fraction

The passage around this formula

Image and video inputs are priced by tokenization rules that are public, mechanical, and different enough across vendors that a workload’s cost cannot be estimated from a single provider’s numbers and assumed to generalise. The general form, common to every tiling or patch-based image tokenizer, is $T(w, h) = \left\lceil \frac{w}{P} \right\rceil \times \left\lceil \frac{h}{P} \right\rceil$. where w and h are the image’s pixel dimensions after any provider-side resize and P is that provider’s patch edge length in pixels. The formula is the same shape everywhere; the constant P , the resize rule applied before it, and the price per resulting token are what an integrator actually has to look up and budget against.

Read this part in the article →