# OpenAI API adds 12-hour prompt caching option

OpenAI · 2026-10-20 · Capability update

> OpenAI added a 12-hour prompt caching option in the API so persistent agents can keep shared instructions, tools and context cached longer at the lower cached-input rate.

This update bears on 2 kinds of work in 1 market. Highest level accepted: L1 Assisted.

## The work it bears on

- [Implement tool use and agent workflows](https://surviagi.com/work/software-intelligent-systems-agent-workflows) (Model applications and agent systems): L1 Assisted · From the publisher only
- [Integrate models retrieval and context flows](https://surviagi.com/work/software-intelligent-systems-model-integration) (Model applications and agent systems): L1 Assisted · From the publisher only

## Published at

- [Source 1](https://x.com/OpenAIDevs/status/2112603916076781778)

---

Page: https://surviagi.com/updates/ev-b3a389a2e56192e78945c5885395945bc306ab12

Data generated 2026-10-21T04:03:52.433156+00:00; method activity-level-1; ontology 2.4.0.
Machine-proposed: no person has reviewed these readings, and the method is not calibrated.
Cite the page address together with the generation time.