Tibo· @thsottiaux · X·· 4 小时前精选AI 评分67
AI 导读
OpenAI 宣布 API 现已支持 12 小时提示缓存，间隔数小时的请求也能以更低的缓存输入价格复用共享指令、工具和上下文。对 Codex 与 Work 的登录用户，缓存永久保留，回到旧对话或数小时后恢复会话都能保证命中缓存且无额外代价。
推荐理由
原文给出 API 12 小时缓存与 Codex、Work 用户永久缓存的具体变化，可据此评估长间隔请求的成本影响。
正文 · 原文
Day 16/
You can now cache for 12h in the API and for logged in users across Codex & Work we keep cache forever and you don’t have any penalty for coming back to an old conversation or resuming after a few hours and are now guaranteed to hit the cache.
You can now choose 12-hour prompt caching in the API. Persistent agents, like dots, reuse context throughout the day. You can keep shared instructions, tools, and context cached longer and pay the lower cached-input rate, even when requests are hours apart.在 X 查看被引用的帖子
来源：Tibo · x.com