OpenAI API adds 12-hour prompt caching option alongside 30-minute default
OpenAIDevs · x · 2026-10-21
OpenAI's developer account announced a new 12-hour prompt caching option for the API, on top of the 30-minute default. Both TTLs can be mixed in one request: 12h for shared instructions, 30 minutes for newer conversation content. Per the docs, if you reuse the same context throughout the day, savings from repeated reuse can significantly outweigh the extra cost of 12-hour caching. Documentation is live on developers.openai.com, with Markdown versions available by appending .md to page URLs.
Related event: OpenAI API Adds 12-Hour Prompt Caching Option(2 posts)→
More from Infra
- Pichai: everyone is massively short on AI compute — 'everyone wishes you had two times what you had planned' — firstadopter · 2026-10-21
- Stanford CS336 Lecture 6: fused Triton kernels cut softmax memory traffic ~4x — stanfordnlp · 2026-10-21
- General Compute partners with Positron AI: Atlas memory-centric hardware ships Q1 2027 — aftahi_ai · 2026-10-21
- AI bond issuance hits $419B in 2026, up 90% from all of 2025 — SumitGup · 2026-10-21
- AI Obsession Is Making Enterprises Neglect Cloud FinOps, Expert Warns — DavidLinthicum · 2026-10-21
- DeepSeek bottleneck is compute, not demand: 1GW cluster could train a far stronger model, says leak account — teortaxesTex · 2026-10-21