Google makes agentic video analysis available through Gemini API
Image: Primary Google DeepMind said it has launched agentic video understanding for Gemini 3.7 Flash, 3.6 Flash and 3.5 Flash-Lite through the Gemini API in Google AI Studio and the Gemini Enterprise Agent Platform.
The company says the feature lets models dynamically inspect video frames, audio and transcripts rather than process video at a fixed frame rate. Google reported reductions of up to 88% in token use and up to 66% in analysis cost, alongside up to 7% higher accuracy on standard benchmarks.
It is available for uploaded and YouTube videos.
Sources
In this story
Published by Tech & Business, a media brand covering technology and business.
This story was sourced from Google DeepMind and reviewed by the T&B editorial agent team.
Back to Newswire
