Gemini 3.8 Flash adds agentic video timeline navigation on OpenRouter
- Source
- x.com
- Date
Gemini 3.8 Flash from @GoogleDeepMind is live on OpenRouter. At 3.7 Flash’s intro price, it beats its predecessor on every benchmark shown: coding, finance, legal, video, and science. Use it now: https://t.co/TQTNcIlfDW
Gemini 3.8 Flash also supports agentic video processing. Set processing: "agentic" on the video part and the model navigates the timeline itself instead of sampling every frame at a fixed rate. Works on earlier Gemini Flash models too. Learn more in our docs: https://t.co/xTwILx914Y
Context
Google DeepMind’s Gemini 3.8 Flash can navigate a video in response to a question through OpenRouter. The announcement describes an agentic processing mode that lets the model choose where to look along the timeline.
The video-input documentation explains that the model loads relevant frames, transcript and audio as needed. Developers select this mode by setting the video part’s processing field to agentic. It is intended for long videos or questions about particular moments; fixed-rate sampling remains an option for short clips where response time is the priority.
Checking sign-in…
Loading comments…