this is pure f**king gold
Anthropic basically hid a routing problem inside a pricing table, and once you model the loop properly, Opus 5.5 stops looking like the “2x model”
the trick is that old context gets cheap:
> 20K context: Opus is 1.88x Sonnet per turn
> 150K context: the gap falls to 1.49x
> 400K context: it drops again to 1.26x
cache reads cost the same $0.20 / 1M on both models, so the longer the session runs, the less the sticker price explains the real bill
then the routing starts to matter more than the model:
> clear task? keep it on Sonnet
> real check fails? escalate
> give Opus the failing state + useful files
> never drag the whole dead transcript across
because a 300K switch costs $1.50 just to rebuild cache
the same clean 20K handoff costs $0.10
and at 150K context, 30 Sonnet turns cost $1.76 while 20 Opus turns cost $1.75
so the expensive mistake isn’t choosing Opus
it’s making the wrong model stay in the loop for too long
price the path to “done,” not the logo on the model ↓
10K Followers 144 Followingfounder • entrepreneur • living & making money in AI ecosystem and sharing it with you ⚡️
AI safety external advisor at OpenАІ🧠
14K Followers 1K Following📚 AI dev 4y exp | FullTime AI/X | Two master's degrees in engineering and marketing | Become part of our big family of smart-users
14K Followers 1K Following📚 AI dev 4y exp | FullTime AI/X | Two master's degrees in engineering and marketing | Become part of our big family of smart-users