# Introducing agentic video understanding with Gemini

Publisher-attributed story with a reviewed brief or permitted publisher paragraph. The original publisher is responsible for the linked reporting.

- Publisher: Google DeepMind
- Category: AI
- Original publication time: 2026-09-01T17:08:51Z
- First observed by NexusTechWire: 2026-10-01T20:28:41Z
- Original source: https://deepmind.google/blog/introducing-agentic-video-in-gemini/
- NexusTechWire record: https://nexustechwire.com/news/news-20b040f8e58f31e96773

## The brief

Google DeepMind introduced a video-analysis mode that lets Gemini search and re-examine relevant moments instead of processing footage at a fixed frame rate. The September 1 announcement covers Gemini 3.7 Flash, 3.6 Flash and 3.5 Flash-Lite through the Gemini API. Google reports lower token use and costs in its benchmarks, with particular benefits for long recordings; these are vendor-reported results.

AI-assisted NexusTechWire summary, checked against the linked source on 2026-10-02T02:55:35Z. Not independent reporting.

Read the full original: [Google DeepMind](https://deepmind.google/blog/introducing-agentic-video-in-gemini/)

This record does not reproduce the complete article or represent independent confirmation of every source claim.