# Model Routing

> Sending each request to the model that fits it, cheap or strong.

**Field:** Software Development  
**Category:** AI Engineering  
**Also known as:** LLM Routing, LLM Router, Model Router

## Think of it like

It is like a school nurse. Small cuts get a plaster, and big hurts go to the doctor.

## Definition

Model routing picks which model should answer each request before it is sent. A simple rule might send short, easy questions to a small, cheap model. Hard ones, like long code or tricky reasoning, go to a big model. Some routers use a small model of their own to make the choice. The aim is to pay for a big model only when the task needs one.

## Example

Lucy's help desk sends password questions to a small model and refund fights to a large one. Her bill drops by more than half, and the answers stay as good.

## Why it matters

Most requests in an app are easy. Sending them to a small model cuts cost and wait time, while hard ones still get the best answer.

## Common mistake

Routing without checking the answers. Test the small model on real requests first. If not, quality can slip and nobody sees it.

## Three principles

- **Choose before sending.** Each request gets its own pick.
- **Cheap by default.** Big models only when needed.
- **Check the quality.** Test each route on real requests.

## Related terms

- [LLM Gateway](https://learn.benibix.com/term/development/llm-gateway)
- [Model Fallback](https://learn.benibix.com/term/development/model-fallback)
- [Token Pricing](https://learn.benibix.com/term/development/token-pricing)
- [LiteLLM](https://learn.benibix.com/term/development/litellm)
- [Small Language Model (SLM)](https://learn.benibix.com/term/ai/small-language-model)
- [LLM Evaluation](https://learn.benibix.com/term/ai/llm-evaluation)
- [OpenRouter](https://learn.benibix.com/term/ai/openrouter)

## Told apart from

- [Model Routing vs Model Fallback](https://learn.benibix.com/compare/model-routing-vs-model-fallback): People think model routing and model fallback are the same switch between models. Routing picks a model before the call is sent, based on how hard the request looks. Fallback waits for a call to fail, then sends it again to a second model. Routing saves money on easy requests. Fallback keeps the app up when a model is down.
- [Model Selection vs Model Routing](https://learn.benibix.com/compare/model-selection-vs-model-routing): People think model selection and model routing are the same job, and they are not. Model selection is a choice you make once. You test a few models on real examples of your task, then pick one. Model routing is code that picks a model again for each request, as it comes in. You often do the first to set up the second.

![Requests arrive on the left: reset my password, what are your hours, and review this 400-line contract. A router box in the middle sorts them. The two easy ones go along the top lane to a small model marked fast and cheap. The hard one goes along the bottom lane to a large model marked slow and strong.](https://learn.benibix.com/diagrams/dev6-model-routing.svg)

---

Source: https://learn.benibix.com/term/development/model-routing
Author: Behnia Zarei (a developer in Vienna, Austria, who builds and teaches data, AI and business intelligence at BENIBIX)
Publisher: BENIBIX Learn (https://learn.benibix.com/)
Last updated: 2026-11-20
Licence: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Quote freely with attribution.
