Gemini API adds Agentic Video, cuts token use by 88%
RubenEVillegas · x · 2026-09-02
Google introduces "Agentic Video" in the Gemini API, a new method for processing long videos that reduces token consumption by up to 88% while increasing quality. This feature can be controlled on a per-video basis via the API and is available with newer models like 3.7 Flash.
More from Multimodal
- Five-year-old AI-generated sci-fi short 'Blightsight' resurfaces — generativist · 2026-09-02
- Atlas Reconstructs Berkeley Campanile from 10 Ground Images — petewoodbridge · 2026-09-02
- AI Video Generation Will Let Fans Patch Together Universes — generativist · 2026-09-02
- World Labs ships a new world model for 3D world generation — petewoodbridge · 2026-09-02
- An underrated alternative to Krea2 and Ideogram4: testing depth and spatial coherence — COMPLOGICGADH · 2026-09-02
- Higgsfield Launches Genjutsu: AI Video Transformation With Full Motion and Lip Sync — azed_ai · 2026-09-02