Unverified50% confidenceFactExact time
In the three days of data, 97.6% of the tokens were cache reads.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/15/2026
First Seen
Valid until: 10/29/2026
Sources
Related Entities
Related Claims
UnverifiedIn memory note reading, looking only at the data after the change, the waste from tiered reading is only 1% compared with reading the whole file.72% similarUnverifiedIn an AWS sample application, across 28 calls reviewing the same document, CloudWatch recorded 196,680 tokens written to cache and 0 reads, because the cache point was placed after each entry's own instructions; after moving the cache point to after the document, the second entry immediately became a read of 4,624 tokens.65% similarUnverifiedA Strands user reported that a turn with 18 tool calls resulted in 0 cache reads and 134,082 tokens of cache writes.64% similarUnverifiedWithout RTK, tool output accounts for only 7% of non-model output, while cache reads account for 94% to 98% of total token usage.64% similarUnverifiedOn a 4-core 8-thread laptop in the eight-thread single-file scenario, cycles per read drop from about 2950 to about 725, and reads per second rise from 9.9 million to 10.4 million up to 30 million to 33 million.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1033182API
curl https://kongchang.com/api/v1/knowledge/claims/1033182MCP
get_claim(id=1033182)