> ## Documentation Index
> Fetch the complete documentation index at: https://docs.xpander.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Aliases and fallbacks

> A stable model name your people and apps call, with models to try when it fails.

An alias is a model name your organization defines, such as `default-coding`. Clients send it as the model, and the LLM Gateway sends the call to its target. Change the target and every client follows, with no change on any laptop or app.

![Diagram](https://docs.xpander.ai/images/diagrams/run-llm-gateway-aliases-64f5f510.svg)

## Add an alias

**1. Start from a model**

In [Models](https://platform.xpander.ai/governance/model-access), open the provider, then the model's **⋯** menu, and choose **Add alias…**.

**2. Name it**

Enter a **Name**: lowercase letters, digits, dots, dashes and underscores, starting with a letter or digit, 63 characters at most. A **Description** is optional.

**3. Choose the target**

**Points to** starts on the model you chose. Pick any other model you turned on.

**4. Add fallbacks**

Under **Fallbacks, tried in order**, choose **Add a fallback model** for each model to try. The target can't be a fallback, and each fallback appears once.

**5. Save**

Choose **Add alias**.

Names starting with `xp-` are reserved: *Names starting with xp- are xpander's built-in models; choose another name for: ...*

## Read, edit and remove aliases

Each alias is a tag under its model. Aliases whose model is not listed join **Other aliases**. A grayed-out tag means the target is off. A warning dot means a fallback is off. Hover for details. Click a tag to edit it and choose **Save alias**, or use **Delete alias** in the card's menu. Clients still sending a deleted alias get an error.

An alias applies to the whole organization, but each caller is still limited to the models they may use, as when calling the model directly.

## Fallbacks

An overload or server error is retried on the same model, then on each fallback in order. A failure that will not change (an invalid request, a model that is off, a spent budget) is not retried. Each fallback runs on the key assigned for its own provider ([Whose key pays](https://docs.xpander.ai/run/llm-gateway/providers-and-keys.md#whose-key-pays)), and each attempt shows under **Routing** on the request in [Logs](https://platform.xpander.ai/governance/logs).

## Where people find aliases

Under **Shortcuts your admin set up** in [AI models & keys](https://chat.xpander.ai/?settings=my-gateway), in the **Model** picker of Codex, OpenCode and SDK setups, and in `/v1/models` on the gateway address.

## Next steps

> **[Choose whose key pays](https://docs.xpander.ai/run/llm-gateway/providers-and-keys.md#whose-key-pays)**
>
> Keys per organization, group, person or agent.

> **[Follow a request in Logs](https://platform.xpander.ai/governance/logs)**
>
> Each routing attempt.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.