Tools #OpenAI Oct 21, 2026 · Originally published Oct 20

OpenAI adds 12-hour prompt caching to the API, with writes at 2.5x the input price

Cache lifetime stretches from the default 30 minutes to 12 hours, so requests hours apart still get cached-input pricing, at a higher write cost.

Primary source OpenAI developer changelog · developers.openai.com Read the original ↗

// Key points

The Responses API can now use 12-hour prompt caching, keeping shared instructions, tools and context cached longer so requests hours apart still get lower cached-input pricing.
12-hour cache writes cost 2.5x the input token price; default 30-minute writes cost 1.25x.
One request can set both 12-hour and 30-minute breakpoints; upgrading existing 30-minute coverage to 12 hours is charged as a new 12-hour write, with no credit for the earlier one.

Builder's takeThis picks up from yesterday's Cloudflare item: cut cost through cache structure first. I'll pull out the system prompts PandaClaws reuses all day but with gaps longer than half an hour, put them before a 12-hour breakpoint, and keep session content on 30-minute breakpoints; work out from your own call spacing how many reuses a day a prefix needs before the 2.5x write pays off.

// Background · from #OpenAI

Full timeline →