> For the complete documentation index, see [llms.txt](https://docs.agentalk.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.agentalk.io/settings-and-administration/use-agentalk-with-enterprise-api-keys.md).

# Use Agentalk with enterprise API keys

Enterprise plan customers can configure an agent to route LLM usage through their own API key from supported providers such as OpenAI or Gemini.

This allows you to use your existing LLM contracts, monitor usage directly in your provider dashboard, and keep full control over LLM-related costs.

### Before you start

You need the following before you begin:

* An **Enterprise plan** (this feature is not available on standard plans).
* An active API key from a supported provider (such as OpenAI or Gemini).

When using your own API key:

* LLM usage is billed directly by your provider.
* Agentalk credits still apply for call infrastructure.

### Why organizations use enterprise API keys

Organizations typically use their own API keys for the following reasons:

<table data-view="cards"><thead><tr><th></th><th></th></tr></thead><tbody><tr><td><strong>Existing LLM contracts</strong></td><td><p></p><p>Route usage through pre-negotiated agreements with providers like OpenAI or Gemini.</p></td></tr><tr><td><strong>Cost control and visibility</strong></td><td><p></p><p>Track usage directly in your provider’s dashboard alongside other systems.</p></td></tr><tr><td><strong>Compliance requirements</strong></td><td><p></p><p>Ensure all AI usage goes through approved and auditable credentials.</p></td></tr></tbody></table>

### Configure an enterprise API key

Set up your API key and assign it to agents.

{% hint style="warning" %}
The exact configuration steps depend on your account setup. If you do not see this option, contact Agentalk support.
{% endhint %}

1. Open the settings area where enterprise API keys are configured.
2. Select your provider (for example, OpenAI or Gemini).
3. Enter your API key.
4. Assign the key to the agents that should use it.
5. Save your configuration.

Once configured, the selected agents will use your API key for LLM requests.

### Security considerations

You are responsible for securing your API key.

Follow these best practices:

* Use a **dedicated API key** for Agentalk.
* Store the key securely and avoid sharing it publicly.
* Set usage limits in your provider’s dashboard.
* Rotate keys periodically.
* Revoke the key immediately if it is compromised.

### Next steps

Here are the recommended next steps after completing this guide:

* [**Credits and pricing**](/core-concepts/credits-and-pricing.md): Understand how Agentalk credits work alongside your API usage.
* [**Manage your organization**](/settings-and-administration/manage-your-organization.md): Configure organization-level settings before going live.


---

# 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 dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.agentalk.io/settings-and-administration/use-agentalk-with-enterprise-api-keys.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.