> For the complete documentation index, see [llms.txt](https://docs.stackai.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.stackai.com/technical-reference/models-agents-and-skills/model-settings-and-supported-capabilities.md).

# Model Settings and Supported Capabilities

The selected model determines which inputs, tools, and generation settings a node can use. Choose capabilities for the task before changing individual parameters.

{% embed url="<https://1957915746-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FSQ1Sgy933krTyK0S4JpP%2Fuploads%2Fv2JXGLiSnBMhmOVOfXCF%2Fmodel-settings-and-capabilities.mp4?alt=media&token=21e4e16c-ef3b-4f0d-8c65-c9caaef70741>" %}
A short walkthrough of model settings and supported capabilities.
{% endembed %}

## Before you begin

Access to an enabled model and any required model-provider connection.

## Model concepts

| Term           | Definition                                                                                                         |
| -------------- | ------------------------------------------------------------------------------------------------------------------ |
| Model provider | The service hosting the selected model. Provider account access and billing can differ from StackAI-managed usage. |

## Configuration options

| Option            | Purpose                                                                     | Behavior                                                                             |
| ----------------- | --------------------------------------------------------------------------- | ------------------------------------------------------------------------------------ |
| Model             | The selected language, vision, or other AI model.                           | Supported inputs, tools, reasoning, and output formats depend on the model.          |
| Reasoning setting | A model-specific control for supported reasoning behavior.                  | Available values and their effects are not identical across models.                  |
| Temperature       | A model setting that affects variation in generated output where supported. | Lower variation is not a guarantee of identical or correct answers.                  |
| Output limit      | A cap on generated response length.                                         | Reaching it can truncate the response; it does not increase available input context. |

## Choose a model and configure its capabilities

1. Open the model settings and select the provider and model.
2. Check support for the required input type, tool calling, structured output, and reasoning options.
3. Set supported generation controls, then inspect the response and finish reason.

<figure><img src="https://1957915746-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FSQ1Sgy933krTyK0S4JpP%2Fuploads%2FkyMv3FH6lN928dyiBEPR%2Fmodel-and-prompt.png?alt=media" alt="Model and prompt controls in StackAI" width="800"><figcaption><p>Select a model, then review the controls available for that model. Instructions define the ongoing task and constraints. Prompt supplies the input for the current request. Reasoning and Web Search are separate capabilities; availability depends on the selected model.</p></figcaption></figure>

The node uses a model that supports the required work.

## Behavior and limitations

Settings are model-specific. Some models restrict sampling or always use reasoning. A setting available for one provider need not exist for another. Provider selection, model ID, and connection are separate choices. A successful request with an unknown finish reason is not proof that the answer was complete.

## Related resources

[Choosing thinking levels](https://docs.stackai.com/guides-and-quickstarts/workflow-builder/configure-models-and-prompts/choosing-thinking-levels.md) explains when to use lower or higher effort, how to test the tradeoff, and which provider differences affect the choice.

[Instructions, Context, and Token Limits](https://docs.stackai.com/technical-reference/models-agents-and-skills/instructions-context-and-token-limits.md)


---

# 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.stackai.com/technical-reference/models-agents-and-skills/model-settings-and-supported-capabilities.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.
