精选理由
3.5 Flash-Lite跑到350 tokens/秒，延迟敏感UI和智能体场景体验更好，速度提升明显。
3.5 Flash-Lite 达到近350输出tokens每秒的速度。该速度使其在延迟敏感的UI体验中非常流畅。它现在也成为驱动智能体（agent harness）的可行选项。
原文 · Logan Kilpatrick
3.5 Flash-Lite runs at nearly 350 output tokens per second which feels so smooth on many latency sen...
3.5 Flash-Lite runs at nearly 350 output tokens per second which feels so smooth on many latency sensitive UI experiences and is now also a viable option to drive agent harnesses! 💬 7 🔄 3 ❤️ 55 👀 3777 📊 11 ⚡