Msty Integration

Msty is a desktop AI workspace that can use local models and connect to remote model providers. Connect it to LLM API to access models from multiple providers through one API key and endpoint.

This guide adds LLM API as an OpenAI-compatible provider, fetches the models available to your API key, and verifies the connection in a chat.

Prerequisites

An LLM API account
The Msty desktop application installed

Setup

Get Your LLM API Key

Open the LLM API dashboard.
Click Create Key to Start.
Copy the new API key. It is shown only once.
Store the key securely, such as in a password manager.

WARNING

Treat your API key like a password. Do not share it or include it in screenshots.

Open the Model Provider Settings

Open Msty and go to Model Hub.
Select Model Providers in the left sidebar.
Click Configure Cloud Providers.

Open the cloud provider settings from Msty Model Hub

Configure LLM API

Add a provider and enter these values:

Field	Value
Provider	`Open AI Compatible`
API Key	Your LLM API key
Inference Endpoint	`https://api.llmapi.ai/v1`
Provider Name	`LLM API`

Click Fetch Models after entering the API key and endpoint. Msty loads the models available to your LLM API key.

Configure LLM API as an OpenAI-compatible provider in Msty

WARNING

The screenshot was captured in a development environment. Use the public https://api.llmapi.ai/v1 endpoint from the table above, not the internal hostname shown in the image.

Select the models you want to make available, then click Add Provider. If you are editing an existing provider, the button is labeled Update Provider.

Select a Model and Test the Connection

Return to the chat screen and start a new conversation.
Open the model selector below the message box.
Choose a model from the LLM API provider.
Send a short test message.

A successful chat response from an LLM API model in Msty

The request is routed through LLM API and appears in your LLM API usage analytics. You can switch between LLM API cloud models and local models without changing the provider configuration.

Add a Model Manually

If a model does not appear after you click Fetch Models:

Open the LLM API provider in Model Hub.
Click Add Custom Model.
Copy the exact model ID from the models page.
Save the model, then update the provider.

Use the model ID exactly as shown. A display name or misspelled ID causes a model-not-found error.

Troubleshooting

Models Do Not Appear

Confirm that the inference endpoint is exactly https://api.llmapi.ai/v1.
Verify that the API key is active and does not contain leading or trailing spaces.
Click Fetch Models again after entering both the endpoint and API key.
Add the exact model ID manually if automatic discovery is unavailable.

Authentication or 401 Error

Paste the API key again without quotation marks or extra spaces.
Confirm that the key is active in the LLM API dashboard.
Make sure the selected model belongs to the LLM API provider.

404 or Connection Error

Include /v1 in the inference endpoint, but do not add /chat/completions.
Confirm that the provider type is Open AI Compatible.
Make sure your computer can make outbound HTTPS requests to api.llmapi.ai.

Model Not Found or Access Denied

Copy the exact model ID from the models page.
Confirm that the API key's IAM rules allow the selected model and provider.
Make sure your LLM API account has sufficient credits.

Next Steps

Browse the available LLM API models.
Review requests, costs, and provider routing in the LLM API usage analytics.
Add other models to the existing provider without creating another API key.