Unverified50% confidenceBenchmarkExact time
In one long conversation of 36 turns with approximately 1.78 million tokens, the full-retention configuration was actually the cheapest because 97% of the tokens hit the cache.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/11/2026
First Seen
Valid until: 12/10/2026
Sources
Related Entities
Related Claims
Unverified在1.78百万token的长会话实测中，因为97%的token被缓存，发送token最多的配置反而最便宜80% similarUnverifiedAnthropic has reduced the price of cache reads by 75%, now costing only $0.25 per million tokens.68% similarUnverifiedIn the cache hit mechanism, a lower fee is charged for the cached portion, typically 10–25% of the original price.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/901138API
curl https://kongchang.com/api/v1/knowledge/claims/901138MCP
get_claim(id=901138)