How does model routing cut cost without collapsing quality?
PICTURE THIS: AN LLM TURN
Simple meaning
A classifier or small model handles easy intents
WHY — Tokens instead of words?
LLMs use tokens (not full words) because it helps them:
question about Cost.
trade-offs, and what you would actually do on a GenAI / LLM project - not buzzwords.
Each piece maps to a number the network can learn.
Fixed pieces are what transformers expect as input.
STEPS — What happens step by step?
Before you speak the answer, walk the interviewer through these steps:
- 1A classifier or small
model handles easy intents
- 2hard or high-risk queries
go to a frontier model.
- 3You need evals per
route and a fallback when confidence is low.
- 4Routing on user identity
alone is not a quality strategy.
- 5Common mistake
What juniors usually get wrong.
- 6Close
When you pick this over the alternative.
EXAMPLE — See it in action
Here's a short line you can speak, broken into clear beats:
Note: Adapt this scaffold to your own project — keep it under 60–90 seconds.
Key takeaway
A classifier or small model handles easy intents hard or high-risk queries go to a frontier model.