Unverified50% confidenceFactExact time
KV Cache技术可复用历史Token的注意力计算结果，部分厂商对命中缓存的Token给予标准价格10%-50%的折扣
1
Sources
50%
Confidence
Long-term
Relevance
7/21/2026
First Seen
Sources
Related Claims
UnverifiedThe Prompt Caching mechanism can reuse the KV Cache of identical prefix contexts, typically reducing input token costs by 50%–90%.80% similarUnverifiedAnthropic 的提示词缓存机制基于 KV Cache，可使匹配前缀的输入 token 费用降低约 90%75% similarUnverifiedThe API cache hit mechanism allows input tokens that have already been sent to enjoy discounted pricing on repeated calls, typically at 10%–50% of the original price.68% similarUnverifiedBy reusing prefix KV Cache, Prompt Caching can reduce latency by approximately 85% and costs by approximately 90%, using Anthropic's pricing as a reference.68% similarUnverifiedBoth OpenAI and Anthropic have launched Prompt Cache functionality that can reuse KV Cache, manifesting for callers as a token cost discount (typically 50%–90%)66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/582164API
curl https://kongchang.com/api/v1/knowledge/claims/582164MCP
get_claim(id=582164)