Gemini API adds agentic video understanding for three Gemini models
Original titleSeptember 1, 2026
AISummary
Google released agentic video understanding for Gemini 3.7 Flash, Gemini 3.6 Flash, and Gemini 3.5 Flash-Lite across the Interactions and GenerateContent APIs. The model dynamically navigates video timelines, requesting transcripts, frames, or audio tracks on demand. The source says this approach uses up to 88% fewer tokens for long-form content than static processing.
AIWhy it matters
The changelog names the affected models and API surfaces, and states a token-use figure that helps developers judge the cost of long video workloads.
Source: Gemini API Changelog · ai.google.devPublished · added here