# Deployment options

CKEditor AI backend is available in two deployment modes: **Cloud (SaaS)** and **On-premises**. Both options provide the same core AI features – [Chat](ckeditor-ai-chat.md), [Quick Actions](ckeditor-ai-actions.md), [Review](ckeditor-ai-review.md), and [Translate](ckeditor-ai-translate.md) – with the on-premises version offering additional capabilities such as custom AI models and [MCP support](ckeditor-ai-mcp.md).

<a id="cloud-saas">

## Cloud (SaaS)

> **Unlock this feature with selected CKEditor Plans**
>
> Try all premium features – no credit card needed.
>
> [Sign up for a free trial ](https://portal.ckeditor.com/checkout?plan=free)[Select a Plan](https://ckeditor.com/pricing/)

The Cloud (SaaS) deployment offers the fastest way to get started with CKEditor AI. The AI service is hosted and managed by CKEditor, so there is no server-side setup required on your end. You only need to provide a valid license key and configure the editor-side plugins as described in the [integration guide](ckeditor-ai-integration.md).

For more information about the Cloud AI service, refer to the [CKEditor AI Cloud Services documentation](../../../../cs/latest/guides/ckeditor-ai/overview.md).

<a id="on-premises">

## On-premises

> **Unlock this feature with the Custom Plan**
>
> Want to try this feature? Contact us to request a trial or learn more about our plans.
>
> [Request a trial ](https://ckeditor.com/contact-sales/)[View plans](https://ckeditor.com/pricing/)

The on-premises deployment allows you to run the CKEditor AI service on your own infrastructure, including private cloud environments. The service is distributed as Docker images compatible with standard container runtimes.

On-premises deployment gives you full control over the AI service, including the ability to use custom AI models and providers, and to extend CKEditor AI with custom tools via [MCP (Model Context Protocol)](ckeditor-ai-mcp.md).

For detailed setup instructions, requirements, and configuration, refer to the [CKEditor AI On-Premises documentation](../../../../cs/latest/onpremises/ckeditor-ai-onpremises/overview.md).

<a id="connecting-the-editor-to-an-on-premises-service">

### Connecting the editor to an on-premises service

To point the editor to your on-premises AI service, set the [`config.ai.serviceUrl`](../../api/module_ai_aiconfig-AIConfig.md#member-serviceUrl) property to the URL of your on-premises instance:

```js
ClassicEditor
	.create( {
		licenseKey: '<YOUR_LICENSE_KEY>',

		ai: {
			serviceUrl: 'https://your-on-prem-host.com/v1',

			// ... Other AI configuration options.
		}

		// ... Other editor configuration.
	} )
	.then( /* ... */ )
	.catch( /* ... */ );
```

<a id="custom-ai-models">

### Custom AI models

The on-premises version supports custom AI model providers, including major clouds (Google Cloud, Amazon Bedrock, Azure OpenAI) and any OpenAI-compatible endpoint (e.g. OpenRouter, Together AI, self-hosted). Models configured on the server side will automatically appear in the editor’s model selector.

For configuration details, refer to the [on-premises configuration guide](../../../../cs/latest/onpremises/ckeditor-ai-onpremises/configuration.md#custom-models).

<a id="mcp-support">

### MCP support

The on-premises deployment supports the Model Context Protocol (MCP), which allows you to extend CKEditor AI with custom external tools. Learn more in the [MCP support](ckeditor-ai-mcp.md) guide.

<a id="feature-comparison">

## Feature comparison

| Feature                           | Cloud (SaaS) | On-premises |
| --------------------------------- | ------------ | ----------- |
| Hosted and managed by CKEditor    | ✅ Yes        | ❌ No        |
| Custom infrastructure             | ❌ No         | ✅ Yes       |
| Custom AI models and providers    | ❌ No         | ✅ Yes       |
| [MCP support](ckeditor-ai-mcp.md) | ❌ No         | ✅ Yes       |

---

Full index of the CKEditor 5 documentation: [llms.txt](../../../llms.txt)