Getting started with Serverless AI endpoints: Deploy an nginx server with authentication

Serverless AI lets you deploy and manage endpoints without handling infrastructure yourself. This quickstart shows how to validate basic endpoint functionality with minimal setup. In the web console, Quick start Serverless endpoint deploys a ready-made example with preconfigured settings.

Prerequisites

Web console
CLI

Make sure you are in a group that has the admin role within your tenant; for example, the default admins group. You can check this in the Administration → IAM section of the web console.
In the Quota section of the web console, check the following quotas:
- Number of virtual machines (VMs) under Compute: make sure that at least one VM is available.
- Total number of allocations under Virtual Private Cloud: make sure that at least one allocation is available.
If necessary, increase the quotas.

Make sure you are in a group that has the admin role within your tenant; for example, the default admins group. You can check this in the Administration → IAM section of the web console.
In the Quota section of the web console, check the following quotas:
- Number of virtual machines (VMs) under Compute: make sure that at least one VM is available.
- Total number of allocations under Virtual Private Cloud: make sure that at least one allocation is available.
If necessary, increase the quotas.
Install and configure the Nebius AI Cloud CLI. Check that your project ID is saved in the Nebius AI Cloud CLI profile configuration:
```
cat ~/.nebius/config.yaml
```

Steps

Create an endpoint

Web console
CLI

In the sidebar, go to AI Services → Endpoints.
Click Quick start Serverless endpoint. The flow uses a preconfigured container image and default settings.
Click Create endpoint.

Wait for the endpoint to be ready. It takes approximately 30 seconds.

Create a token for authorization and save it to an environment variable:
```
export AUTH_TOKEN=$(openssl rand -hex 32)
```

Get the ID of the default subnet where you create an endpoint:

nebius vpc subnet get-by-name --name default-subnet \
  --format jsonpath='{.metadata.id}'

Create an endpoint with a simple HTTP server:

nebius ai endpoint create \
  --name qs-endpoint-nginx \
  --image nginx:alpine \
  --platform cpu-d3 \
  --preset 4vcpu-16gb \
  --public \
  --container-port 80 \
  --auth token \
  --token "$AUTH_TOKEN" \
  --subnet-id <subnet_ID>

Wait for the endpoint to be ready. It takes approximately 30 seconds.

Test the endpoint

Web console
CLI

Open AI Services → Endpoints.
Click the endpoint name to open its details. In the Network section, copy the public IP address.
In a terminal, send a request to the endpoint:
```
curl -v http://<public_IP_address>
```

In the command, specify the public IP address that you copied earlier.The response should have HTTP status 200 OK. The body is the default nginx welcome page, which confirms that the endpoint is serving traffic.

Save the endpoint ID to an environment variable:

export ENDPOINT_ID=$(nebius ai endpoint get-by-name \
  --name qs-endpoint-nginx --format jsonpath='{.metadata.id}')

Get the endpoint IP address:

export ENDPOINT_IP=$(nebius ai endpoint get "$ENDPOINT_ID" \
  --format jsonpath='{.status.public_endpoints[0]}')

Test the endpoint with authentication:

curl -v http://$ENDPOINT_IP -H "Authorization: Bearer $AUTH_TOKEN"

Test the endpoint without a token:
```
curl -v http://$ENDPOINT_IP
```
The test should fail with the error 401 Unauthorized or 403 Forbidden.

View logs

Web console
CLI

In the sidebar, go to AI Services → Endpoints.
In the endpoint list, next to the endpoint, click View logs. Alternatively, click → View logs.

View endpoint logs:

nebius ai endpoint logs $ENDPOINT_ID

Delete the endpoint

If you no longer need the endpoint, delete it. Once you delete the endpoint, you will not be charged for it.

Web console
CLI

In the sidebar, go to AI Services → Endpoints.
In the endpoint list, find the endpoint and click → Delete.
Confirm the endpoint deletion.

nebius ai endpoint delete $ENDPOINT_ID

Expected results

A request without a token in the web console returns 200 OK.
A request without a token in the CLI returns 401 Unauthorized or 403 Forbidden.
An endpoint can be deleted successfully.

Serverless AI

Managed Service for MLflow

Applications in Nebius AI Cloud

Tutorials

Third-party integrations

Getting started with Serverless AI endpoints: Deploy an nginx server with authentication

Prerequisites

Steps

Create an endpoint

Test the endpoint

View logs

Delete the endpoint

Expected results

See also

Serverless AI

Managed Service for MLflow

Applications in Nebius AI Cloud

Tutorials

Third-party integrations

​Prerequisites

​Steps

​Create an endpoint

​Test the endpoint

​View logs

​Delete the endpoint

​Expected results

​See also

Prerequisites

Steps

Create an endpoint

Test the endpoint

View logs

Delete the endpoint

Expected results

See also