> 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/19.latest/management-api/providers/list.md).

# List Providers

List all registered AI providers.

Returns all AI providers registered in the system.

## Request

```http
GET /umbraco/ai/management/api/v1/providers
```

### Headers

| Header          | Value                  |
| --------------- | ---------------------- |
| `Authorization` | Bearer token or cookie |

### Query Parameters

None.

## Response

### Success (200 OK)

Returns an array of provider items.

{% code title="Response" %}

```json
[
    {
        "id": "openai",
        "name": "OpenAI",
        "capabilities": ["Chat", "Embedding"]
    },
    {
        "id": "azure-openai",
        "name": "Azure OpenAI",
        "capabilities": ["Chat", "Embedding"]
    }
]
```

{% endcode %}

### Response Properties

| Property       | Type      | Description                |
| -------------- | --------- | -------------------------- |
| `id`           | string    | Unique provider identifier |
| `name`         | string    | Display name               |
| `capabilities` | string\[] | Supported capabilities     |

## Capabilities

Possible capability values:

| Value        | Description                                              |
| ------------ | -------------------------------------------------------- |
| `Chat`       | Conversational AI / chat completions                     |
| `Embedding`  | Text to vector embeddings                                |
| `Decision`   | Typed yes/no, pick-one, and score answers (experimental) |
| `Extraction` | Typed values read out of text (experimental)             |

Experimental capabilities are only listed when their feature flag is enabled. A provider whose capabilities are all disabled is left out of the response. For example, [TypeSafe AI](/ai-in-umbraco/19.latest/providers/typesafe.md) is only listed when the `Umbraco:AI:Experimental:Decision` flag is on, and [Cloudflare](/ai-in-umbraco/19.latest/providers/cloudflare.md) only when the `Umbraco:AI:Experimental:Extraction` flag is on.

## Example

### cURL

```bash
curl -X GET "https://your-site.com/umbraco/ai/management/api/v1/providers" \
  -H "Authorization: Bearer {token}"
```

### C# HttpClient

{% code title="Example" %}

```csharp
using var client = new HttpClient();
client.DefaultRequestHeaders.Authorization =
    new AuthenticationHeaderValue("Bearer", token);

var response = await client.GetAsync(
    "https://your-site.com/umbraco/ai/management/api/v1/providers");

var providers = await response.Content
    .ReadFromJsonAsync<ProviderItemResponseModel[]>();

foreach (var provider in providers)
{
    Console.WriteLine($"{provider.Name}: {string.Join(", ", provider.Capabilities)}");
}
```

{% endcode %}

### JavaScript

{% code title="Example" %}

```javascript
const response = await fetch("/umbraco/ai/management/api/v1/providers", {
    headers: {
        Authorization: `Bearer ${token}`,
    },
});

const providers = await response.json();
providers.forEach((p) => {
    console.log(`${p.name}: ${p.capabilities.join(", ")}`);
});
```

{% endcode %}

## Notes

* Providers are discovered automatically from installed NuGet packages
* The list is read-only - providers cannot be added via API
* Only active (properly configured) providers are returned


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.umbraco.com/ai-in-umbraco/19.latest/management-api/providers/list.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.