> ## Documentation Index
> Fetch the complete documentation index at: https://docs.omni.co/llms.txt
> Use this file to discover all available pages before exploring further.

# Anthropic Direct - Bring Your Own Key (BYOK)

> Directly call Anthropic APIs to power AI features in Omni.

export const provider_2 = "Anthropic Direct"

export const provider_1 = "Anthropic Direct"

export const type_0 = "models"

export const fieldType_0 = "dropdown"

export const provider_0 = "Anthropic Direct"

When you use Anthropic Direct as an [LLM provider on your own key][model-providers], Omni calls the Anthropic API with your API key to power AI features.

## Requirements

To follow the steps in this guide, you'll need:

* **Organization Admin** permissions in Omni
* **An Anthropic API key**

## Enabling Anthropic Direct as a provider

<Steps>
  <Step>
    In Omni, navigate to **AI Hub > General** and click the **LLM settings** tab.
  </Step>

  <Step>
    In the **Providers** section, click the **Your API keys** tab.
  </Step>

  <Step>
    Click **{provider_0}** to open its settings.
  </Step>

  <Step>
    Enter your Anthropic API key in the **API key** field.
  </Step>

  <Step>
    {fieldType_0 === "dropdown" ? (
              <MDX>
                  In the **Simple-task model** dropdown, select the model you want to use for [light tasks](/ai/settings/llm-settings#simple-tasks), such as naming a chat and writing summaries.
              </MDX>
          ) : (
              <MDX>
                  In the **Simple-task model** field, enter the model identifier to use for [light tasks](/ai/settings/llm-settings#simple-tasks), such as naming a chat and writing summaries. A smaller, faster LLM is recommended.
              </MDX>
          )}
  </Step>

  <Step>
    Click **Save and approve**.
  </Step>

  <Step>
    To run AI features on {provider_1} by default, select one of the {type_0} as the [organization default](/ai/settings/llm-settings#organization-defaults).
  </Step>
</Steps>

By default, Omni approves all available LLMs once a provider is successfully configured, which means users can select the LLMs in the [chat picker](/ai/chat#selecting-an-ai-model-tier). Use the LLM section to [revoke specific LLMs](/ai/settings/llm-settings#llm-approval), mark an LLM as [test only](/ai/settings/llm-settings#test-only), and add [useful descriptions](/ai/settings/llm-settings#description).

## Disabling Anthropic Direct as a provider

In the **Your API keys** tab, use the toggle next to **{provider_2}** to disable it as a provider.

After Omni saves the changes, a **Delete saved key** option will display.

Check this option and click **Save** to permanently delete the key. If you decide to re-enable {provider_2} later, you'll need to add a new API key.

[model-providers]: /ai/settings/model-providers


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.