Skip to main content

Available infrastructures

This page lists the available compute infrastructures for your deployments.

Deployment environment

All deployments runs on a Linux-based environment, with the versions of Python and Ikomia API defined by the workflow.

Serverless deployments

These deployments runs on serverless functions (CPU only). Serverless deployments come with auto-scaling capability, making them a good choice for applications that need to adapt to traffic loads. They are better suited for lightweight workflows as they are generally limited in terms of compute power.

When you run these deployments, you are charged based on the workflow execution time. Idle time is free of charge.

Such deployments may have cold starts, which means high latency for the first request after a period of inactivity.

SizevCPURAMEphemeral storageAvailable regions
AWS
S34GB512MBFrance, Germany, Ireland
M46GB512MBFrance, Germany, Ireland
L58GB512MBFrance, Germany, Ireland
XL610GB512MBFrance, Germany, Ireland

Serverless deployments comes with ephemeral storage which is used to stores images/videos during the workflow execution.

Instance CPU deployments

These deployments run on dedicated CPU instances. Once they are running, they respond instantly and are generally more powerful than serverless deployments.

When you run these deployments, you are charged based on the time the instance is running, not depending on the number of requests.

SizevCPURAMDiskAvailable regions
AWS
XS28GB30GBFrance, Germany, Ireland
S48GB30GBFrance, Germany, Ireland
M816GB30GBFrance, Germany, Ireland
L1632GB30GBFrance, Germany, Ireland
XL3264GB30GBFrance, Germany, Ireland
GCP
XS28GB100GBNetherlands, United States (Central)
S416GB100GBNetherlands, United States (Central)
M832GB100GBNetherlands, United States (Central)
L1664GB100GBNetherlands, United States (Central)
XL32128GB100GBNetherlands, United States (Central)
Scaleway
XS28GB128GBFrance
S416GB128GBFrance
M832GB128GBFrance
L1664GB128GBFrance
XL32128GB128GBFrance

Instance GPU deployments

These deployments run on dedicated instances with GPU acceleration. They are generally the most powerful deployments, and are a good choice for workflows running deep learning models or other GPU intensive tasks.

When you run these deployments, you are charged based on the time the instance is running, not depending on the number of requests.

SizevCPURAMDiskGPUAvailable regions
AWS
XS416GB100GBNVIDIA T4 16GBFrance, Germany, Ireland
S832GB100GBNVIDIA T4 16GBFrance, Germany, Ireland
M416GB100GBNVIDIA A10 24GBGermany, Ireland
L832GB100GBNVIDIA A10 24GBGermany, Ireland
XL1664GB100GBNVIDIA A10 24GBGermany, Ireland
GCP
XS416GB100GBNVIDIA L4 24GBNetherlands, United States (Central)
S832GB100GBNVIDIA L4 24GBNetherlands, United States (Central)
M1664GB100GBNVIDIA L4 24GBNetherlands, United States (Central)
L1285GB100GBNVIDIA A100 40GBNetherlands, United States (Central)
XL12170GB100GBNVIDIA A100 80GBNetherlands, United States (Central)
Scaleway
XS816GB128GBNVIDIA RTX 3070 8GBFrance
S848GB128GBNVIDIA L4 24GBFrance
M1696GB128GB2x NVIDIA L4 24GBFrance
L896GB128GB + 1.6TB ephemeralNVIDIA L40S 48GBFrance
XL24240GB128GB + 3TB ephemeralNVIDIA H100 80GBFrance

High-end Scaleway GPU instances also comes with large partitions of ephemeral storage which is used to stores images/videos during the workflow execution.