Calculator
Every multiple in the directory rests on an assumption about how much you use a thing. Yours is different. Put your own numbers in.
Recompute this for your own usage
Scaling assumes your usage has the same shape as ours, just more or less of it. If your mix is different — far more output than input, say — the estimate drifts. It is an estimate either way.
What this does and does not do
It scales our usage assumption up or down and recomputes the estimate against the same rate card. That answers "what if I use it twice as much" honestly.
It does not know the shape of your usage. If your mix differs from ours — far longer outputs, much shorter context — the estimate drifts, and no percentage in the box above fixes that. The per-product pages state each assumption in plain language so you can see how far from you it is.
Nothing you type here leaves your browser. There is no analytics on this page, or any other page — seestats for what is counted and how.