# Bring your own model (/ai/bring-your-own-model)

<!-- agent-signals: reading_time_min: 2 · est_tokens: 844 · updated: 2026-09-23 -->
Related: [Contextual menu](/ai/contextual-menu.md), [llms.txt](/ai/llmstxt.md), [Markdown export](/ai/markdown-export.md), [Admin Model Context Protocol (MCP) server](/ai/mintlify-mcp.md), [Search Model Context Protocol (MCP) server](/ai/model-context-protocol.md), [skill.md](/ai/skillmd.md)

<Info>
  Bring your own model requires an [Enterprise plan](https://mintlify.com/pricing?ref=bring-your-own-model). [Contact sales](https://www.mintlify.com/contact/sales) to inquire about adding it to your contract. The **AI model** section appears in your dashboard only when your contract includes it.
</Info>

By default, Mintlify selects the models that power the assistant and agent. To use a specific model with your own provider account, supply an API key and choose the model. Mintlify then runs inference against your provider.

One configuration covers every AI product on a deployment: the [assistant](/assistant), [agent](/agent), and [automations](/automations/index).

Bring your own model applies to a single deployment, not to your whole organization. If your organization has more than one deployment, configure each one separately. Deployments you don't configure use Mintlify's default models.

## Supported providers [#supported-providers]

| Provider          | Coverage                                                                                           |
| :---------------- | :------------------------------------------------------------------------------------------------- |
| OpenRouter        | Full. Every AI product uses your key and your model.                                               |
| Anthropic         | Limited. The assistant uses your key. The agent and automations continue to use Mintlify's models. |
| OpenAI-compatible | Limited. The assistant uses your key. The agent and automations continue to use Mintlify's models. |

Each provider supports a fixed set of models.

## Configure your model [#configure-your-model]

[Editors and admins](/dashboard/roles) can configure the model.

1. Select the deployment you want to configure.
2. Navigate to the [API keys](https://app.mintlify.com/settings/organization/api-keys) page in your dashboard.
3. In the **AI model** section, enable **Bring your own model**.
4. Select a provider. For an OpenAI-compatible provider, enter a provider name and base URL. The base URL must use HTTPS and point to a publicly reachable host.
5. Select a model.
6. Enter your provider API key.
7. Click **Save**.

Mintlify stores your key encrypted and never displays it again after you save it.

## How credits work [#how-credits-work]

AI usage on a deployment with bring your own model enabled does not consume Mintlify [credits](/credits). Your provider bills you directly for inference, and those charges do not appear in your Mintlify usage. Set any spending limits with your provider.

Credits pool at the organization level. Other deployments in the same organization still draw from that shared balance at the standard rate for their AI usage.

## Rotate or remove your key [#rotate-or-remove-your-key]

Mintlify reuses your saved key across models for the same provider on that deployment. Enter a key again only when you rotate it, switch providers, or configure another deployment.

To rotate your key, enter the new key in the **API key** field, then click **Save**.

To stop using your own model, disable **Bring your own model**. Mintlify deletes the stored configuration and key for that deployment, and its AI products return to Mintlify's default models. AI usage on the deployment then consumes credits at the standard rate. Other deployments keep their own configurations.