End-to-end cloud compute

Model inference, batch jobs, task queues, web apps and more. All without your own infrastructure.

Trusted by the most ambitious engineering teams

Why Modal

Iterate at the speed of thought

Cloud power, local productivity

Run your code in the cloud within seconds. No need to install Docker, set up Kubernetes clusters, or even have an AWS account.

deploy to

production

0.00s

container

start-ups

Built from scratch for high performance

A brand new container runtime written in Rust, specifically designed for modern-day use cases.

Infinite use cases

You create it, we run it. Explore the use cases that align with your goals.

Model inference

Job queues

Large-scale parallelism

Web apps

Cron jobs

The Future Now

Say hello to Cloud 2.0

Seamless infrastructure.: Deploy from a local machine to the cloud with just two additional lines of code.
Top-notch speed.: Run code in the cloud with the same instant feedback loop you have when you develop locally. Launch hundreds of containers of a freshly-built image within seconds.

Whatever you need

Self-provisioning runtime

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 primititves.: All infrastructure needs in Modal are expressed in code. This includes hardware requirements, parallelism, storage volumes, and data structures.

No limits

Deploy and scale anything

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.
Many patterns, one solution.: Leave the scheduling and scaling to us, whether it's a cron job, task queue, or web endpoint.
Pay only for what you use.: Everything scales to 0 by default, and Modal only charges you for the time your code runs in the cloud.

Deployed on Modal

See the possibilities

gradio

diffusers

Stable Diffusion CLI

Stable Diffusion 1.5 on Modal with a number of optimizations for faster inference

whisper

tortoise

vicuna

Voice chat with LLMs

Real-time voice chat with open-source LLMs

gradio

diffusers

Pet Art using Dreambooth

Fine-tune Stable Diffusion v1.5 on images of your pet using textual inversion

whisper

ffmpeg

Podcast Transcriptions with Whisper

Build a podcast episode transcriber for all of the podcasts you enjoy

transformers

job queues

Document OCR Job Queue

Use Modal as an infinitely scalable job queue that can service async tasks from a web app

datasets

concurrency

Analyze datasets in parallel with DuckDB

Use DuckDB to analyze datasets such as that of the Taxi and Limousine Commission of NYC in parallel

langchain

openai

Question-answering with LangChain

Create a large-language-model (LLM) powered question answering web endpoint and CLI

slack

cron jobs

Hacker News Slackbot

Use Modal to deploy a cron job that periodically queries Hacker News for new posts, and posts the results to Slack

huggingface

Real-time Object Detection

Create a web endpoint that does object detection in real-time

diffusers

gradio

ControlNet Playground

Play with all 10 demo Gradio apps from the ControlNet project

gradio

diffusers

Stable Diffusion CLI

Stable Diffusion 1.5 on Modal with a number of optimizations for faster inference

Build together

Our community loves Modal

special shout out to @modal_labs and @_hex_tech for providing the crucial infrastructure to run this! Modal is the coolest tool I’ve tried in a really long time— cannnot say enough good things.

Izzy Miller

@isidoremiller

Wow - @modal_labs looks so good. I see great things in their future.

Ian H

@ianhunter

we ❤️ modal team - they’re super responsive even on weekends for niche issues 🙌

ashe

@ashe_cs

Modal is cool! Easily the best serverless dev experience I've seen. That said, it's definitely more optimized for an interactive experience than a programmatic one. This makes sense! It's early days, and it's already providing extremely powerful abstractions.

Garrett Hoffman

@garrettleeh

My new fav stack: @nextjs on @vercel, with a @supabase backend, and @modal_labs for data processing/queues/etc It's kinda wild how powerful this is.

Codeptualize

@codeptualize

The Tech Stack you need to build powerful apps. Frontend: @nextjs Backend: @supabase Deploy: @vercel Data Processing: @modal_labs The beauty of this stack is that you can start for FREE

Afiz ⚡️

@itsafiz

Shoutout to @modal_labs, which I used to run the @OpenAI Whisper models to transcribe the audio. Appreciate the previous commenters who recommended it! It was easy to parallelize around ~80 containers so a 90+ min podcast could be transcribed in under a minute🤯🤯🤯 [3/4]

Jesse Zhang

@thejessezhang

@modal_labs (modal.com): the easiest way to run stuff in the cloud. Honestly it's mind-blowing. Thanks @bernhardsson!

Max Halford

@halford_max

@modal_labs is a blessing built by the Cloud Computing deity to bring joy and love for our lives. I've never seen anything like it, but it is the best PaaS/SaaS/ Whatever-a-a-S I've ever used.

@piesposi_to

Something like this would of been basically impossible to do so quickly without @modal_labs, since I'd have to learn ML infra on gcp/aws, auto scaling, managing gpu infra, etc. It's autoscaled by them, so I can easily tune 5,10,15 models at a time. Don't have to manage A100s

Sully

@SullyOmarr

This tool is awesome. So empowering to have your infra needs met with just a couple decorators. Good people, too!

Erin Boyle

@erinselene

Modal has already completely changed the way I interact with the cloud. It's so fast that I skip the local dev environment and just develop my code in the cloud from the start of a project. 1/

Ryan Abernathey

@rabernat

Find out if Modal is right for you

Get started

with 100+ hours of free compute

Pricing

Pay as you go

Modal charges you for only the time and resources your code actually uses in the cloud.

CPU starting at $0.0000533/core/sec

GPU starting at $0.000164/sec

Memory starting at $0.00000667/GiB/sec

See pricing