Unverified50% confidenceFactExact time
Cached input refers to pre-storing the same context on the server side so that subsequent requests can reuse the cache without repeated computation, and is billed at a lower price.
1
Sources
50%
Confidence
Long-term
Relevance
9/30/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedAnthropic的Prompt Caching功能对请求中的固定前缀部分若能复用缓存，则对相应Token给予折扣76% similarUnverifiedSome service providers have introduced cache-hit pricing, charging at a lower discounted rate when repeated long system prompts hit the cache.72% similarUnverifiedThe cache read mechanism retains the KV cache for recurring long prompt prefixes, charging at an extremely low rate upon a cache hit; the leaked cache read price for Opus 5.5 is approximately 1/20 of the input price.70% similarUnverifiedBatch processing bundles large numbers of requests for submission, processes them asynchronously on the server side, and returns results collectively, usually accompanied by more favorable pricing.70% similarUnverifiedCached input tokens typically enjoy a discount of 25%–50% off the original price, as there is no need to recompute embeddings and attention weights—only the precomputed KV vectors need to be loaded from cache.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/961322API
curl https://kongchang.com/api/v1/knowledge/claims/961322MCP
get_claim(id=961322)