the.ai

Inference / Adaptive

verified

Model Routing

Decide which model should answer before any of them does. A router looks at the request and sends it to the cheapest model likely to handle it — which is the same goal as a cascade and a different shape, because nothing is computed twice and nothing is thrown away.

Viz primitive · threshold-sweepseparation = 1.5 · threshold = 0.7 · base-rate = 0.3
let throughcutflagged

402 of 1000 flagged. 59% of them were right and 163 were false alarms; 80% of what should have been caught was, leaving 61 missed.

Requests that genuinely need the large model against ones that do not, scored by a router reading only the request. Drag the separation up to watch them come apart — where it sits is a property of the traffic, since some domains show their difficulty and some do not.

1.5

Reviewed by opendroid · 2026-08-18

  • arXiv:2305.05176 — FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance
  • arXiv:2403.02419 — Are More LLM Calls All You Need? Towards Scaling Laws of Compound Inference Systems