context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
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
Concrete numbers for slotting Grok 4.6 into a stack: near-frontier intelligence at $2/$6 per million 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 → with a 500k window, offset by below-average output speed and above-median verbosity.
