# OpenAI API adds a 12-hour prompt caching option



OpenAI



OpenAI announced 12-hour prompt caching for its API on October 20, 2026, at 17:56 UTC \(01:56 Beijing time on October 21\). Developers can reuse shared instructions, tools and context at the lower cached-input rate even when requests are hours apart. They can retain the 30-minute default or combine both durations in one request, using 12 hours for shared instructions and 30 minutes for newer conversation content. Longer caching carries an extra cost; OpenAI says repeated reuse throughout the day can more than offset it. The announcement does not specify pricing.

- Review updated: Oct 21, 2026 09:43 Wed · Beijing Time (UTC+8)

## Sources

- Source excerpt: https://x.com/OpenAIDevs/status/2112603916076781778
- Source excerpt: https://x.com/OpenAIDevs/status/2112603918522105890

Canonical entry: https://www.ailyre.com/source/?id=openai-api-12h-prompt-caching-2026-10-20&lang=en