Home / Rank #3

Model routing & cascades

Typical savings40–98% depending on workload mix
EffortMedium — needs routing logic and evals

Most requests do not need your most expensive model. Routing sends simple queries to cheap models (Haiku, GPT-mini class, Nova) and reserves frontier models for the requests that actually need them; cascade designs try cheap first and escalate only on failure.

Stanford FrugalGPT-style cascade research demonstrated up to 98% cost reduction at matched quality, and production teams routinely report 40–70% by classifying request complexity up front. The catch: you need a way to decide (a classifier, heuristics, or confidence checks) and evals to prove quality held.

How to do it

  1. Segment traffic by task type; label which segments a small model already handles well.
  2. Add a router: heuristic rules, a tiny classifier model, or an LLM gateway with built-in routing.
  3. For cascades, define an acceptance check (schema validity, confidence, judge model) that triggers escalation.
  4. Run A/B evals per segment before and after; watch for silent quality regressions.

Frequently asked questions

What is the difference between routing and a cascade?

Routing decides the model before the call based on the request. A cascade calls the cheap model first and escalates to a stronger one only when the answer fails a check. Cascades save more but add latency on escalated requests.

Tools for this method

Open-source LLM gateway

LiteLLM

The default self-hosted gateway: one OpenAI-compatible proxy across 100+ providers with budgets, caching, routing, fallbacks, and …

Managed AI gateway

Portkey

Managed gateway with the strongest built-in semantic caching, plus guardrails, routing, and cost analytics. The low-ops route to t…

Multi-provider model marketplace

OpenRouter

One API and one bill across hundreds of models from every major lab — the fastest way to arbitrage the model price war and A/B che…

Next method: #4 Semantic caching