DeepMind adds agentic video understanding to Gemini: 88% fewer tokens, 66% cheaper
petrusenko_max · x · 2026-09-03
Google DeepMind announced agentic video understanding for Gemini. It dynamically searches across frames, audio, and transcripts, cutting tokens by up to 88%, lowering cost by 66%, and improving accuracy by 7%. It enables sub-second retrieval, anomaly detection, and precise counting. Available on Gemini 3.7 Flash, 3.6 Flash, and 3.5 Flash-Lite at no extra fee — just enable "agentic" processing.
More from Models
- Running Ling 3.1 Flash (560B MoE, 25B Active) Across 4 DGX Sparks via llama.cpp RPC — BerryBlush_Rogers691 · 2026-10-18
- Users press OpenAI on long-delayed Adult Mode a year after it was promised — ___Patrice___ · 2026-10-18
- Polymarket opens betting market on who releases the next Gemini Argon model — Polymarket · 2026-10-18
- Grok matter-of-factly lists which groups user was racist against, exempting Africans and Latin Americans — teortaxesTex · 2026-10-18
- A quick test for benchmaxxed demos: swap in Mirror's Edge and see if it generalizes — teortaxesTex · 2026-10-18
- Did OpenAI distill DeepSeek's gains? Benchmark shows OpenAI's Luna scoring just 38 — teortaxesTex · 2026-10-18