[OpenAI API Introduces 12-Hour Prompt Caching, Permanent Cache Retention for Codex and Work Logged-In Users] According to OpenAI Developers, the OpenAI API now supports 12-hour prompt caching. Developers can cache shared instructions, tools, and context for a longer duration, allowing requests made hours apart to be billed at a lower cached input rate. This feature is primarily aimed at agents that run continuously and reuse context throughout the day. Tibo (@thsottiaux) further added that the cache for logged-in users of Codex and Work will be retained permanently. Users returning to old conversations or resuming after a few hours can hit the cache without incurring additional costs.