谷歌出了 Gemini 3.6 Flash，更聪明还更省 token，价格也降了，实测效果不错，有官方指南可以照着用。
Google 正式发布 Gemini 3.6 Flash，该模型在智能、token 效率和定价上均有显著改进。开发者 patloeber 实测后表示，3.6 Flash 相比前代更高效、更快速。官方同时发布了详细的开发指南，帮助开发者快速上手。新模型基于开发者反馈优化，适用于真实场景。
been building with 3.6 Flash over the last couple of weeks, and it's noticeably better and more toke...
been building with 3.6 Flash over the last couple of weeks, and it's noticeably better and more token efficient (and thus also often faster)⚡️ we wrote a dev guide with all the details: ai.google.dev/gemini-api/doc… Logan Kilpatrick @OfficialLoganK Say hello to Gemini 3.6 Flash, designed to be higher intelligence, more token efficient, and with a new lower price, based directly on developer feedback! 3.6 Flash continues our progress towards models that are deeply usable in real world scenarios! 🔗 View Quoted Tweet 💬 0 🔄 0 ❤️ 3 👀 426 📊 1 ⚡