# Google Gives Gemini Agentic Video Search and Claims an 88 Percent Cut in Token Use

The feature lets the model choose which segments of a video to inspect instead of ingesting every frame, and Google puts the cost reduction at up to 66 percent.

- Published: 2026-09-02T06:20:39.906Z
- Canonical: https://polylog.news/ai/2026-09-02/google-gives-gemini-agentic-video-search-and-claims-an-88-pe
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [Google DeepMind](https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-agentic-video-in-gemini/), [Google AI Blog](https://blog.google/innovation-and-ai/technology/google-ai-updates-august-2026/)

Google introduced agentic video understanding for Gemini on September 1. Instead of tokenizing an entire video up front, the model scans segments dynamically and pulls in only the parts it needs to answer the question. Developers switch it…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-09-02/google-gives-gemini-agentic-video-search-and-claims-an-88-pe (subscription information: https://polylog.news/pricing).