{"data":{"slug":"distillation","etype":"concept","name":"Distillation","cat":"Training & Inference","subtitle":"Teaching a small model to imitate a big one.","summary":"Distillation trains a compact student on a larger teacher's outputs, keeping most capability at a fraction of the serving cost — the standard way 'mini' and 'flash' tiers are made. It is also a flashpoint: training on a rival API's outputs against its terms is industrial-scale imitation, an accusation that surfaced prominently around DeepSeek's rise.","attrs":null,"kf":null,"aliases":["knowledge distillation"],"ticker":null,"exchange":null,"hq":null,"founded":null,"website":null,"status":null,"region":null,"asof":"2026-01-15","sources":[{"url":"https://arxiv.org/abs/1503.02531","label":"Distillation paper (Hinton et al.)"}]},"meta":{"found":true,"count":1,"served_from":"site cache (no live upstream calls)","as_of":"2026-10-14T07:38:01+00:00","disclaimer":"Research and information only — not investment advice. Structured records carry basis labels (vendor spec / reported / estimate); market quotes are delayed/indicative.","attribution":"Records compiled from vendor documentation, official filings and reputable public reporting; market quotes via financial data providers. See /data-sources."}}