Unverified50% confidenceFactExact time
Prompt Caching在提示词前缀完全相同且超过约1024 token阈值时命中，缓存token通常按原价的25%甚至更低计费
1
Sources
50%
Confidence
Long-term
Relevance
7/18/2026
First Seen
Sources
Related Claims
UnverifiedOpenAI launched the Prompt Caching feature in 2024; when the prompt prefix is completely identical and exceeds the 1,024-token threshold, the KV Cache is reused, and the cached portion is typically billed at 25% of the original price or even lower.79% similarUnverifiedAnthropic's Prompt Caching requires that prefix content be byte-for-byte identical and meet a minimum length threshold of approximately 1,024 tokens, delivering approximately a 90% token discount.77% similarUnverifiedPrompt Caching is a server-side optimization mechanism introduced by Anthropic in 2024, achieving approximately 90% token discounts, requiring the prefix bytes to be completely identical and meeting a minimum length threshold of approximately 1024 tokens.76% similarUnverifiedAnthropic's Prompt Caching feature grants a discount on the corresponding tokens if the fixed prefix portion of a request can reuse the cache.75% similarUnverifiedThe Prompt Caching mechanism can reuse the KV Cache of identical prefix contexts, typically reducing input token costs by 50%–90%.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/552340API
curl https://kongchang.com/api/v1/knowledge/claims/552340MCP
get_claim(id=552340)