How to stop and restart a Serverless AI Devlab or endpoint

Devlabs

If you don’t currently need your Devlab but you want to preserve it, you can stop the Devlab and then restart it later. While the Devlab is stopped, you’re not billed for computing resources, but you are billed for the disk of the underlying Compute virtual machine (VM). Data under the workspace path persists across stop and restart operations. If you mount a volume to a Devlab, you are also charged for the volume even if the Devlab is stopped.

How to stop and restart a Devlab

Make sure you are in a group that has at least the editor role within your tenant or project; for example, the default editors group. You can check this in the Administration → IAM section of the web console.

Web console
CLI

In the sidebar, go to Serverless AI → Devlabs.
Find the Devlab and then click → Stop or Restart.
In the window that opens, confirm the action.

List Devlabs and copy the required ID:
nebius ai devlab list
To stop a Devlab, run the following command:
nebius ai devlab stop <devlab_ID>
To restart a Devlab, run the following command:
nebius ai devlab restart <devlab_ID>

Endpoints

If you don’t currently need your endpoint but you want to preserve it, you can stop the endpoint and then restart it later. Computing resources of stopped endpoints aren’t billed. However, if you mounted a volume to the endpoint, you are charged for the volume even if the endpoint is stopped. When you stop an endpoint, Serverless AI releases the underlying Compute VM and its disk but preserves the endpoint’s configuration, including a reserved IP address and a public HTTPS URL. When you restart the endpoint, Serverless AI creates a new VM and once again pulls the container image that was used earlier. As a result, the endpoint is available at the same URL and IP address. The URL and address only change if you delete the endpoint and create a new one. Since the original VM and its disk are released when you stop an endpoint, no data at this disk is preserved. Unlike Devlabs, endpoints don’t keep workspace for the disk across stop and restart operations.

How to stop and restart an endpoint

Web console
CLI
REST API

In the sidebar, go to Serverless AI → Endpoints.
Locate the endpoint and then click → Stop or Restart.
In the window that opens, confirm the action.

To get the endpoint ID, list all endpoints:
nebius ai endpoint list
In the output, copy the ID of the required endpoint.
Restart the endpoint:
nebius ai endpoint restart --id <endpoint_ID>
This command runs both the stop and restart operations, so you reboot the endpoint.

To only perform the stop operation, run the following command:

nebius ai endpoint stop --id <endpoint_ID>

For starting the endpoint, run the following command:

nebius ai endpoint start --id <endpoint_ID>

List endpoints:
curl --request GET \ --url "https://api.nebius.cloud/ai/v1/endpoints?parentId=<project_ID>" \ --header "Authorization: Bearer <access_token>"
In the request, specify:
- Your access token in the Authorization header.
- The project ID in the parentId query parameter.
In the response, copy the metadata.id of the required endpoint.

Restart the endpoint:

curl --request POST \
  --url 'https://api.nebius.cloud/ai/v1/endpoints/restart' \
  --header "Authorization: Bearer <access_token>" \
  --header 'Content-Type: application/json' \
  --data '{
    "id": "<endpoint_ID>"
  }'

In the request, specify:

Your access token in the Authorization header.
<endpoint_ID>: Endpoint ID that you copied.

To only perform the stop operation, send the following request:

curl --request POST \
  --url 'https://api.nebius.cloud/ai/v1/endpoints/stop' \
  --header "Authorization: Bearer <access_token>" \
  --header 'Content-Type: application/json' \
  --data '{
    "id": "<endpoint_ID>"
  }'

For starting the endpoint, send the following request:

curl --request POST \
  --url 'https://api.nebius.cloud/ai/v1/endpoints/start' \
  --header "Authorization: Bearer <access_token>" \
  --header 'Content-Type: application/json' \
  --data '{
    "id": "<endpoint_ID>"
  }'

AI services in Nebius AI Cloud

Serverless AI

Managed Service for MLflow

Applications in Nebius AI Cloud

Tutorials

Third-party integrations

How to stop and restart a Serverless AI Devlab or endpoint

Devlabs

How to stop and restart a Devlab

Endpoints

How to stop and restart an endpoint

​Devlabs

​How to stop and restart a Devlab

​Endpoints

​How to stop and restart an endpoint

Devlabs

How to stop and restart a Devlab

Endpoints

How to stop and restart an endpoint