Google Launches Agentic Video Understanding for Gemini

Scobleizer · x · 2026-09-02

Google has launched Agentic Video Understanding in Gemini 1.5 Flash, 1.5 Flash-8B, and 1.5 Flash-Lite.

Unlike traditional static processing, this feature enables Gemini to actively decide what to watch, the playback speed, and which signals (frames, audio, or transcripts) to use. Google reports approximately 88% fewer tokens, 66% lower costs, and 7% higher accuracy.

The feature is available now via the Gemini API and will soon roll out to the Gemini App and YouTube's "Ask YouTube" experience.

Related event: Google DeepMind rolls out Agentic Video Understanding for Gemini, cutting token use up to 88%(12 posts)→

Original post →

More from Multimodal

Multimodal channel →