processing 2-hour long videos used to mean massive token bills. not anymore !!! we are announcing agentic video understanding with Gemini today, that cuts token usage by up to 88% & reduces costs by up to 66% 🔥 another fun launch I got to work with the team. with this capability, you can ask complex questions & create needle-in-a-haystack search apps. for example, users can query multi-hour lectures or how-to guides and the model will dynamically scrub to the exact answer without wasting tokens.