This guide covers the essential management operations for Runpod Serverless endpoints, helping you deploy, configure, and maintain your Serverless applications effectively.

​
Create an endpoint

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(/serverless/workers/github-integration).
    • 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:
    • Set the Endpoint Name
    • Choose your Endpoint Type: select Queue for traditional queue-based processing or Load balancer for direct HTTP access (see Load balancing endpoints for details)
    • Under GPU Configuration, select the appropriate GPU types and configure worker settings
    • Set Environment Variables and other options as needed. For a full list of options, see Endpoint configurations
  6. Click Create Endpoint to deploy.
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.

​
Add a network volume

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 a volume from the dropdown below Network Volume.
  6. Click Save Endpoint to attach the volume to your endpoint.
Network volumes are mounted to the same path on each worker, making them ideal for sharing large models, datasets, or any data that needs to persist across worker instances.

​
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.

​
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