Modal

The serverless cloud infra for AI, ML, and data applications

5.0•67 reviews•

437 followers

The serverless cloud infra for AI, ML, and data applications

5.0•67 reviews•

437 followers

Visit website

Run or deploy machine learning models, massively parallel compute jobs, task queues, web apps, and much more, without your own infrastructure.

Modal Reviews

The community submitted 67 reviews to tell us what they like about Modal, what Modal can do better, and more.

5.0

Based on 67 reviews

Review Modal?

Reviewers, mostly founders, describe Modal as a practical way to run serious compute without building or babysitting infrastructure. Makers of Fathom, viktor.com, and Cartesia Sonic are especially positive about fast spin-up, clean Python-first workflows, reliable sandboxes, and easy scaling up or down. Across reviews, common use cases include GPU training, inference, code execution, and background workers. There is little critical feedback here, so the picture is narrow but consistently favorable.

+65

Summarized with AI

Pros

inference at scale (4)

training pipelines (3)

cold start management (2)

fine-tuning models (2)

Python hosting (2)

scalable GPU serving (2)

Pros

Cons

AWS Startup AdvisorPersonalized AWS guidance that meets you where you’re already building

Promoted

Reviews

All Reviews

Most Informative

used Modal to build Reactive Workflows [LW24]

•8 reviews

Modals VM's power our AI agent environments, allowing them to view pull requests, inspect files, and even execute code! Thanks to the Modal team for prioritizing our feature requests and building a GREAT headless compute environment.

What's great

headless compute environment (1)

Report

29 views2yr ago

used Modal to build FlexChords

•4 reviews

Modal was a game-changer for FlexChords. Scaling GPU-intensive workloads with zero cold-start headaches and deploying directly from Python saved us weeks of infrastructure work. It simply works.

Alternatives Considered

Report

7 views1mo ago

used Modal to build RunLLM

•19 reviews

Modal helps us spin up Python workloads with speed and control. Great for agents that need to run fast, ephemeral jobs. A dream for short-lived compute without DevOps overhead.

Report

10 views1yr ago

used Modal to build Relace Repos

•1 review

Serverless GPU infrastructure helps us scale to workloads of hundreds of H200s/B200s within seconds to maintain low latency for our retrieval models in a cost-effective way.

Report

13 views1yr ago

used Modal to build Face Animator

•6 reviews

We run our models on Modal. Amazing DX, brilliantly documented API, and very fast and helpful support on their Slack.

What's great

excellent documentation (1)fast support (1)

Report

6 views2yr ago

used Modal to build Scoopika

•5 reviews

We use Modal to serve TTS and embedding models with scalable GPU power

Report

4 views2yr ago

used Modal to build AnythingLLM

•6 reviews

For when you want to quickly spin-off a fine-tuned model from AnythingLLM. There is no easier way to build that pipeline we offer in-app than using Modal Labs for creating fine-tuning jobs on powerful GPUs for a fair price.

What's great

scalable GPU serving (2)training pipelines (3)fine-tuning models (2)

Report

3 views2yr ago

used Modal to build ScaryStories Live

•7 reviews

Huge shoutout to Modal! The cloud infrastructure made spinning up AI and ML tasks for ScaryStories.Live effortlessly. We couldn’t have scaled our real-time horror experiences without you. We’re truly grateful for your generous support in our early days!

Report

8 views1yr ago

used Modal to build SnowSEO 2.0

•6 reviews

Modal helped us train our model to generate human-like content, we developed state-of-the-art content engine that writes content indistinguishable from the one written by subject-expert human.

What's great

training pipelines (3)

Report

1yr ago

used Modal to build Viktor for Microsoft Teams

•9 reviews

Viktor runs its agents server-side, 24/7, which means spinning up isolated sandboxes for thousands of teams at once and scaling back to zero the moment they go idle. We looked at rolling our own on Kubernetes and at the usual serverless suspects. Modal was the only one where a Python engineer could define the whole sandbox, schedule, and scaling story in code and ship it the same afternoon. It is a big part of why a small team can run this much compute without standing up a platform team to babysit it.

Alternatives Considered

Report

6 views5mo ago

1 2 3

•••