Unverified50% confidenceBenchmarkExact time
Without RTK, tool output accounts for only 7% of non-model output, while cache reads account for 94% to 98% of total token usage.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/29/2026
First Seen
Valid until: 12/28/2026
Sources
Related Entities
Related Claims
UnverifiedIn large model API call scenarios, cache hit rate refers to the reuse ratio of the KV Cache (key-value cache), where the model can directly read the attention key-value pairs of already-processed tokens from the cache.63% similarUnverifiedIn a well-designed memory system, the information injected into the context typically occupies only 30%–50% of the total context window capacity.63% similarUnverifiedThe read-to-write ratio in short URL systems is typically around read:write = 100:1.61% similarUnverifiedAcross more than 355 sessions on Theo's machine, only 19 had ever opened a certain memory file, yet 80 sessions had written to or edited memory, resulting in a write-to-read ratio of 3:1.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/957970API
curl https://kongchang.com/api/v1/knowledge/claims/957970MCP
get_claim(id=957970)