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
Luna drops 80% to $0.2/$1.2 per 1M 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 Terra 20% to $2/$12, with Sol's fast mode now 2.5x — and since model IDs are unchanged, existing requests pick up the new rates with no code change.
