API
The Gcore Customer Portal is being updated. Screenshots may not show the current version.
Edge AI
Edge AI
Billing
About GPU CloudCreate an AI Cluster
Prepare a custom model for deployment
Deploy AI models in the Customer PortalDeploy AI models in the Customer Portal
Manage deployments in the Customer PortalCreate and manage API keysCreate and configure a registry
API
Chosen image
Home/Edge AI

Create an API Key

You can create API Keys to make sure that only authenticated clients can access your AI models.

Step 1. Initialize API Key creation

To open the Create API Key dialog, you can use this direct link or take the following two steps:

  1. Navigate to Everywhere Inference > API Keys in the Gcore Customer Portal.
Create an API Key
  1. Click Add API Key in the top right of the screen.
Create an API Key

This will open the Create API Key dialog, where you can configure the new API Key.

Step 2. Configure the API Key

In the Create API Key dialog, you can name and describe the API key and select the instances (e.g., AI model deployments) to which it should grant access.

You can select multiple instances for one key, and each instance can have multiple keys. You can also add and remove instances from the API Key or the deployment side later. For security reasons, you should set an expiration date for API Keys. The key will expire on the selected date at 00:00 UTC. You can change this setting later. Create an API Key

Step 3. Finalize the API Key creation

After entering the API Key details, click the Create button. The new API key will appear in the list of API Keys.

You can now select the API key for an AI model deployment. To learn how to deploy a custom AI model, read the guide.

Was this article helpful?