# What is Model aliases?

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

- Generated: 2026-10-25T05:06:02.023Z
- HTML page: https://kymaapi.com/glossary/model-aliases
- Model catalog: https://kymaapi.com/models.md
- Pricing: https://kymaapi.com/pricing.md

A model alias is a short name that a gateway resolves to a concrete model, instead of an exact model id.

The best model for a task changes as new ones launch. If your code hardcodes a specific model id, you have to edit and redeploy every time you want to upgrade. An alias decouples intent ('I want the fastest model') from the specific model serving it today.

The trade-off is that behaviour and price move with the target, so production code that must not change under it should pin an exact model id.

## How Kyma does it

Kyma does not publish model aliases: you call an exact model id. Kyma never repoints a live model id to another model. On chat completions and messages, if a failover has to serve a different model, X-Kyma-Served-Model names it. Old alias names from earlier versions keep working for existing integrations.

- [Browse models](https://kymaapi.com/models)
- [Model aliases guide →](https://docs.kymaapi.com/guides/model-aliases)
- [What is an LLM router?](https://kymaapi.com/glossary/llm-router)

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)
- [LLM router](https://kymaapi.com/glossary/llm-router)
- [Prompt caching](https://kymaapi.com/glossary/prompt-caching)
- [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)