OpenAI revamps prompt caching for GPT-6
OpenAI revamped prompt caching for GPT-6 — the cache lifetime was extended to 30 minutes, and cached input tokens get a discount of up to 90%. It also released explicit cache breakpoints; configuration_update, which keeps the cache from breaking when reasoning effort is changed mid-conversation; a feature that keeps the cache even when the tool list changes via allowed_tools; cache warming; and a dashboard and diagnostic tools showing hit rates and the causes of misses. In cases cited by the company, GitHub Copilot cut newly processed tokens by more than 50%, and one partner raised its hit rate from 83% to 91%, cutting inference costs by 36%
Why it matters
A change that brings to the API surface the fact that the cost of long-running agent loops depends on cache design. Taking tool-list changes and reasoning-effort adjustments off the list of reasons for cache invalidation means that agents running for hours in a single session, swapping tools in and out, are recognized as a first-class usage pattern
Source — Primary sources first; secondary reports are labelled “Press”
Officialopenai.comhttps://openai.com/index/better-prompt-caching-for-gpt-6/Added in Week 40, 2026 · See that week