---
title: "exo ai"
description: "On-demand Inference management"
url: https://community.exoscale.com/reference/cli/exo/ai/
section: reference
last_updated: 2026-10-22
---
> For AI agents: the documentation index is at https://community.exoscale.com/llms.txt. Every page is available as markdown at `<page URL>index.md` or with `Accept: text/markdown`.

# exo ai

Use the Exoscale CLI (`exo`) to manage On-demand Inference from your terminal.

On-demand Inference has two main resources:

* A **public model** is a ready-to-use model, available as a shared resource on the Exoscale infrastructure.
* A **AI API key** a token that allows access to one or multiple **public models** on a global inference endpoint.

All On-demand Inference commands are available under the `exo ai` namespace:

```bash
exo ai --help
```

### Related Commands

* [exo](https://community.exoscale.com/reference/cli/exo/index.md) - Manage your Exoscale infrastructure easily
* [exo ai model](https://community.exoscale.com/reference/cli/exo/ai/model/index.md) - List and show public models
* [exo ai api-key](https://community.exoscale.com/reference/cli/exo/ai/api-key/index.md) - Manage AI API keys