Unverified50% confidencePredictionExact time
By estimate, when an 8000-token document is split into 10 chunks (each with 100 tokens of context) and caching is used, each document costs about $0.003, i.e. about $0.38 per million document tokens; without caching it is about $1.17 per million tokens.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/15/2026
First Seen
Valid until: 1/13/2027
Sources
Related Entities
Related Claims
UnverifiedAccording to Anthropic's published prices (input $10, output $50, cache read $1, cache write $12.50 per million tokens), the example session in the article costs $16.88, of which cache reads account for 29.6%, cache writes 25.9%, fresh input 14.8%, and output 29.6%.79% similarUnverifiedEstimated on the median page, each delivery per page saves about 8,000 input tokens; at an illustrative price of about $1 per million input tokens, that is equivalent to saving about $8 per delivery per 1,000 pages.76% similarUnverifiedWallaby's per-million-token pricing is: input $2.70, cached input $0.27, output $13.50; the official list price is: input $3.00, cached input $0.30, output $15.00.76% similarUnverifiedUnder the same H100 configuration, the cost per million output tokens is about $0.22–0.23 under an 8-request concurrent load.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1034446API
curl https://kongchang.com/api/v1/knowledge/claims/1034446MCP
get_claim(id=1034446)