做 AI 应用或负责成本优化的团队，这条关于模型路由的洞察直接关系到你的预算和架构选择——Coinbase 已经验证了在 token 使用暴增时成本可控的路径，值得参考。
Coinbase CEO Brian Armstrong 在 X 上分享了对模型路由趋势的看法，认为对智能的需求近乎无限，但未来 12-18 个月内，80% 的工作负载将运行在便宜 99% 的模型上，仅 20% 需要最新高端模型。他类比高端 MacBook 或游戏 PC 的配置比例，指出价格下降速度远超摩尔定律，因此瓶颈将是能源和算力而非模型本身。Coinbase 正积极将提示路由到更便宜的模型，在 token 使用量指数增长的同时保持成本基本持平。
Model routing is growing a lot these days
Model routing is growing a lot these days Brian Armstrong @brian_armstrong Good take My guess is - demand for intelligence is near infinite - but 80% of workloads will be running on 99% cheaper models within 12-18 months - 20% of workloads will still run on latest gen models where IQ maxing is important (scientific breakthroughs, higher level ochestrator agents?) - rough analogy might be what % of macbooks or gaming PCs sold have the maxed out specs for CPU/GPU, prices are falling much faster than Moore's law here though - this leads me to think the limiting factor will be energy and compute, not better models At Coinbase we're working hard on routing prompts to cheaper models where appropriate, and in some cases have been able to keep costs roughly flat, while token usage continues to grow exponentially. 🔗 View Quoted Tweet 💬 8 🔄 0 ❤️ 9 👀 810 📊 8 ⚡