Modal Sandboxes are generally available
Jan 21, 2025

Summary
This post announces the general availability of Modal Sandboxes, a primitive for safely running untrusted code. It details the `exec` API for executing code in arbitrary languages, dynamic image configuration using the `Image` API, and filesystem snapshots for persistence. It highlights customer use cases like SWE-bench for agent benchmarks, Quora Poe for secure code execution, Codegen for large-scale refactors, and Relevance AI for AI workforce automation. Performance testing demonstrated sandbox creation throughput up to 1000 Sandboxes per second.
More from the Sandboxed Code Execution trail
- Runtime Roundup: VM Sandboxes, Multi-node clusters, and more | Modal Blog
- VM Sandboxes: Full computers for agents | Modal Blog
- Sidecars: A low-latency trust boundary for Sandboxes | Modal Blog
- Product updates: Sandbox Sidecars, new models, a refreshed dashboard, and more | Modal Blog
- Devin Outposts on Modal | Modal Blog