# Models & Credentials

<figure><img src="/files/81ezcZgZLTAlT2OFDYAJ" alt=""><figcaption></figcaption></figure>

The **Models & Credentials** section allows Admins to configure the AI models available to the workspace. This is where you can add API keys for different AI providers, enable or disable models, and adjust the model-specific settings such as temperature and context window. Having control over AI models ensures that your team can manage costs and leverage the right tools for their projects and tasks.

### Key Features

1. **Add API Keys**
   * Admins can add API keys for supported AI models such as OpenAI, Anthropic, and Perplexity. Adding these credentials enables your workspace to access the models for use in chats and prompts.
   * To add an API key:
     1. Select the provider (OpenAI, Anthropic, Perplexity) from the dropdown menu.
     2. Enter the API key in the provided field.
     3. Click **Save** to activate the model for your workspace.
2. **Enable or Disable Models**
   * Once API keys are added, admins can choose which models are available for workspace members. For example, you may enable GPT-4o for complex tasks but disable GPT-3.5 if it is not needed.
   * To enable or disable a model:
     1. Toggle the switch next to the model name.
     2. Enabled models will be available in the chat interface and prompts section for all workspace members.
3. **Adjust Model Settings**
   * Admins can fine-tune specific settings for each enabled model, such as temperature and context window:
     * **Temperature**: This controls how creative or focused the AI model is. A higher temperature (e.g., 1.0) makes the model more creative, while a lower temperature (e.g., 0.2) makes it more deterministic.
     * **Context Window**: This defines how much text the model can keep in context during conversations or tasks. Larger context windows allow the model to remember more information from previous interactions but increases the cost.

### Supported AI Providers

* **OpenAI**: Offers models like GPT-4o and GPT-o1-preview, which are widely used for generating text, performing complex tasks, and answering questions.
* **Anthropic**: Provides Claude, a family of models that focus on safe and helpful AI outputs.
* **Perplexity**: Known for models that are particularly good at research and knowledge retrieval tasks.

### How to Configure Models

1. Go to **Workspace Settings** > **Models & Credentials**.
2. Add or update your API keys for the desired providers.
3. Toggle the models you want to enable or disable.
4. Adjust model settings as necessary to suit your workspace needs.


---

# Agent Instructions: 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:

```
GET https://docs.chat.ngo/workspaces/workspace-settings/models-and-credentials.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.