“Our org runs on Modal. We use it for AI agent environments, scalable deployment of AI agents, hosting of deep learning models, and visualization. It dramatically simplified our engineering infrastructure and completely changed the scope of projects we can do.”
“We used Modal to build an inference server for our model, Chai-1, which allows people to predict molecular structures via a web app. Modal allowed us to build and launch the server in days: our engineers didn't have to worry about maintaining infrastructure, delivering the product in record time.”
Run large-scale batch processing on GPUs and CPUs
Powerful and easy fan-out support
Parallelize your Python functions over thousands of containers
Go from zero to 100 GPUs in seconds
Run structure prediction, molecular dynamics, and more
Scale up and scale out CPU-heavy jobs
Search terabyte-scale sequence databases in minutes, not hours
Run anything on Modal
A general-purpose compute layer
Modal's infrastructure runs your code in the cloud
Bring your custom container images to Modal
Run any packages, frameworks, or binaries you want
Build multi-step workflows that mix environments
Seamlessly exchange data between containers
You do the science, we do the infrastructure
Declare your infrastructure needs in a few lines of Python
No YAML needed. Get started in minutes, then scale for years.
Fully usage-based pricing
No need to make long-term reservations. Spin up and down in seconds.
Get access to a range of different GPU types
T4s, L4s, A10Gs, A100s, H100s. And CPUs too!
Try it out
Use Cases