Dossier Patrick's news
pm7.news EST. 2026
laden
← Overzicht

Gemini adds agentic video understanding

· opgehaald 19:15

Samenvatting

Google turned on agentic video understanding in Gemini 3.7 Flash, 3.6 Flash, and 3.5 Flash-Lite so the model scans only the frames, audio, and transcript it needs. It says that cuts token use up to 88% and cost up to 66% versus static FPS ingest; the mode is live in the Gemini API, AI Studio, and Gemini Enterprise Agent Platform.

Het verhaal

Google 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 to search and inspect target segments across frames, audio, and transcripts. Google reports up to 88% fewer tokens, 66% lower cost, and up to 7% higher quality on video-analysis benchmarks. Available today for uploads and YouTube via the Gemini API in Google AI Studio and the Gemini Enterprise Agent Platform (set API config to agentic).