Training & tuning
Distillation
Training a smaller "student" model to mimic a larger "teacher" model, keeping much of the quality at far lower cost and latency.
In practice
A distilled mini model runs cheaply while echoing a frontier model's behavior.
Related terms
See what your tokens really cost
Track usage and spend across every model and platform, free.
Image: panumas nikhomkhai on Pexels. Definition free to reuse under CC BY 4.0.