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.
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
Why it matters
RTFM generates video in real time as you move through a scene on one H100 and keeps the world persistent when you look away, with published numbers on why interactive world models cost far more to serve than LLMs.
