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.
agent harness — The scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.
sandbox — An isolated environment where AI-generated code or agent actions run without being able to touch anything real.
Why it matters
Laguna M.1 and XS.2 now serve 256K context windowThe maximum amount of text a model can consider at once — its working memory for the current conversation or task.Full definition → on the API and OpenRouter while staying free, with M.1 at 45.8% on Terminal-Bench 2.0 and full agent harnessThe scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.Full definition → and sampling details published alongside.
