Skip to content

Update from code changes: document self-serve BYOK AI model settings #19

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
mintlify wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Update from code changes: document self-serve BYOK AI model settings #19

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions product-guide/docs.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -48,6 +48,7 @@
"platform/quickstart",
"platform/key-concepts",
"platform/configuration/settings",
"platform/configuration/ai-model",
"platform/configuration/user-management",
"platform/administration/roles-permissions"
]
Expand Down
43 changes: 43 additions & 0 deletions product-guide/platform/configuration/ai-model.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,43 @@
---
title: Bring your own AI model
description: Power AI features with your own LLM provider and API key.
---

By default, AI features run on a managed model. Bring your own key (BYOK) lets you supply your own LLM provider, model, and API key instead. Use BYOK when your organization requires a specific model, has an existing provider agreement, or needs AI traffic billed to its own provider account.

The model you configure powers all AI products in your deployment.

<Info>
BYOK is available on Enterprise plans. Configuring the AI model requires permission to update assistant settings. Members without this permission can view the configuration but cannot change it.
</Info>

## Configure your model

1. Go to **Settings → Organization → API keys**.
2. Find the **AI model** section and turn on the **Bring your own model** toggle.
3. Select a provider.
4. Select a model from the searchable list. Each provider shows a **Browse models** link if you want to compare options.
5. Enter your provider API key.
6. Click **Save**.

## Providers

Three provider options are supported:

| Provider | Base URL | Notes |
|----------|----------|-------|
| **Anthropic** | `https://api.anthropic.com/v1` | Choose from supported Claude models. |
| **OpenRouter** | `https://openrouter.ai/api/v1` | Choose from supported models across Anthropic, OpenAI, Google, xAI, and other model families. |
| **OpenAI-compatible** | Custom | Any endpoint that implements the OpenAI API format. Set your own provider name and base URL. |

For the OpenAI-compatible option, the base URL must be a valid HTTPS URL. The dashboard rejects unsafe or malformed URLs when you save.

## API key handling

- Your API key is stored securely and never displayed after saving.
- The saved key is reused when you switch models within the same provider. You only re-enter a key when you change providers or the base URL.
- To rotate a key, enter the new key in the **API key** field and click **Save**. Leaving the field blank keeps your saved key.

## Disable BYOK

Turn off the **Bring your own model** toggle to remove your provider configuration and stored API key. AI features revert to the managed default model.