Google DeepMind has introduced Agentic Video for the Gemini API, a new method for processing long videos that can reduce token consumption by up to 88% while improving output quality. The feature offers per-video control within the API and is already available in the latest models, including Gemini 3.7 Flash. This update provides developers with a more efficient way to handle video AI tasks, reducing costs and enhancing performance. The feature is now accessible via the API and can be used with models like Gemini 3.7 Flash.
Google DeepMind just rolled out Agentic Video for the Gemini API, a fresh way to handle long videos that can cut token use by as much as 88% while also lifting output quality. And yes, it’s simple to control for each video inside the API. It’s already live in the newest models, including Gemini 3.7 Flash.
This article was originally published by Bit.Fan. For more cryptocurrency news and market insights, visit www.bit.fan. Disclaimer:
The market information, project data, and third-party content displayed on this platform are for industry information sharing only and do not constitute any form of investment advice or return commitment.
Cryptocurrency trading carries high risks. Users should fully assess their risk tolerance and make independent decisions. All profits, losses, and legal responsibilities are borne by the users themselves.
