# Function router LLM

**Source:** https://promtable.com/glossary/function-router-llm

> A function router LLM is a small fast model whose only job is to classify the incoming request and emit a structured tool call — pre-deciding which function the downstream pipeline should run.

---
A function router LLM is a small fast model whose only job is to classify the incoming request and emit a structured tool call — pre-deciding which function the downstream pipeline should run.

When agent tool counts grow past ~30, frontier models start mis-routing tools. A function router LLM specialises a small cheap model (GPT-4o-mini, Claude Haiku, Gemini Flash, or a fine-tuned open-weight) on the single task of routing — given a query, emit the correct function name + arguments. The strong executor model handles the actual response. This pattern combines well with semantic routing and is the production default in 2026 for cost-sensitive multi-tool agents. Best practice: fine-tune the router on your specific tool surface with synthetic queries + labelled tools for a measurable accuracy lift.

## When to use

- Cost-sensitive agents with diverse tool sets.
- Multi-skill assistants where wrong-tool routing degrades quality fast.

## Common mistakes

- Using a too-weak router — mis-routes silently.
- No fallback when the router is uncertain — pick a safe default or escalate.

## Related terms

- [model-router](https://promtable.com/glossary/model-router)
- [tool-router](https://promtable.com/glossary/tool-router)
- [semantic-routing](https://promtable.com/glossary/semantic-routing)
- [router-llm](https://promtable.com/glossary/router-llm)

*Last updated: 2026-06-01*
---

Original page: https://promtable.com/glossary/function-router-llm
Maintained by Promtable (https://promtable.com). Content: CC BY 4.0. Cite as "Promtable — https://promtable.com/glossary/function-router-llm".
Contact: info@vibecodingturkey.com.