Modal

What it is

Quick answers

What counts as billable time?

Modal bills you during application load time and during the time your container is processing inputs. By default, containers stay alive for 60 seconds after the last inputs before shutdown, which is also billable. This timeout is configurable. Once your application scales down to zero containers you are no longer charged.

How are CPU and memory usage metered?

Modal continuously records CPU and memory consumption. CPU usage is tracked in fractional physical cores, allowing higher utilization than providers with minimum thresholds. Each physical core equals 2 vCPUs. You are charged based on whichever is higher: the amount you request or the amount you actually use. Each container has a minimum of 128 MiB memory and 0.125 CPU cores.

How does serverless pricing differ from traditional on-demand pricing?

Modal's serverless model differs from traditional cloud compute in several ways. Traditional cloud has slow provisioning (10+ minutes) and requires minimum usage commitments of 1 minute to 1 hour. Modal spins containers up and down in 1-2 seconds with no minimum commitment. While per-hour prices may appear higher, overall costs are lower for spiky or unpredictable workloads because you pay less for non-execution time and avoid over-provisioning for peak loads.

Do I need to purchase credits?

Workspaces receive a free allotment of compute per month, but usage on the Starter and Team plans is pay-as-you-go and does not require pre-purchasing compute or tokens. If you want to limit monthly spend, you can set a Workspace budget.

What kinds of applications can I deploy using Modal?

You can deploy any application that can be containerized using Python. Modal is especially well-suited for compute-intensive workloads that benefit from horizontal scaling, including ML inference at scale, model training and fine-tuning, data pipelines, numerical and scientific computing, and compute-heavy job queues.