The Gcore Customer Portal is being updated. Screenshots may not show the current version.
Edge Cloud
Edge Cloud
Chosen image
Home/Edge Cloud

Manage deployments in the Customer Portal

After you deploy an AI model, it will appear on the Deployments page. There, you can find all the necessary information about the model:

  • Name: Name of your AI model (you entered it in the Deployment details section).

  • Endpoint: A URL for the pretrained deployed model.

  • Created: The date and time when the model was deployed.

  • Deployment status: An Inference at the Edge instance can have the following statuses:

    • New: We’re in the process of allocating resources to a deployment.
    • Succeeded: The instance has been successfully deployed.
    • Active: The deployment is up and running.
    • Failed: An error occurred when allocating resources. Recreate the deployment.
    • Disabled: The deployment is currently paused/inactive.
  • Running status: Maintenance deployment status, showing how many pods are run in the selected regions. Move the cursor over the number of running models and a list of regions will appear.

Deployments page with two inference instances

Manage deployments

You can view the configuration details of a deployed AI model, pause the deployment, or delete it from the Gcore Customer Portal. If you have a large number of deployments, you can also use search to find the one that you need.

Pause deployments

You can temporarily stop the deployment:

1. In the Gcore Customer Portal, navigate to Cloud > Inference at the Edge.

2. Click Deployments.

3. Find the deployment you want to stop and click the three-dot icon to open the settings menu.

4. Click Stop.

Stop deployment dialog

After stopping, the deployment status will change to “Disabled.” You can run the deployment anytime by clicking the three-dot icon and clicking Start.

View deployment details

To get comprehensive information about your deployment configuration and adjust the settings if needed:

1. In the Gcore Customer Portal, navigate to Cloud > Inference at the Edge.

2. Click Deployments.

3. Find the required deployment and click the three-dot icon next to it.

4. Click Overview.

Overview deployment dialogs

A new page with a deployment overview will open. Navigate to the corresponding tab to check a particular functionality.


This tab contains all the details related to your model's deployment. This includes the number of pods currently running, deployment status, price rate, endpoint, and description (if available).

Overview tab in the deployment overview

Click Show map with running replicas to view the regions where your models have been deployed.

Map with deployments

API key authentication

This tab allows you to configure API authentication for your Inference instance. To activate the feature, toggle the Enable API Key authentication toggle.

API keys section with enabled toggle

Choose one of the following options:

  • Select API keys: Add one or more keys that are already stored in the Gcore Customer Portal by selecting them from the dropdown list.

  • Create new API key:: Generate a new key.

Inference instances have a many-to-many relationship. A single instance can have multiple API keys, and the same API key can be attached to multiple instances.

To generate a key, select the Create new API key link:

1. In a new dialog that opens, enter the key name to identify the key in the system.

2. (Optional) Add a description to give more context about the key and its usage.

4. As a security measure, you can specify the key expiration date. If you don’t want to regenerate the key and want to keep it indefinitely, select Never expire.

4. Click Create.

Create API key dialog with annotated steps

You can now select the key from the API Keys dropdown and use it for authentication.


Here, you can delete a deployment and all its data.

Delete tab in the deployment overview

To delete the deployment:

1. Click Delete deployment.

2. Confirm your action by typing “Delete” in the text field.

3. Click Yes, delete.

Delete deployment confirmation dialog

The deployed AI model has been successfully deleted.


Here, you can change the following settings of the deployment:

  • Pod configuration: Change the parameters of a Kubernetes pod your model is deployed to.
Pod configuration section
  • Port: Change the port inside the container on which the model is listening.
Port section
  • Autoscaling: Increase or decrease the number of maximum and minimum pods during traffic changes.
Autoscaling section
  • Environment variables: Add metadata.
Environment variables section
  • Pod lifetime: Change the number of MB and vCPU allocated to the Kubernetes pod.
Pod lifetime section

Delete deployment

When you delete a deployment, you lose all its data. Deleted deployments can't be restored.

1. In the Gcore Customer Portal, navigate to Cloud > Inference at the Edge.

2. Click Deployments.

3. Find the deployment you want to delete and click the three-dot icon next to the deployment you want to view.

4. Click Delete.

Delete deployment option in the settings

5. Confirm your action by typing “Delete” in the text field.

6. Click Yes, delete.

The deployed AI model has been successfully deleted.

Was this article helpful?

Not a Gcore user yet?

Discover our offerings, including virtual instances starting from 3.7 euro/mo, bare metal servers, AI Infrastructure, load balancers, Managed Kubernetes, Function as a Service, and Centralized Logging solutions.

Go to the product page