Gemini API新增智能体视频理解，能自主分析长视频，大幅降低成本并提高准确率。
Gemini 3.7 Flash、3.6 Flash和3.5 Flash Lite模型现已支持智能体视频理解功能。该功能可迭代导航视频时间线，自主选择观看内容、帧率和所需信息类型。在长视频处理中，可减少88%的token数量和66%的成本，并在基准测试中提高约7%的准确率。用户可通过设置processing="agentic"启用此功能。
Gemini video understanding is now agentic. Gemini can now iteratively navigate video timelines, deci...
Gemini video understanding is now agentic. Gemini can now iteratively navigate video timelines, decide watch what, pick frame rates, or chooses whether it needs speech transcripts, audio, or visual frames to answer your prompt. Result: Long videos get up to 88% fewer tokens and 66% lower costs, with ~7% higher accuracy on benchmarks. How it works: - Receives a lightweight URI reference (Files API or YouTube) and loads content via tool. - Scans speech transcripts to pinpoint relevant moments before fetching visual frames. - Navigates key timestamps and picks its own frame rate (0.1 or 10 FPS). - Pulls audio tracks directly when acoustic cues matter. Set `processing="agentic"`on `video` to enable. Keep `static` (none) for videos under 2 minutes. Available today in the Gemini API and Google AI Studio across Gemini 3.7 Flash, 3.6 Flash, and 3.5 Flash Lite. ai.dev/learn/agentic-… 💬 1 🔄 1 ❤️ 29 👀 1450 📊 6 ⚡