> 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/using-the-api/chat/advanced-options.md).

# Advanced Options

Fine-tune AI responses with ChatOptions for temperature, token limits, and more.

Override profile defaults on a per-request basis using `ChatOptions`. These options are passed directly to the AI provider.

## ChatOptions

Pass `ChatOptions` through the builder to configure chat behavior:

{% code title="WithOptions.cs" %}

```csharp
var messages = new List<ChatMessage>
{
    new(ChatRole.User, "Write three tagline options for a coffee shop.")
};

var options = new ChatOptions
{
    Temperature = 0.9f,
    MaxOutputTokens = 200,
    TopP = 0.95f,
    StopSequences = ["---"]
};

var response = await _chatService.GetChatResponseAsync(
    chat => chat.WithAlias("tagline-writer").WithChatOptions(options),
    messages);
```

{% endcode %}

## Available Options

| Option             | Type                  | Description                                           |
| ------------------ | --------------------- | ----------------------------------------------------- |
| `Temperature`      | `float?`              | Controls randomness (0 = deterministic, 1 = creative) |
| `MaxOutputTokens`  | `int?`                | Maximum tokens in the response                        |
| `TopP`             | `float?`              | Nucleus sampling threshold                            |
| `StopSequences`    | `IList<string>?`      | Sequences that stop generation                        |
| `FrequencyPenalty` | `float?`              | Penalizes repeated tokens                             |
| `PresencePenalty`  | `float?`              | Penalizes tokens already present                      |
| `Seed`             | `long?`               | Seed for reproducible outputs                         |
| `ResponseFormat`   | `ChatResponseFormat?` | Request JSON or text output                           |

{% hint style="info" %}
Not all providers support every option. Unsupported options are ignored. Check the provider documentation for supported parameters.
{% endhint %}

## Requesting JSON Output

Use `ChatResponseFormat` to request structured JSON responses:

{% code title="JsonResponse.cs" %}

```csharp
var options = new ChatOptions
{
    ResponseFormat = ChatResponseFormat.Json
};

var messages = new List<ChatMessage>
{
    new(ChatRole.System, "Return a JSON object with 'title' and 'summary' fields."),
    new(ChatRole.User, "Describe Umbraco CMS.")
};

var response = await _chatService.GetChatResponseAsync(
    chat => chat.WithAlias("json-responder").WithChatOptions(options),
    messages);
// response.Message.Text contains JSON: {"title": "...", "summary": "..."}
```

{% endcode %}

## Combining with Profiles

Options override profile settings for that request only. The profile settings remain unchanged:

{% code title="Override.cs" %}

```csharp
// Profile has Temperature = 0.7
var options = new ChatOptions
{
    Temperature = 0.2f  // Override to more deterministic for this request
};

var response = await _chatService.GetChatResponseAsync(
    chat => chat.WithAlias("profile-example").WithProfile(profileId).WithChatOptions(options),
    messages);
```

{% endcode %}

## Related

* [Basic Chat](/ai-in-umbraco/19.latest/using-the-api/chat/basic-chat.md) - Sending chat requests
* [Streaming](/ai-in-umbraco/19.latest/using-the-api/chat/streaming.md) - Streaming with options
* [Profiles](/ai-in-umbraco/19.latest/concepts/profiles.md) - Default profile settings


---

# 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/using-the-api/chat/advanced-options.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.