core practice · coding problem

Route by cost and difficulty

Classify queries: "2+2" → small model; "design payment system" → large model. Write a 2-rule router on length and keyword "design".

The mechanism

Not every request needs the frontier model. A router classifies difficulty and dispatches: small/cheap model for easy calls, large model for hard ones — with cost and latency tracked per route.

Study Model Routing

Expected evidence

Rule-based router with fallback to large on low confidence.

Try this drill in the practice workspace →

Hints when you need them

Cheap path for easy queries.
Escalate on failure.

Watch for these mistakes

Routing without evals, so quality silently drops
No fallback when the cheap model fails

Check the sources

Building Effective AI Agents (Anthropic Engineering)
FrugalGPT: Using LLMs While Reducing Cost and Improving Performance (Chen et al.)
How to Scale Your Model (JAX ML scaling book)
RouteLLM: Learning to Route LLMs with Preference Data

Browse all practice briefs