Model Routing, Fallback & Degraded Mode

Two problems share this skill. Routing = picking the cheapest model that still meets the quality bar for this request (a value decision). Fallback = surviving when the chosen model is unavailable (a reliability decision). Build both — routing without fallback is a single point of failure; fallback without routing burns money on easy work.

Tiers, not model IDs, are the durable unit: frontier (most capable, slowest, ~10–30× cost), mid (workhorse), small (fast, cheap, weak). Names shift quarterly; the tier logic does not.

1. Why route — don't send everything to the frontier model

The frontier model is the wrong default. ~70–90% of production traffic is easy (classification, extraction, short rewrites, routine Q&A) and a small model handles it at a fraction of the cost and latency. Routing trades three axes: