Modal

Scalable AI coding platform built on Modal that generates sandboxed React apps via LLM prompts.

High-performance distributed file system for Modal applications, optimized for write-once, read-many I/O workloads.

Modal's sandboxed compute primitive for running untrusted code in isolated containers.

Hosted Jupyter notebooks running serverless Python in Modal's cloud with GPU access, collaborative editing, and automatic idle shutdown.

Deploy production-ready LLM inference endpoints on Modal's managed infrastructure with a single command.

Serverless GPU cloud platform for running and deploying machine learning workloads.

Secure containers for executing untrusted user or agent code on Modal with lifecycle events, probes, and configurable timeouts.

Beta version of Modal Volumes with improved scalability, concurrent writes, and random access performance.

Distributed FIFO queues for Modal Apps with partitioned keys and sync/async access.

Run LLM inference at maximum throughput This example demonstrates some techniques for running LLM inference at the highest possible throughput on Modal.

Distributed, persisted key-value storage for Modal Apps, like Python dicts in the cloud.

Python SDK for Modal, providing the Environment API for managing environments, roles, and billing.

Voice chat example app built on Modal using Kyutai Lab's Moshi speech-to-speech model.