{"slug": "introducing-agentic-video-understanding-with-gemini", "title": "Introducing agentic video understanding with Gemini", "summary": "Google launched agentic video understanding across Gemini 3.7 Flash, 3.6 Flash, and 3.5 Flash-Lite, reducing analysis costs by up to 66% and token consumption by up to 88% while improving accuracy by up to 7%. The feature is available via the Gemini API in Google AI Studio and the Gemini Enterprise Agent Platform.", "body_md": "# Introducing agentic video understanding with Gemini\n\nToday, we’re launching [agentic video understanding](https://ai.google.dev/gemini-api/docs/video-understanding#agentic-video-understanding) across our latest models: Gemini 3.7 Flash, 3.6 Flash and 3.5 Flash-Lite. This new capability improves accuracy while dramatically reducing token usage and costs for video analysis. Similar to [agentic vision](https://blog.google/innovation-and-ai/technology/developers-tools/agentic-vision-gemini-3-flash/), which combines code execution with Gemini models’ native image understanding, agentic video understanding uses Gemini’s native video tools to improve performance and unlock new capabilities for video processing like sub-second moment retrieval, more accurate anomaly detection, precise counting and more.\n\nThe feature is available today for video uploads and YouTube videos via the Gemini API in Google AI Studio and the Gemini Enterprise Agent Platform.\n\n## Benchmarks\n\nUnlike current ‘static’ processing, where the model ingests the video at a fixed frames-per-second rate (default 1 FPS, adjustable via API), agentic video understanding pairs the model’s core reasoning with native video tools to dynamically search, scan, and inspect target video segments across visual frames, audio, and transcripts. Across standard video analysis benchmarks, Gemini models with agentic video understanding **reduce analysis costs by up to 66% and token consumption by up to 88%, while improving accuracy by up to 7%.**\n\nThese efficiency gains are especially pronounced on long-form video (from 10-minute how-to guides to 90-minute lectures and multi-hour recordings), where static processing forces developers to choose between high token costs or techniques that drop critical details.\n\nActivating agentic video understanding drops token consumption by up to 88% and boosts accuracy by up to 7% with Gemini 3.7 Flash.\n\nWhile these gains span all three supported models, Gemini 3.7 Flash with agentic understanding offers the best possible quality overall and the best combination of quality and cost efficiency, putting it at the accuracy-to-cost pareto frontier among tested models for video understanding.\n\nUsing agentic video understanding places Gemini 3.7 Flash at the accuracy-to-cost pareto frontier for video analysis.\n\n## How it works\n\nInstead of static processing where the model ingests media streams at a fixed frame rate, agentic video understanding enables Gemini to take an active, goal-directed role in determining *what* to watch, at *what* speed, and through *which* modality (frames, audio, or transcript), fetching only the moments and signals needed. While developers could previously do this manually, with agentic video understanding, Gemini can accomplish it through an agentic loop, invoking an internal tool to load the relevant part of the video file, significantly reducing development overheads.\n\n## Capabilities and use cases\n\nAgentic video understanding transforms how developers can process long-form video content across a variety of demanding applications.\n\n**Sub-second moment retrieval**: Pinpoint split-second state changes and tight cut boundaries that are easily missed at 1 FPS, making precise automated video editing possible.**Long-form needle-in-a-haystack search**: Answer complex queries across multi-hour videos without consuming millions of tokens.** Anomaly detection**: Resample interesting time windows at higher FPS to inspect rapid motion and subtle visual artifacts.** Counting action & object**: Accurately track repeated physical movements and distinct objects over time.\n\n## Real-world results\n\nMany of our early access partners saw strong performance while testing with agentic video understanding. Here’s what they have to say:\n\n## Getting started\n\nAgentic video understanding is available via the Gemini API in [Google AI Studio](https://ai.google.dev/gemini-api/docs/video-understanding#agentic-video-understanding) and [Gemini Enterprise Agent Platform](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/capabilities/video-understanding), launching across Gemini 3.7 Flash, 3.6 Flash, and 3.5 Flash-Lite. It uses standard Gemini API token pricing with no additional feature fee.\n\nTo enable it, simply set processing to \"agentic\" in the API configuration. Read our [developer guide](http://ai.dev/learn/agentic-video-understanding-with-gemini) to get more insights into the feature and how to get started.\n\n``` python\nfrom google import genai\n\nclient = genai.Client()\n\ninteraction = client.interactions.create(\n    model=\"gemini-3.7-flash\",\n    input=[\n        {\n            \"type\": \"video\",\n            \"uri\": \"https://youtu.be/7Z5Vy9JBANs\",\n            \"processing\": \"agentic\"\n        },\n        {\n            \"type\": \"text\",\n            \"text\": \"What are the 3 most important announcements in this keynote?\",\n        },\n    ],\n)\n\nprint(interaction.output_text)\n```\n\nWe are also bringing the efficiency and quality improvements of agentic video understanding to billions of users across Google products. The feature will roll out to all users in the Gemini app across Flash and Flash-Lite models soon. And in the coming months, agentic video understanding will also power YouTube's ‘[Ask YouTube’](https://support.google.com/youtube/answer/14110396?hl=en&co=GENIE.Platform%3DAndroid) feature on the video watch page, leveraging Gemini to deliver higher-quality answers grounded in the visuals.\n\n*Acknowledgement for their contribution to this work:**Sergi Caelles, Filip Pavetić, Ahmet Iscen, Suhas Yogin, and the Agentic Vision team.*", "url": "https://wpnews.pro/news/introducing-agentic-video-understanding-with-gemini", "canonical_source": "https://deepmind.google/blog/introducing-agentic-video-in-gemini/", "published_at": "2026-09-01 17:08:51+00:00", "updated_at": "2026-09-01 17:24:51.412055+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-products", "ai-tools"], "entities": ["Google", "Gemini 3.7 Flash", "Gemini 3.6 Flash", "Gemini 3.5 Flash-Lite", "Gemini API", "Google AI Studio", "Gemini Enterprise Agent Platform"], "alternates": {"html": "https://wpnews.pro/news/introducing-agentic-video-understanding-with-gemini", "markdown": "https://wpnews.pro/news/introducing-agentic-video-understanding-with-gemini.md", "text": "https://wpnews.pro/news/introducing-agentic-video-understanding-with-gemini.txt", "jsonld": "https://wpnews.pro/news/introducing-agentic-video-understanding-with-gemini.jsonld"}}