Modal

Name: Modal
Author: Modal

Serverless Python compute with GPUs, built for inference and heavy ML workloads.

Docs Website

Overview

Modal turns a decorated Python function into serverless infrastructure, including GPU-backed inference. For agents it fills the heavier end of execution — model calls, batch jobs, and pipelines that need real compute and persistent volumes rather than a short-lived shell.

Why it's indexed

The option when the sandboxed work needs a GPU, not just a shell.

Editorial judgement, not a measurement — see our methodology. Listing is never paid for.

At a glance

Vendor: Modal
Category: AI Sandboxes
License: Proprietary
Deployment: Hosted
Languages: Python
Pricing model: Free tier · Usage-based

Pricing is shown as a model, not a rate. Published rates change without notice — check the vendor's own page before budgeting.

Also in AI Sandboxes

E2B

Firecracker microVM sandboxes purpose-built for running AI-generated code.

Daytona

Fast, stateful development environments for agents that need to persist a workspace.

Northflank

Production platform with microVM isolation and bring-your-own-cloud deployment.