Skip to main content
Latitude.sh provides a variety of Operating systems that you can use to create your servers, such as Windows and Linux distributions. You can find all supported operating systems by going to the server create page or through the following API request. 
curl --request GET \
     --url https://api.latitude.sh/plans/operating_systems \
     --header 'Authorization: Bearer <API_KEY>'

​
ML-in-a-Box

ML-in-a-Box is a custom image built by Latitude.sh that you can use to get started quickly with any of the GPU servers available. This image comes with several dependencies needed for Machine Learning and AI workloads and is automatically selected when you are deploying a GPU server and select Ubuntu as the Operating System. The versions of the installed dependencies are optimized for compatibility and might not be the latest versions available.
DepdendencyVersion
Python3.10
NVIDIA CUDA12.8
NVIDIA Driver570.133.20
NVIDIA Container Toolkit1.17.7-1
NVIDIA cuDNN9.8.0
Docker28.1.1
PYTorch2.6.0+cu124

​
Custom images

Installing your own images is supported through iPXE scripts. Go to Custom image (iPXE) to learn more.
⌘I