# Live news

Canonical: https://ournews.ai/live/18968037-35c9-49f6-b9fc-622ed61d8262
Published: 2026-10-21T01:42:05.323124+00:00
Updated: 2026-10-21T01:42:05.323124+00:00

OpenAI adds 12-hour API prompt caching, with cache writes at 2.5× the input-token price; Tibo says logged-in Codex and Work users now keep caches indefinitely when resuming conversations.

Source: Thibault Sottiaux; OpenAI API changelog — https://x.com/thsottiaux/status/2112712984644784534
Source date: 2026-10-21T01:10:02Z