Unverified50% confidenceBenchmarkExact time
RunInfra claims that its session-aware routing can achieve a cache hit rate of up to 99.5%; this figure is the vendor's claimed upper limit, and the actual hit rate depends on usage patterns.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/20/2026
First Seen
Valid until: 1/18/2027
Sources
Related Entities
Related Claims
UnverifiedIn long-running agentic conversation scenarios, more than 90% of input tokens are billed at the cache price.63% similarUnverifiedContext caching mechanisms can reduce API costs by 60%–80% for enterprise applications that repeatedly query the same knowledge base, with some providers offering cache-hit token discounts as high as 90%.62% similarUnverified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61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1075736API
curl https://kongchang.com/api/v1/knowledge/claims/1075736MCP
get_claim(id=1075736)