AI 导读
OpenAI 宣布 API 现可选择 12 小时 prompt caching。共享指令、工具和上下文可缓存更久，即使请求间隔数小时也按更低的 cached-input 费率计费，适合 dots 这类全天复用上下文的持续型 Agent。
正文
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.
来源：OpenAI Developers · x.com