> For the complete documentation index, see [llms.txt](https://university.mindstudio.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://university.mindstudio.ai/workspace-management/configuring-manual-connections-to-ai-model-providers.md).

# Configuring Manual Connections to AI Model Providers

Use your API keys to connect directly to model providers.

MindStudio allows you to manually connect to AI model providers by supplying your own API keys. This gives you full control over billing, quotas, and provider-specific settings while still using the MindStudio Service Router to access models inside agents, workflows, and tools.

## How to Add a Custom Connection

#### 1 – Navigate to [MindStudio AI Models Page](https://app.mindstudio.ai/services/models)

<figure><img src="https://3216313986-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FpGwRPnWO6pBvzbcecqLI%2Fuploads%2FBCZ2tJA7Ps6WBOGFSMkV%2FSCR-20260112-jwjx.png?alt=media&amp;token=ff198664-e2a0-462c-aa0b-f85ee890b05e" alt=""><figcaption></figcaption></figure>

**Workspace Sidebar → Service Router → AI Models**

* This page lists all supported model providers along with their available models and connection status.

#### 2 – Add your custom API Key

<figure><img src="https://3216313986-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FpGwRPnWO6pBvzbcecqLI%2Fuploads%2FS8YSzG5hdBjbRtJclOdv%2FSCR-20260112-juwy.png?alt=media&amp;token=75eab9de-4451-4960-ab92-90dbe1437ee5" alt=""><figcaption></figcaption></figure>

* Locate the provider you want to configure (for example, OpenAI, Anthropic, Google)
* Click **Custom Key** on the right side of the provider row
* A modal will appear prompting you to enter an API key
* Paste your provider-issued API key into the field
* Click **Save**

## Understanding Provider Connection States

Each provider row shows three possible states:

* **Disabled** – The provider is not currently usable
* **Custom Key** – The provider uses your manually supplied API key
* **Managed** – The provider uses MindStudio-managed routing and billing

You can switch between Managed and Custom Key at any time.

## Verifying the Connection

After saving a custom key:

* The provider status updates to **Custom Key**
* All supported models under that provider become selectable
* Requests route directly to the provider using your credentials

If a key is invalid or revoked, requests will fail and surface an upstream provider error.

## Switching Back to Managed Routing

You can revert to MindStudio-managed billing at any time:

1. Return to **AI Models**
2. Find the provider
3. Click **Managed**

This disables your custom key and resumes routing through MindStudio’s shared infrastructure.


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://university.mindstudio.ai/workspace-management/configuring-manual-connections-to-ai-model-providers.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.
