Unverified50% confidenceFactExact time
On most Claude models, Anthropic bills cache reads at 0.1× the base input price; default 5-minute cache writes at 1.25×; 1-hour cache writes at 2×; and a 5-minute cache entry is refreshed for free each time it is used.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/12/2026
First Seen
Valid until: 1/10/2027
Sources
Related Entities
Related Claims
VerifiedThe 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.78% similarUnverifiedClaude's prompt caching is an optimization mechanism provided by Anthropic at the API level, where the price of cached read tokens is approximately one-tenth that of regular input tokens.73% similarUnverifiedA Prompt Caching cache hit read costs only 0.1 times the base input price, while the initial write cost is 2 times the regular input price.72% similarUnverifiedOpenAI's official example shows that one write plus nine full reads totals 2.15× the prefix input price, compared to 10× without caching.69% similarUnverifiedThe cost of cache reads should, by industry convention, be approximately one-tenth that of regular input tokens.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1002837API
curl https://kongchang.com/api/v1/knowledge/claims/1002837MCP
get_claim(id=1002837)