 0 minute
Author：小编
Google DeepMind has introduced a video understanding feature for Gemini agents, now available to the Gemini 3.7 Flash, 3.6 Flash, and 3.5 Flash-Lite models. This feature significantly enhances the efficiency and accuracy of long video analysis, reducing token consumption by up to 88% compared to traditional methods, lowering analysis costs by 66%, and improving accuracy by up to 7%. Currently, the feature is accessible via the Gemini API in Google AI Studio and the Gemini Enterprise Agent Platform, with plans to expand to the Gemini app and YouTube's 'Ask YouTube' feature in the future.
-
C114 Communication Network -
Communication Home
7 X 24 Track global technological trends
