Unverified50% confidenceFactExact time
Prompt Caching可将公共前缀的KV Cache持久化存储，成本可降至普通输入的10-20%
1
Sources
50%
Confidence
Long-term
Relevance
8/24/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedBy reusing prefix KV Cache, Prompt Caching can reduce latency by approximately 85% and costs by approximately 90%, using Anthropic's pricing as a reference.79% similarVerifiedOpenAI Prompt Caching can reduce the cost of repeated prefixes to 10%–25% of the original price.76% similarUnverifiedThe Prompt Caching mechanism can reuse the KV Cache of identical prefix contexts, typically reducing input token costs by 50%–90%.74% similarUnverifiedAnthropic's prompt caching feature reduces the input token cost for cache hits to 10% of the original price73% similarVerifiedAnthropic的Prompt Caching功能允许将重复出现的长上下文缓存在服务端，缓存token的计费价格仅为标准输入价格的10%72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/795538API
curl https://kongchang.com/api/v1/knowledge/claims/795538MCP
get_claim(id=795538)