Day 16:

First reported Oct 21, 2026, 01:22 UTC

Source reports

Day 16: OpenAI just extended prompt caching in the API from the usual 30 minutes to an optional 12 hours. This means developers can reuse instructions, tools, and other context that a model has already processed, even when requests are hours apart, without having to process… — @TokenGremlin (X), Oct 21, 2026, 01:22 UTC

Excerpts are quoted from the linked sources, which own their text.