Google DeepMind is rolling out agentic video understanding to its latest Gemini models, which reason over transcript, audio, and frames and dynamically adjust frame rate instead of scanning entire files. Accuracy improves while using up to 88% fewer tokens, with the largest gains on long-form content. The feature is live via API for Gemini 3.7 Flash, 3.6 Flash, and 3.5 Flash-Lite in Google AI Studio.

Key Takeaways

  • ✓Agentic frame selection replaces full-file scans, cutting tokens by up to 88%
  • ✓Gemini reasons jointly over transcript, audio, and frames with dynamic frame-rate control
  • ✓Rolling out now to 3.7 Flash, 3.6 Flash, and 3.5 Flash-Lite via Google AI Studio API
⚡

Key Decision Metrics at a Glance

TL;DR Verdict
🏆 Benchmark RankRank
Agentic frame selection replaces full-file scans, cutting tokens by up to 88%
Full Leaderboard→
💰 Cost & PlansCompare
in: $0.75 / out: $3.75
Compare Plans↗
🛠️ Ecosystem & IDERules
AI · LLM · Multimodal
Setup IDE Rules↗
🧭

Turn your technical choice into a development budget

Compare 40 dev plans & simulate token costs vs $20/mo subscriptions

⚔️ Compare Model→💰 Compare plans & limits↗
Action HubReady to adopt this in production?

Benchmark side-by-side against alternatives, or calculate monthly token cost vs subscription break-even.

⚔️ Launch VS Compare→💳 View Plans↗
Up NextGoogle DeepMind Adds Agentic Video Understanding to Gemini, Cutting Tokens up to 88%
Read Now→