{
 "id": "https://redfinchadvisory.com/lexicon/inference",
 "slug": "inference",
 "prefLabel": "Inference",
 "altLabel": [
  "Model serving",
  "Serving"
 ],
 "hiddenLabel": [],
 "definition": "The act of running a trained model to produce an output from inputs, as opposed to training it.",
 "scopeNote": "",
 "tier": "core",
 "group": "How models work",
 "broader": [],
 "narrower": [
  "https://redfinchadvisory.com/lexicon/batch-inference",
  "https://redfinchadvisory.com/lexicon/reasoning-effort"
 ],
 "related": [
  {
   "id": "https://redfinchadvisory.com/lexicon/training",
   "type": "pair"
  },
  {
   "id": "https://redfinchadvisory.com/lexicon/cost-per-token",
   "type": "related"
  }
 ],
 "links": [
  {
   "id": "https://redfinchadvisory.com/lexicon/context",
   "label": "input to",
   "direction": "in"
  },
  {
   "id": "https://redfinchadvisory.com/lexicon/model",
   "label": "runs the",
   "direction": "out"
  },
  {
   "id": "https://redfinchadvisory.com/lexicon/token",
   "label": "measured in",
   "direction": "out"
  },
  {
   "id": "https://redfinchadvisory.com/lexicon/llm-gateway",
   "label": "sits in front of",
   "direction": "in"
  }
 ],
 "modified": "2026-10-21",
 "markdown": "https://redfinchadvisory.com/lexicon/inference.md",
 "inScheme": {
  "id": "https://redfinchadvisory.com/lexicon",
  "version": "1.0",
  "currentAsOf": "2026-10-21"
 }
}