Google introduced agentic video understanding in Gemini, which lets models dynamically search, scan, and inspect specific video segments rather than processing footage at a fixed frame rate. The feature supports Gemini 3.7 Flash, Gemini 3.6 Flash, and Gemini 3.5 Flash-Lite, and Google says it reduces token consumption by up to 88% and analysis cost by up to 66% while improving accuracy by up to 7% on long videos. It is available in the Gemini API, Google AI Studio, and the Gemini Enterprise Agent Platform by setting the processing mode to agentic, priced at standard Gemini API token rates with no additional feature fee.

Editor's note

This summary is based on the primary source. Open the original for full context, data, and qualifying details.