mixture-of-experts — A model built from many specialist sub-networks where only a few activate per token, giving big-model capability at small-model running cost.
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.
structured output — Forcing a model's response to match a schema, so downstream code can parse it instead of guessing at prose.
Why it matters
A cheap, long-context windowThe maximum amount of text a model can consider at once — its working memory for the current conversation or task.Full definition → model aimed at repetitive agent tasks like tool useA model's ability to call external functions — run code, search the web, edit files — instead of only generating text.Full definition → and structured outputForcing a model's response to match a schema, so downstream code can parse it instead of guessing at prose.Full definition →. Published scores and per-token pricing let you test it against your current high-volume agent model.
