Serverless compute platform for AI with custom Rust-based infrastructure that spins up GPU-enabled containers in one second, supporting Python workloads with per-second billing.
Loading more......
Modal is a serverless compute platform for AI, ML, and data teams that makes it easy for developers to run workloads like ML inference, fine-tuning, and batch data jobs in the cloud. Modal is a serverless cloud platform for running Python code with GPU acceleration where you write Python with Modal decorators, and Modal handles provisioning, scaling, and teardown.
Modal's custom infrastructure allows them to spin up GPU-enabled containers in as little as one second, helping you iterate fast and scale up to large production workloads. Built from scratch with a Rust-based backend, the platform supports rapid container launches, dynamic scaling, and GPU-intensive workloads.
The innovation in Modal's product offering comes from its custom Rust-based container, efficient image building, and implementation of a customer filesystem with FUSE using a process known as lazy loading.
Modal's product line includes Modal Inference, Modal Sandboxes, Modal Training, Modal Notebooks, Modal Batch, and Modal Core Platform.
Modal scales resources up and down for you so you only ever pay for what you use. Modal offers $30 / month free compute credits on their starter plan. Per-second GPU billing is available, with H100 at ~$3.95/hr and A100 80GB at ~$2.50/hr.
The company has raised $32 million as of April 2024, reports usage across more than 100 enterprise customers, and positions itself within a growing market for container-based AI infrastructure projected to reach over $96 billion by 2027.
Modal continues to be actively used in 2026 as a leading serverless GPU platform for AI and machine learning workloads.
Modal integrates with smolagents framework for executing AI agent code in sandboxed environments.