# What is LLM router?

Markdown version of https://kymaapi.com/glossary/llm-router, for agents and crawlers. Same content as the HTML page.

- Generated: 2026-10-28T21:43:30.486Z
- HTML page: https://kymaapi.com/glossary/llm-router
- Model catalog: https://kymaapi.com/models.md
- Pricing: https://kymaapi.com/pricing.md

An LLM router automatically directs each request to an appropriate model or backend based on availability, cost, capability, or a routing rule.

Routing is the decision layer inside a gateway. At minimum it maps a requested model to a backend that can serve it. More advanced routers pick a model dynamically (by task, by cost ceiling, or by which backend is currently healthy) and fall back to an equivalent model when the first choice fails.

Good routing is invisible: your request succeeds even when an individual backend is degraded, and you don't have to write retry-and-fallback logic yourself. Routing also enables aliases: stable names that resolve to a concrete model, such as the newest model of a line.

## How Kyma does it

On chat completions and messages, Kyma works through a multi-layer chain: retry, then an equivalent model, then a parallel race across quality-tier peers, so a single upstream outage usually does not surface as an error.

- [Model aliases](https://kymaapi.com/glossary/model-aliases)
- [LLM failover](https://kymaapi.com/glossary/llm-failover)
- [Live model rankings](https://kymaapi.com/rankings)

Try it with $0.50 free credit on the free tier. No card required. · [Get API key →](https://kymaapi.com/signup)

More terms

- [LLM gateway](https://kymaapi.com/glossary/llm-gateway)
- [Prompt caching](https://kymaapi.com/glossary/prompt-caching)
- [Model aliases](https://kymaapi.com/glossary/model-aliases)
- [LLM failover](https://kymaapi.com/glossary/llm-failover)
- [Tool calling](https://kymaapi.com/glossary/tool-calling)
- [Structured outputs](https://kymaapi.com/glossary/structured-outputs)
- [Pay-per-token pricing](https://kymaapi.com/glossary/pay-per-token)