Run gpt-oss, OpenAI's new open weights model. Run now

Modal Sandboxes

Run AI-generated code in secure, dynamically defined sandboxes. Scale to 10,000+ simultaneous sessions with ease.

“Using Modal, Codegen has been able to move at lightning speed with full-stack AI development. The product is designed with developer experience front and center, and my team is incredibly happy having it as part of our arsenal.”

Jay Hack, Founder & CEO

“We use Modal to securely run LLM-augmented code on a large scale. Modal’s powerful primitives like sandboxes and file systems have allowed us to focus on our core competencies without having to waste time on our own infra.”

Matt Harpe, Co-Founder

“Modal Sandboxes enable us to execute generated code securely and flexibly. With Modal's support, we expedited the development of our code interpreter feature and successfully integrated it into our chat platform, Le Chat, to better assist our users.”

Wendy Shang, AI Scientist

Modal Sandbox Pricing

Only pay for what you use, by the CPU cycle. For GPU Sandboxes, refer to our standard GPU prices.

View full pricing

Compute costs

CPU

Physical core
(2 vCPU equivalent)

$0.00003942 / core / sec

*minimum of 0.125 cores per container

Memory

$0.00000672 / GiB / sec

Safe code execution

Execution of AI-generated code

Run code snippets created by language models or submitted by users in a secure environment.

LLM evaluations

Test the latest LLM models for safety and quality.

gVisor-based runtime

Rely on strict security and isolation guarantees from our battle-tested containerization technology.

Fully programmable container environment

Universal code execution

Orchestrate and run any kind of code or container image, even if it's not Python-based.

Out of the box interactivity

Execute processes in an ongoing sandbox session, and get input/output streaming with each.

Advanced sandbox features

Persistent data management

Maintain stateful data across sessions with dynamically-provisioned network file systems.

Network accessibility

Create tunnels to expose ports inside the sandbox.

Network security

Control over outbound networking.

Try it out

Sandbox a LangGraph agent's code

Run an LLM coding agent that runs its own language models

Build a stateful, sandboxed code interpreter

Execute untrusted Python code in a sandboxed environment

Safely run untrusted Node.js, Ruby, PHP, and more

Execute arbitrary code in your language of choice inside a Sandbox

Run a sandboxed Jupyter notebook

Set up a sandboxed Jupyter server and issue commands via an API

Ship your first app in minutes.

$30 / month free compute