Available infrastructures
This page lists the available compute infrastructures for your deployments.
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), they are usually the smallest and cheapest deployments available. Serverless deployments come with auto-scaling capability, making them a good choice for applications that need to adapt to traffic loads. Conversely, your workflow should not require heavy computing power.
Such deployments may have cold starts, which means that the first request to your deployment may take more time to respond.
When you run these deployments, you are charged based on the workflow execution time.
| Size | vCPU | RAM | Available regions |
|---|---|---|---|
| AWS | |||
| S | 3 | 4GB | France, Germany, Ireland |
| M | 4 | 6GB | France, Germany, Ireland |
| L | 5 | 8GB | France, Germany, Ireland |
| XL | 6 | 10GB | France, Germany, Ireland |
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.
| Size | vCPU | RAM | GPU | Available regions |
|---|---|---|---|---|
| AWS | ||||
| XS | 4 | 16GB | NVIDIA Tesla T4 (16GB) | France, Germany, Ireland |
| S | 8 | 32GB | NVIDIA Tesla T4 (16GB) | France, Germany, Ireland |
| M | 4 | 16GB | NVIDIA A10 (24GB) | Germany, Ireland |
| L | 8 | 32GB | NVIDIA A10 (24GB) | Germany, Ireland |
| XL | 16 | 64GB | NVIDIA A10 (24GB) | Germany, Ireland |
| Google Cloud | ||||
| XS | 4 | 16GB | NVIDIA L4 (24GB) | Netherlands, United States (Central) |
| S | 8 | 32GB | NVIDIA L4 (24GB) | Netherlands, United States (Central) |
| M | 16 | 64GB | NVIDIA L4 (24GB) | Netherlands, United States (Central) |
| L | 12 | 85GB | NVIDIA A100 (40GB) | Netherlands, United States (Central) |
| XL | 12 | 170GB | NVIDIA A100 (80GB) | Netherlands, United States (Central) |
| Scaleway | ||||
| S | 8 | 16GB | NVIDIA RTX 3070 (8GB) | France |
| M | 10 | 42GB | NVIDIA Tesla P100 (16GB) | France |
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. Conversely, such deployment does not include auto-scaling capability.
When you run these deployments, you are charged based on the time the instance is running, not depending on the number of requests.
| Size | vCPU | RAM | Available regions |
|---|---|---|---|
| AWS | |||
| XS | 2 | 8GB | France, Germany, Ireland |
| S | 4 | 8GB | France, Germany, Ireland |
| M | 8 | 16GB | France, Germany, Ireland |
| L | 16 | 32GB | France, Germany, Ireland |
| XL | 32 | 64GB | France, Germany, Ireland |
| Google Cloud | |||
| XS | 2 | 8GB | Netherlands, United States (Central) |
| S | 4 | 16GB | Netherlands, United States (Central) |
| M | 8 | 32GB | Netherlands, United States (Central) |
| L | 16 | 64GB | Netherlands, United States (Central) |
| XL | 32 | 128GB | Netherlands, United States (Central) |
| Scaleway | |||
| S | 3 | 4GB | France |