Expired50% confidenceFactExact time
OpenAI supports automatic prefix caching with a discount of approximately 50%.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
8/20/2026
First Seen
Valid until: 9/3/2026(expired)
Sources
Related Claims
UnverifiedThe prompt caching feature introduced by Anthropic and OpenAI operates on the server side, offering a 50–90% price discount for content with identical long prefixes.76% similarUnverifiedCalling APIs on a pay-per-use basis through APIs typically saves more than 50% in costs compared to subscribing to multiple AI services separately.73% similarUnverifiedOpenAI has introduced a prompt cache breakpoint mechanism that allows developers to manually specify cache breakpoints, with cache-hit portions typically billed at a discounted rate of 10%–25% of the original price.72% similarVerifiedOpenAI Prompt Caching can reduce the cost of repeated prefixes to 10%–25% of the original price.69% similarUnverifiedCache hits can be billed at approximately a 50% discount, while other items such as cache reads remain unchanged.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/778906API
curl https://kongchang.com/api/v1/knowledge/claims/778906MCP
get_claim(id=778906)