> For the complete documentation index, see [llms.txt](https://docs.umbraco.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.umbraco.com/ai-in-umbraco/17.latest/providers/providers.md).

# Overview

Umbraco.AI supports multiple AI providers through installable NuGet packages. Each provider connects to a different AI service and may support different capabilities.

## Available Providers

| Provider                                                                        | Package                       | Capabilities                    | Best For                         |
| ------------------------------------------------------------------------------- | ----------------------------- | ------------------------------- | -------------------------------- |
| [OpenAI](/ai-in-umbraco/17.latest/providers/openai.md)                          | `Umbraco.AI.OpenAI`           | Chat, Embedding, Speech-to-Text | General purpose, most models     |
| [Anthropic](/ai-in-umbraco/17.latest/providers/anthropic.md)                    | `Umbraco.AI.Anthropic`        | Chat                            | Claude models, long context      |
| [Google Gemini](/ai-in-umbraco/17.latest/providers/google.md)                   | `Umbraco.AI.Google`           | Chat                            | Gemini models, multimodal        |
| [Amazon Bedrock](/ai-in-umbraco/17.latest/providers/amazon.md)                  | `Umbraco.AI.Amazon`           | Chat, Embedding                 | AWS integration, multiple models |
| [Microsoft AI Foundry](/ai-in-umbraco/17.latest/providers/microsoft-foundry.md) | `Umbraco.AI.MicrosoftFoundry` | Chat, Embedding                 | Azure, enterprise compliance     |

## Choosing a Provider

Consider these factors when selecting a provider:

### Capabilities Needed

| Capability     | OpenAI | Anthropic | Google | Amazon | MS Foundry |
| -------------- | ------ | --------- | ------ | ------ | ---------- |
| Chat           | Yes    | Yes       | Yes    | Yes    | Yes        |
| Embedding      | Yes    | No        | No     | Yes    | Yes        |
| Speech-to-Text | Yes    | No        | No     | No     | No         |

### Use Case Fit

| Use Case                   | Recommended Provider     |
| -------------------------- | ------------------------ |
| General content generation | OpenAI, Anthropic        |
| Code assistance            | OpenAI, Anthropic        |
| Long document processing   | Anthropic (200K context) |
| Semantic search/RAG        | OpenAI, Amazon Bedrock   |
| AWS infrastructure         | Amazon Bedrock           |
| Azure/Microsoft stack      | Microsoft AI Foundry     |
| Cost optimization          | Google (Gemini Flash)    |

### Enterprise Considerations

| Factor                 | OpenAI  | Anthropic | Google  | Amazon | MS Foundry |
| ---------------------- | ------- | --------- | ------- | ------ | ---------- |
| Data residency options | Limited | No        | Yes     | Yes    | Yes        |
| SOC 2 compliance       | Yes     | Yes       | Yes     | Yes    | Yes        |
| HIPAA eligible         | Yes     | Contact   | Contact | Yes    | Yes        |
| Self-hosted option     | No      | No        | No      | No     | No         |

## Installing Multiple Providers

You can install multiple providers simultaneously. Each provider registers independently and becomes available in the Select AI Provider dialog.

{% code title="Package Manager Console" %}

```powershell
Install-Package Umbraco.AI.OpenAI
Install-Package Umbraco.AI.Anthropic
Install-Package Umbraco.AI.Google
```

{% endcode %}

Or via .NET CLI:

{% code title="Terminal" %}

```bash
dotnet add package Umbraco.AI.OpenAI
dotnet add package Umbraco.AI.Anthropic
dotnet add package Umbraco.AI.Google
```

{% endcode %}

## Provider Configuration Pattern

All providers follow the same pattern:

1. **Install the package** - NuGet package for the provider
2. **Create a connection** - Provide API credentials
3. **Create a profile** - Select model and configure settings
4. **Use the profile** - Reference in code or prompts

```mermaid
graph LR
    A["Provider\n(NuGet)"] --> B["Connection\n(API Key)"]
    B --> C["Profile\n(Model)"]
```

## Custom Providers

If your AI service isn't supported, you can create a custom provider. See [Creating Custom Providers](/ai-in-umbraco/17.latest/extending/providers.md).

## Related

* [Connections](/ai-in-umbraco/17.latest/concepts/connections.md) - Store provider credentials
* [Profiles](/ai-in-umbraco/17.latest/concepts/profiles.md) - Configure models for use
* [Capabilities](/ai-in-umbraco/17.latest/concepts/capabilities.md) - What operations providers support


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.umbraco.com/ai-in-umbraco/17.latest/providers/providers.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.