Google adds agentic video understanding to Gemini 3.7 Flash, 3.6 Flash and 3.5 Flash-Lite
Original titleIntroducing agentic video understanding with Gemini
AISummary
Google AI Studio says agentic video understanding is now available across Gemini 3.7 Flash, 3.6 Flash and 3.5 Flash-Lite via the Gemini API. The company reports cost reductions of up to 66%, token consumption reductions of up to 88% and accuracy gains of up to 7% on standard video benchmarks.
Developers enable it by setting processing to "agentic" in the API configuration, at standard token pricing.
AIWhy it matters
The source gives concrete cost and token figures and explains how the agentic loop replaces fixed-rate frame ingestion, helping developers weigh it against their current video pipelines.
Source: Google AI Studio · x.comPublished · added here