Pricing and Billing

See the pricing page for current rates and your dashboard for usage and billing.

Serverless Compute

You are charged whenever a container is running. This includes:

• Running any code you’ve defined in an on_start function
• Running your application code
• Any keep_warm_seconds you’ve set

You are not charged for waiting for a machine to start or pulling your container image.

Reserved Machines and Your Own Hardware

Reserved machines are billed by the hour until they’re released, even when apps are idle. Leases renew hourly while your workspace has credit, so a reservation can outlast its original TTL. See How Reserved Nodes Are Billed.

Your own hardware has a Beam management charge. Hosted model rates appear in the endpoint catalog.

Credits

Prepaid workspaces need credits to build and deploy. Add them in Settings → Credits.

What About Storage?

Storage volumes are not billed as compute — you aren’t charged for keeping data in a volume while your containers are stopped.

• Every plan includes unlimited storage volumes.
• Storage is included free up to 1 TB. Beyond that, it costs $0.021 per GB per month.
• Snapshots are included.

See the pricing page for current rates.

Default Container Spin-down Times

After handling a request, Beam keeps containers running (“warm”) for a certain amount of time in order to quickly handle future requests. By default, these are the container “keep warm” times for each deployment type:

Deployment Type	Container Keep Warm Duration
Endpoints/ASGI/Realtime	180s
Task Queues	10s
Pods and Services	600s

Always-on settings keep containers running. Sandboxes use a lifetime instead of an idle timer; the Python default is 600 seconds.

Real-World Example

You’ve deployed a REST API. You’ve added two Python Packages in your Image(), which are loaded when your app first starts.

You’ve also added a keep_warm_seconds=300, which will keep the container alive for 300 seconds (5 minutes) after each request.

app.py

from beam import endpoint


# This runs once when the container first starts
def load_models():
    return {}

@endpoint(keep_warm_seconds=300, on_start=load_models)
def predict():
    return {}

Let’s pretend you deploy this and call the API. Suppose it takes:

• 1s to boot your application and run your on_start function.
• 100ms to run your task.
• 300s to keep the container alive, based on the keep_warm_seconds argument.

You would be billed for a total of 301.1 seconds.