modal.com Open in urlscan Pro
54.158.199.14  Public Scan

Form analysis
0 forms found in the DOM

Text Content

Use Cases
PricingCompanyBlogDocs
Log In Sign Up




THE SERVERLESS
PLATFORM
FOR
AI DATA ML TEAMS

Run generative AI models, large-scale batch jobs, job queues, and much more.

Bring your own code — we run the infrastructure.

Get started Docs

1

2

3

4

5

6

7

import modal

app = modal.App()

@app.function()
def hello():
    print("Running remotely on Modal!")

> modal run hello.py
✓ Initialized.
✓ Created objects.
├── 🔨 Created hello.
└── 🔨 Mounted ./hello.py.




CUSTOMERS RUN MODAL TO POWER DATA-INTENSIVE APPLICATIONS




THE ONLY RUNTIME ENVIRONMENT YOU NEED FOR GENERATIVE AI

AI Inference Fine-tuning Batch Processing

Original
Turbo XL

Fast cold boots

Load gigabytes of weights in seconds with our optimized container file system.

Bring your own code

Deploy your model on Modal's custom runtime.

Seamless autoscaling

When your app gets an influx of traffic, Modal scales with you.

Learn more


ENGINEERED FOR LARGE-SCALE WORKLOADS

We built a container system from scratch in Rust for the fastest cold-start
times. Scale to hundreds of GPUs and back down to zero in seconds, and pay only
for what you use.

GPU Containers

Enqueued
Startup
Execution
Status
11:13:29
0.0s
1.0s
Running
11:13:26
1.1s
1.4s
Succeeded
11:13:26
0.0s
2.2s
Succeeded
11:13:21
1.2s
2.1s
Succeeded


ITERATE AT THE SPEED OF THOUGHT

Deploy functions to the cloud in seconds, with custom container images and
hardware requirements. Never write a single line of YAML.

--------------------------------------------------------------------------------


EVERYTHING YOUR APP NEEDS

Environments
Express container images and hardware specifications entirely in code.
Say goodbye to Dockerfiles and YAML.
Storage
Provision network volumes, key-value stores and queues with ease.
Use powerful cloud primitives that feel like regular Python.
Job scheduling
Turn functions into cron jobs with a single line of code.
Spawn compute intensive jobs without blocking your backend.
Web endpoints
Serve any function as an HTTPS endpoint.
Ship to your own custom domains.
Observability
Monitor executions, logs and metrics in real time.
Debug interactively with modal shell.
Security
Secure your workloads with our battle-tested gVisor runtime.
Industry-standard SOC 2 compliance.

--------------------------------------------------------------------------------

Mike Cohen
Head of Data

“Substack recently launched a feature for AI-powered audio transcriptions. The
data team picked Modal because it makes it easy to write code that runs on 100s
of GPUs in parallel, transcribing podcasts in a fraction of the time.”

Karim Atiyeh
Co-Founder & CTO

“Ramp uses Modal to run some of our most data-intensive projects. Our team loves
the developer experience because it allows them to be more productive and move
faster. Without Modal, these projects would have been impossible for us to
launch.”

--------------------------------------------------------------------------------


ONLY PAY FOR WHAT YOU USE

Scale up to hundreds of nodes and down to zero within seconds. Pay for actual
compute, by the CPU cycle. With $30 of compute on us, every month.

See pricing


COMPUTE COSTS

Per Second
Per Hour

CPU

Physical core (2 vCPU equivalent)

$0.0000533 / core / sec

GPU

Nvidia H100

$0.002125 / sec

Nvidia A100, 80 GB

$0.001553 / sec

Nvidia A100, 40 GB

$0.001036 / sec

Nvidia A10G

$0.000306 / sec

Nvidia L4

$0.000291 / sec

Nvidia T4

$0.000164 / sec

Memory

$0.00000667 / GiB / sec

Are you an early-stage startup or academic?
Startups and academic researchers can get up to $25k free compute credits on
Modal. These credits can be used towards GPU compute and accessing in-demand GPU
types.
Apply now

--------------------------------------------------------------------------------


JOIN MODAL'S DEVELOPER COMMUNITY

Modal Community Slack
Emanuel Ferm
VP of Data, Cometeer

I've had Modal running in production flawlessly for over a year now. Mark of a
great product: using infra it replaces feels ridiculous and archaic.

Jessie Frazelle
CEO, Zoo.dev

Deployed two models to @modal_labs today, was very easy. Nice thing they have
there and cold starts are FAST! Much better than hugging face or anything else!

Pedro Alcocer
ML Engineer

Whether @modal_labs is part of the tech stack will absolutely factor into my
decision about where I work next. Never had a better developer experience.

Erin Boyle
ML Engineer, Tesla

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

Aman Kishore
CTO, MirageML

If you are still using AWS Lambda instead of @modal_labs you're not moving fast
enough

Lindsay Pettingill
Data @ Replit

Modal has the most magical onboarding I've ever seen and it's not even close.
And Erik's walk through of how they approached it is a Masterclass.

Jai Chopra
Product, LanceDB

Recently built an app on Lambda and just started to use @modal_labs, the
difference is insane! Modal is amazing, virtually no cold start time, onboarding
experience is great 🚀

Izzy Miller
DevRel, Hex

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.

Rahul Sengottevelu
Head of Applied AI, Ramp
My favorite thing to do on Modal - running massively parallel GPU finetune jobs

At Ramp, we’ve trained hundreds of LLMs at the same time without the infra
hassle - Modal allows us to move insanely fast
Max Halford
Head of Data, Carbonfact

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

Ashe Magalhaes
Founder, Hearth AI

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

James Kirk
AI/ML at Hunt Club

been using @modal_labs for a few hours and am already certain this is how I will
be getting things done for a long time to come


SHIP YOUR FIRST APP IN MINUTES

Get started

with $30 / month free compute

© 2024
Use Cases
Language Model Inference Image, Video & 3D Inference Audio Inference Fine-Tuning
Job Queues & Batch Processing Sandboxed Code Execution
Popular Examples
LoRAs Galore! Serve Mixtral 8x7B at 100s of tokens per second Custom Art of Your
Pet Replace your CEO with an LLM Analyze Parquet files from S3 with DuckDB
Resources
Documentation Pricing Slack Community Security & Privacy
Company
About Blog
CareersWe're hiring!
Privacy Policy Terms