Unverified50% confidenceFactExact time
For this architecture, the cached bytes per token is not a constant; the equivalent bytes/token of the window layers alone is about 688.0 at a context of 8,192, about 43.0 at 131,072, and about 5.4 at 1,048,576.
1
Sources
50%
Confidence
Long-term
Relevance
10/18/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn computer use, the system prompt adds 466–499 tokens, each tool definition adds 735 tokens, and each screenshot consumes roughly 2,000–5,000 tokens.77% similarUnverifiedA Strands user reported that a turn with 18 tool calls resulted in 0 cache reads and 134,082 tokens of cache writes.74% similarUnverifiedThe hosted-side usage across the 400 cases totals 1,222,211 tokens (290,606 input, 931,605 output), i.e. 3,055.5 tokens per case.73% similarUnverifiedWhen performing text classification on CPU, a chunk size of 256 or 512 tokens generally outperforms an 8192 large window.72% similarUnverifiedBefore the fix, the cache reads for messages 2 and 3 were 0, with cache writes of about 19,600 tokens per message.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1061812API
curl https://kongchang.com/api/v1/knowledge/claims/1061812MCP
get_claim(id=1061812)