Opus 5.5 is 20% cheaper per input and output token than Opus 5, and 60% cheaper on cache reads. So what does that actually do to the cost of a task in Claude Code?
We ran the numbers, and built a calculator so you can run yours from /usage:
https://t.co/WUqoFoecW3
token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
Why it matters
Gives Claude Code users a direct way to estimate how Opus 5.5's 20% cheaper tokenThe chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.Full definition → and 60% cheaper cache reads change their own task costs, via the /usage calculator.
