Comment by george_max 12 hours ago This is just cache reads. In real usage it costs 15% more than Fable 5 -- all for marginal gains.https://artificialanalysis.ai/ 2 comments george_max Reply edg5000 5 hours ago Cache reads dominate in modern workflows (coding CLIs and modern web clients such as ChatGPT Work and Claude Cowork (web)). fastball 2 hours ago Output tokens are 5x more expensive than input tokens, so I'm not sure "dominate" is entirely correct.A conversation with 20 turns, 50k tok growth per turn, 1m tok context at end would price out like this:Fable 5 ($1/M cache reads) ; cache reads 9.5M tok × $1.00 = $9.50 ; cache writes 1M tok × $12.50 = $12.50 ; output 1M tok × $50 = $50.00 ; total = $72.00Fable 5.1 ($0.25/M cache reads) ; cache reads 9.5M tok × $0.25 = $2.38 ; cache writes 1M tok × $12.50 = $12.50 ; output 1M tok × $50 = $50.00 ; total = $64.88So yes, cheaper, but not massively.
edg5000 5 hours ago Cache reads dominate in modern workflows (coding CLIs and modern web clients such as ChatGPT Work and Claude Cowork (web)). fastball 2 hours ago Output tokens are 5x more expensive than input tokens, so I'm not sure "dominate" is entirely correct.A conversation with 20 turns, 50k tok growth per turn, 1m tok context at end would price out like this:Fable 5 ($1/M cache reads) ; cache reads 9.5M tok × $1.00 = $9.50 ; cache writes 1M tok × $12.50 = $12.50 ; output 1M tok × $50 = $50.00 ; total = $72.00Fable 5.1 ($0.25/M cache reads) ; cache reads 9.5M tok × $0.25 = $2.38 ; cache writes 1M tok × $12.50 = $12.50 ; output 1M tok × $50 = $50.00 ; total = $64.88So yes, cheaper, but not massively.
fastball 2 hours ago Output tokens are 5x more expensive than input tokens, so I'm not sure "dominate" is entirely correct.A conversation with 20 turns, 50k tok growth per turn, 1m tok context at end would price out like this:Fable 5 ($1/M cache reads) ; cache reads 9.5M tok × $1.00 = $9.50 ; cache writes 1M tok × $12.50 = $12.50 ; output 1M tok × $50 = $50.00 ; total = $72.00Fable 5.1 ($0.25/M cache reads) ; cache reads 9.5M tok × $0.25 = $2.38 ; cache writes 1M tok × $12.50 = $12.50 ; output 1M tok × $50 = $50.00 ; total = $64.88So yes, cheaper, but not massively.
Cache reads dominate in modern workflows (coding CLIs and modern web clients such as ChatGPT Work and Claude Cowork (web)).
Output tokens are 5x more expensive than input tokens, so I'm not sure "dominate" is entirely correct.
A conversation with 20 turns, 50k tok growth per turn, 1m tok context at end would price out like this:
Fable 5 ($1/M cache reads) ; cache reads 9.5M tok × $1.00 = $9.50 ; cache writes 1M tok × $12.50 = $12.50 ; output 1M tok × $50 = $50.00 ; total = $72.00
Fable 5.1 ($0.25/M cache reads) ; cache reads 9.5M tok × $0.25 = $2.38 ; cache writes 1M tok × $12.50 = $12.50 ; output 1M tok × $50 = $50.00 ; total = $64.88
So yes, cheaper, but not massively.