Google DeepMind launches agentic video understanding for Gemini
Original title:Introducing agentic video understanding with Gemini
AI summary
Google DeepMind launched agentic video understanding for Gemini 3.7 Flash, 3.6 Flash and 3.5 Flash-Lite. The models dynamically scan video segments, cutting token consumption by up to 88%, costs by up to 66% and improving accuracy by up to 7% compared with fixed-frame-rate processing.
Key Takeaways
- Google DeepMind launched agentic video understanding for Gemini 3.
- 7 Flash,3.
- 6 Flash and 3.
- 5 Flash-Lite.
- The models dynamically scan video segments,cutting token consumption by up to 88%,costs by up to…
Quick Facts
- Published
- Updated
- Source
- Google DeepMind:Blog(RSS)
- Category
- Products & Apps
- AI score
- 72
官方说明列出 token、成本与准确率三项数字和开启方式,开发者可据此评估长视频分析是否换用该模式。
Related entities
Source & copyright
This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.
How to Cite
When citing this article, keep the title, date, and permalink, and credit Orange News as the source.
Orange News: Google DeepMind launches agentic video understanding for Gemini. September 2, 2026. https://new.nat6.net/en/news/cmtiy0v6k01dproel63pg10os/