Google introduces agentic video understanding for Gemini models
Google has launched an agentic video processing feature for selected Gemini models.
2 min read·Wednesday, 2 September
Google introduction graphic for agentic video understanding in Gemini models.
Google has introduced an agentic video understanding feature designed to improve how models process visual media. Available across Gemini 3.7 Flash, 3.6 Flash, and 3.5 Flash-Lite, the new capability shifts away from traditional static frame ingestion toward a dynamic, goal-directed inspection method.
Internal benchmarks displaying token consumption reduction and accuracy improvements across Minerva, 1H-VideoQA, and LVBench. · Source ↗
How agentic processing works
Traditional video analysis typically relies on ingesting media at a fixed frame rate, such as one frame per second. This static approach forces developers to choose between high token consumption or missing important visual details.
By contrast, agentic video understanding pairs the model's core reasoning with native video tools. The model actively determines what to watch, adjusts its speed, and selectively queries visual frames, audio tracks, or transcripts. This allows the system to fetch only the specific moments and signals required for a given query.
Performance and benchmarks
According to internal benchmarks, the new feature yields notable efficiency gains, particularly for long-form content ranging from ten-minute guides to multi-hour recordings.
Token consumption is reduced by up to 88 percent.
Analysis costs decrease by up to 66 percent.
Overall accuracy improves by up to 7 percent.
Among the supported models, Gemini 3.7 Flash delivers the optimal combination of quality and cost efficiency, positioning it at the accuracy-to-cost pareto frontier for video tasks.
Capabilities and availability
The capability enables several advanced use cases, including sub-second moment retrieval for precise video editing, long-form needle-in-a-haystack searches, and detailed anomaly detection through dynamic resampling.
Developers can access the feature today via the Gemini API in Google AI Studio and the Gemini Enterprise Agent Platform by configuring the processing parameter to agentic. Google also plans to integrate the technology into consumer products, including the Gemini app and YouTube's Ask YouTube feature.
Gemini Spark: Autonomous AI Agent Setup & Master BlueprintFree guide
Comments