Google 为 Gemini 推出智能体视频理解，Token 使用量最高减少 88%
Google 为最新 Gemini 模型推出智能体视频理解能力。该功能可动态检索长视频，在公司公布的基准测试中最多减少 88% 的 token 使用量，并提升视频分析准确率。
Google 表示，智能体视频理解现已覆盖 Gemini 3.7 Flash、3.6 Flash 和 3.5 Flash-Lite。与按固定帧率处理视频的传统方式不同，该能力会结合模型推理和原生视频工具，动态决定需要检查的片段，并利用画面、音频和转录内容寻找答案。
官方称，该功能在测试中最多可减少 88% 的 token 使用量、降低 66% 的分析成本，并将准确率提高 7%。它支持通过 Gemini API 在 Google AI Studio 中处理上传的视频和 YouTube 视频，也可通过 Gemini Enterprise Agent Platform 使用；这些指标是公司公布的最高测试结果，实际效果会因任务而异。
来源证据
Introducing agentic video understanding with Geminiblog.google · supportingToday, we’re launching 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, 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. The feature is available today for video uploads and YouTube videos via the Gemini API in Google AI Studio and the Gemini Enterprise Agent Platform. ## Benchmarks [...] ## Benchmarks Unlike 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,
Google Adds Agentic Video Understanding to Gemini, Claiming 88% Lower Token Use | Superpower Dailysuperpowerdaily.com · supportingGoogle is giving Gemini a new way to watch video: instead of sampling frames at a fixed rate, it can decide which moments to inspect, and whether frames, audio, or transcripts contain the answer. The feature, called agentic video understanding, is available now through the Gemini API for uploaded and YouTube videos. Google says it cut token use by as much as 88 percent, reduced analysis cost by up to 66 percent, and improved accuracy by up to 7 percent on standard video-analysis benchmarks. Those are company-reported results, so they indicate tested performance—not a guarantee for every task. The supported models are Gemini 3.7 Flash, 3.6 Flash, and 3.5 Flash-Lite. Developers turn the setting on in Google AI Studio or the Gemini Enterprise Agent Platform, with standard Gemini API pricing [...] Google has launched agentic video understanding for Gemini 3.7 Flash, 3.6 Flash and 3.5 Flash-Lite. The feature lets the models search selected parts of a video, using images, audio and transcrip
We're launching agentic video understanding across our latest modelsfacebook.com · supportingAvailable via Gemini Enterprise Agent Platform, this new capability improves accuracy while cutting token consumption up to 88% and reducing
Google DeepMind's Post - LinkedInlinkedin.com · supportingWe're bringing agentic video understanding to our latest Gemini models. They can now analyze videos with better accuracy while using up to 88%
Google on X: "With agentic video understanding, developers can dynamically search, scan, and inspect long-form video with up to: 📉 88% fewer tokens 📉 66% lower cost ✅ 7% better accuracy" / Xx.com · supportingLog inSign up ## Post # Google on X: "With agentic video understanding, developers can dynamically search, scan, and inspect long-form video with up to: 📉 88% fewer tokens 📉 66% lower cost ✅ 7% better accuracy" @Google Google @Google With agentic video understanding, developers can dynamically search, scan, and inspect long-form video with up to: 📉 88% fewer tokens 📉 66% lower cost ✅ 7% better accuracy Scatter plot titled 5:30 PM · Sep 1, 202641KViews 6 @Google Google @Google Sep 1 We’re introducing a new capability to our latest Gemini models: agentic video understanding. This allows developers to process long-form video content with more accuracy, while using up to 88% less tokens. See how it works 🧵 00:00 199 @Google Google @Google Sep 1 [...] 6 @Google Google @Google Sep 1 Agentic video understanding is available now across our latest models via the Gemini API in @GoogleAIStudio and the Gemini Enterprise Agent Platform.
Introducing agentic video understanding with Gemini | Google AI Studio (@GoogleAIStudio) on Xx.com · supportingToday, we’re launching 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, 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. The feature is available today for video uploads and YouTube videos via the Gemini API in Google AI Studio and the Gemini Enterprise Agent Platform. Benchmarks [...] Benchmarks Unlike 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,