Your end-to-end stack
for cloud compute
Modal lets you run or deploy machine learning models, massively parallel compute jobs, task queues, web apps, and much more, without your own infrastructure.
Cloud power, local productivity
Modal lets you run your code in the cloud within seconds. No need to install Docker, set up Kubernetes clusters, or even have an AWS account.
Run your entire AI/ML stack
Deploy a stable diffusion bot running on GPUs, train computer vision models, or run large-scale batch inference using a pretrained model.
End-to-end machine learning, from experimentation to deployment and continuous training on a schedule.
1
2
3
4
5
6
7
8
9
10
>
Say hello to Cloud 2.0
- Seamless infrastructure
- We built our own container engine, our own container image builder, and our own filesystem. Partly because we're crazy, mostly because we want to offer a more native experience.
- Top-notch speed
- Run code in the cloud with the same super fast feedback loop you have when you develop locally. Launch hundreds of containers of a freshly-built image within seconds.
1
2
3
4
5
6
7
8
>
Code that provisions itself
- Define your environment in code
- Need a new Python library, a binary dependency, or a dataset? Just declare it in your image. No need to install Docker, we'll build it for you.
- Distributed programming
- All infrastructure in Modal is in code. This includes image definitions, hardware requirements, parallelism, and distributed resources.
1
2
3
4
5
6
7
8
9
Deploy and scale any code
- Use the whole Python ecosystem
- Modal's flexible compute model extends to a wide range of applications, like web scraping, 3D rendering, and running distributed DuckDB SQL queries.
- Advanced infrastructure needs
- You can also deploy cron jobs, job queues, web endpoints, and many other types of applications on Modal.
Pay as you go
Modal only charges you for the time your code spends running in the cloud. See our pricing page for more information.