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.
reasoning model — A model trained to think — generating extended internal reasoning before answering — trading time and tokens for accuracy on hard problems.
test-time compute — Spending more computation when the model answers — thinking longer, trying multiple attempts — to buy accuracy without training a bigger model.
Why it matters
A reasoning modelA model trained to think — generating extended internal reasoning before answering — trading time and tokens for accuracy on hard problems.Full definition → that decodes by parallel refinement rather than left to right, hitting four-figure tokens per second on standard NVIDIA GPUs, collapses the usual trade of test-time computeSpending more computation when the model answers — thinking longer, trying multiple attempts — to buy accuracy without training a bigger model.Full definition → against latency and cost in agent loops.