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
The Quasar Alpha and Optimus Alpha stealth models were GPT-4.1 in testing. Those free endpoints now 404 with no redirect, so anything pointed at them breaks rather than silently billing, and GPT-4.1 pricing starts at $2 per 1M input 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 →.
