context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
tool use — A model's ability to call external functions — run code, search the web, edit files — instead of only generating text.
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
Mercury 2 is now deployable inside Azure with network isolation, SOC2/HIPAA compliance, and a no-training data guarantee. This is the path teams blocked from a startup API endpoint were waiting on.