{
  "id": "model-cascade",
  "code": "PTL-0155",
  "term": "Model Cascade",
  "aliases": [
    "LLM cascade",
    "FrugalGPT",
    "cascading"
  ],
  "category": "optimization",
  "definition": "A model cascade sends each query to a cheaper model first and escalates it to progressively more capable and expensive models only when a scoring function judges the cheaper model's answer unreliable.",
  "description": "Because many queries are easy, most are answered cheaply, and only hard ones pay for the strongest model. FrugalGPT reported matching the best single model's performance at a large reduction in cost. The design depends on a reliable way to judge when an answer is good enough. Routing, by contrast, chooses a model before any answer is generated.",
  "example": null,
  "broader": [],
  "narrower": [],
  "related": [
    "routing",
    "confidence-calibration",
    "llm-as-a-judge"
  ],
  "introduced": 2023,
  "added": "2026-10-10",
  "sources": [
    {
      "title": "FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance",
      "authors": "Chen et al.",
      "year": 2023,
      "url": "https://arxiv.org/abs/2305.05176"
    }
  ],
  "url": "https://protologue.com/t/model-cascade/",
  "citation": "Protologue. (2026). Model Cascade. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.4.0, PTL-0155). https://protologue.com/t/model-cascade/"
}