Google launches agentic video understanding in Gemini Flash models
Start here
Google DeepMind launched agentic video understanding across Gemini 3.7 Flash, 3.6 Flash and 3.5 Flash-Lite. Instead of ingesting video at a fixed frame rate, the model uses native video tools in an agentic loop to search frames, audio and transcripts and fetch only the needed segments. Google says this cuts token consumption by up to 88%, analysis costs by up to 66% and improves accuracy by up to 7%, enabling sub-second moment retrieval, long-form needle-in-a-haystack search, anomaly detection and object counting. The feature is available for video uploads and YouTube videos via the Gemini API in Google AI Studio and the Gemini Enterprise Agent Platform, at standard Gemini API token pricing with no additional feature fee. Google says it will roll out to all users in the Gemini app across Flash and Flash-Lite models soon, and in the coming months will power YouTube's "Ask YouTube" feature on the watch page.
Generated from reports · updated 1 h ago
Report timeline
Follow the reports to see the event from different sides.
- Hacker News · AIPicksGoogle launches agentic video understanding in Gemini 3.7 Flash, 3.6 Flash and 3.5 Flash-Lite
5 Flash-Lite, cutting token consumption by up to 88%, analysis costs by up to 66% and improving accuracy by up to 7%. Instead of ingesting video at a fixed frame rate, the model uses native video tools in an agentic loop to search frames, audio and transcripts and fetch only the needed segments, enabling sub-second moment retrieval, long-form needle-in-a-haystack search, anomaly detection and object counting.
Heat for this event
Not enough continuous observations yet to draw a trend.