Unverified50% confidenceBenchmarkExact time
Before the fix, the cache reads for messages 2 and 3 were 0, with cache writes of about 19,600 tokens per message.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/18/2026
First Seen
Valid until: 11/1/2026
Sources
Related Entities
Related Claims
UnverifiedA Strands user reported that a turn with 18 tool calls resulted in 0 cache reads and 134,082 tokens of cache writes.74% 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.70% similarUnverifiedIn the same measurement, of Claude Code's 277.5 million tokens, only about 3,000 were brand-new input, about 264 million were cache reads, about 10.8 million were cache writes, and about 1.8 million were output, with more than 95% of the token volume coming from cache reads.69% similarUnverifiedIn the three days of data, 97.6% of the tokens were cache reads.69% similarUnverifiedUsing Claude Haiku 4.5 on Amazon Bedrock, after the fix the cache reads for messages 2 and 3 were both 18,767 tokens, with cache writes of 597 and 620 tokens respectively.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1057706API
curl https://kongchang.com/api/v1/knowledge/claims/1057706MCP
get_claim(id=1057706)