distillation — Training a small, cheap model to imitate a big one's outputs, keeping much of the capability at a fraction of the cost.
open weights — A model whose trained parameters are published for anyone to download and run — unlike API-only models you can access but never possess.
Why it matters
A small, efficient open weightsA model whose trained parameters are published for anyone to download and run — unlike API-only models you can access but never possess.Full definition → model purpose-tuned for tool-use and agentic workflows gives builders a lighter-weight option to self-host agents without relying on larger models.
