---
title: "exo dedicated-inference api-key create"
description: "Create AI API key"
url: https://community.exoscale.com/reference/cli/exo/dedicated-inference/api-key/create/
section: reference
last_updated: 2026-09-30
---
> 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 dedicated-inference api-key create

### Description

This command creates an AI API key.

The API key value is only returned once, at creation time, so store it securely.

Supported output template annotations: .ID, .Name, .Value, .Models, .Deployments, .AllModels, .AllDeployments

```
exo dedicated-inference api-key create NAME [flags]
```

### Options

| Option | Description |
| --------- | ------------ |
| `--all-deployments` | Grant access to all deployments |
| `--all-models` | Grant access to all public models |
| `--deployment` | Deployment ID the API key can access (repeatable) |
| `--help, -h` | help for create |
| `--model` | Public model name the API key can access (repeatable) |
| `--zone, -z` | zone |


### Options inherited from parent commands

| Option | Description |
| --------- | ------------ |
| `--config, -C` | Specify an alternate config file [env EXOSCALE_CONFIG] |
| `--output-format, -O` | Output format (table\|json\|text), see &#34;exo output --help&#34; for more information |
| `--output-template` | Template to use if output format is &#34;text&#34; |
| `--quiet, -Q` | Quiet mode (disable non-essential command output) |
| `--timeout` | Per-zone timeout for list operations; -1s disables timeout [env EXOSCALE_TIMEOUT] |
| `--use-account, -A` | Account to use in config file [env EXOSCALE_ACCOUNT] |


### Related Commands

* [api-key](https://community.exoscale.com/reference/cli/exo/dedicated-inference/api-key/index.md)	 - Manage AI API keys