Manage Serverless endpoints

Deploy and manage your endpoints using the Runpod console or REST API.

Create an endpoint

Web

To create a new Serverless endpoint through the Runpod web interface:

1. Navigate to the Serverless section of the Runpod console.
2. Click New Endpoint.
3. On the Deploy a New Serverless Endpoint screen, choose your deployment source:
   • Import Git Repository (if GitHub is connected) (see Deploy from GitHub for details.
   • Import from Docker Registry (see Deploy from Docker for details.
   • Or select a preconfigured endpoint under Ready-to-Deploy Repos.
4. Follow the UI steps to configure your selected source (Docker image, GitHub repo), then click Next.
5. Configure your endpoint settings:
   • Endpoint Name: The display name for your endpoint in the console.
   • Endpoint Type: Select Queue for traditional queue-based processing or Load balancer for direct HTTP access (see Load balancing endpoints for details).
   • GPU Configuration: Select the appropriate GPU types and configure worker settings.
   • Model: (Optional) Enter a model URL from Hugging Face to optimize worker startup times. See Pre-cached models for details.
   • Container Configuration: Edit the container start command, specify the container disk size, and expose HTTP/TCP ports.
   • Environment Variables: Add environment variables for your worker containers.
6. Click Deploy Endpoint to deploy.

REST API

To create a Serverless endpoint using the REST API, send a POST request to the /endpoints endpoint:

curl --request POST \
  --url https://rest.runpod.io/v1/endpoints \
  --header 'Authorization: Bearer RUNPOD_API_KEY' \
  --header 'Content-Type: application/json' \
  --data '{
  "allowedCudaVersions": [
    "12.8"
  ],
  "computeType": "GPU",
  "cpuFlavorIds": [
    "cpu3c"
  ],
  "dataCenterIds": [
    "EU-RO-1",
    "CA-MTL-1"
  ],
  "executionTimeoutMs": 600000,
  "flashboot": true,
  "gpuCount": 1,
  "gpuTypeIds": [
    "NVIDIA GeForce RTX 4090"
  ],
  "idleTimeout": 5,
  "name": "my-endpoint",
  "scalerType": "QUEUE_DELAY",
  "scalerValue": 4,
  "templateId": "30zmvf89kd",
  "vcpuCount": 2,
  "workersMax": 3,
  "workersMin": 0
}'

For complete API documentation and parameter details, see the Serverless endpoint API reference.

You can optimize cost and availability by specifying GPU preferences in order of priority. Runpod attempts to allocate your first choice GPU. If unavailable, it automatically uses the next GPU in your priority list, ensuring your workloads run on the best available resources.

You can enable or disable particular GPU types using the Advanced > Enabled GPU Types section.

After deployment, your endpoint takes time to initialize before it is ready to process requests. You can monitor the deployment status on the endpoint details page, which shows worker status and initialization progress. Once active, your endpoint displays a unique API URL (https://api.runpod.ai/v2/{endpoint_id}/) that you can use to send requests. For information on how to interact with your endpoint, see Endpoint operations.

Edit an endpoint

You can modify your endpoint’s configuration at any time:

1. Navigate to the Serverless section in the Runpod console.

2. Click the three dots in the bottom right corner of the endpoint you want to modify.

3. Click Edit Endpoint.

4. Update any configuration parameters as needed:

   • Endpoint name
   • Worker configuration
   • Docker configuration (container image or version)
   • Environment variables
   • Storage

5. Click Save Endpoint to apply your changes.

Changes take effect over time as each worker is updated to the new configuration.

To force an immediate configuration update, temporarily set Max Workers to 0, trigger the Release, then restore your desired worker count and update again.

Delete an endpoint

When you no longer need an endpoint, you can remove it from your account:

1. Navigate to the Serverless section in the Runpod console.
2. Click the three dots in the bottom right corner of the endpoint you want to delete.
3. Click Delete Endpoint.
4. Type the name of the endpoint, then click Confirm.

After confirmation, the endpoint will be removed from your account, and you’ll no longer be charged for its resources.

Attach network volumes

Attach persistent storage to share data across workers:

1. Navigate to the Serverless section in the Runpod console.
2. Click the three dots in the bottom right corner of the endpoint you want to modify.
3. Click Edit Endpoint.
4. Expand the Advanced section.
5. Select one or more volumes from the dropdown below Network Volumes.
6. Click Save Endpoint to attach the volumes to your endpoint.

Network volumes are mounted to /runpod-volume on each worker, making them ideal for sharing large models, datasets, or any data that needs to persist across worker instances.

When you attach multiple network volumes to an endpoint, workers are distributed across the datacenters where those volumes are located. Each worker is attached to exactly one network volume based on its assigned datacenter.

To learn more about how storage works in Serverless, see Storage options.

Best practices for endpoint management

• Start small and scale: Begin with fewer workers and scale up as demand increases.
• Monitor usage: Regularly check your endpoint metrics to optimize worker count and GPU allocation.
• Use GPU prioritization: Set up fallback GPU options to balance cost and availability.
• Leverage network volumes for large models or datasets rather than embedding them in your container image.
• Set appropriate timeouts based on your workload’s processing requirements.

Next steps

• Learn how to send requests to your endpoints.
• Explore advanced endpoint operations.
• Optimize your endpoints for cost and performance.
• Learn about endpoint job states and metrics.