Modal Sandboxes
Modal LabsModal Sandboxes runs untrusted or agent-generated code in gVisor-isolated containers on Modal's serverless cloud, created at runtime from the Python, JavaScript or Go SDK. A sandbox can be built from an arbitrary container image, looked up later by name, given GPUs, and held open for anything from the five-minute default to twenty-four hours. Compute is billed by the core-second.
Modal bills Sandbox compute at a separate rate from its Function compute, so the plan tiers on the pricing page describe the surrounding platform rather than the sandbox itself. Verified 2026-08-13 via the Modal Sandboxes guide and the Modal pricing page.
Openness
1 high confidence- license
- Proprietary
- source
- closed
- service
- proprietary Modal managed cloud (no self-host of the gVisor execution plane)
- open-part
- client SDK only (modal Python/JS client libraries)
- pricing
- pay-as-you-go usage, free starter credits
Closed managed service. The client SDK is open, but the execution substrate is a proprietary managed cloud with no self-host option, and an open client over a closed runtime is not open core. The contrast with E2B is the point: E2B ships self-hostable infrastructure, Modal does not.
- https://modal.com/pricing recorded 2026-06-04
Modal is a managed proprietary cloud platform, pay-per-CPU-cycle, $30/mo free credits
- https://modal.com/docs/guide/sandbox recorded 2026-06-04
Sandboxes = secure containers for untrusted agent code, driven via Modal SDK
- https://modal.com/pricing recorded 2026-08-13
Three plans - Starter ($0 + compute, $30/mo free credits), Team ($250 + compute) and Enterprise (custom) - all metered against Modal's own cloud, with a separate Sandbox and Notebooks compute rate per core-second and GiB-second. Nothing on the page offers a self-hosted, on-premises or source-available deployment.
- https://modal.com/docs/guide/sandbox recorded 2026-08-13
Redirects to /docs/guide/sandboxes. Sandboxes are still "secure containers for executing untrusted user or agent code on Modal", created only through the Python, JavaScript or Go SDK against Modal's service; no runtime is distributed to run elsewhere.
Adoption
3 low confidenceNo Modal Sandboxes user or usage count is disclosed on the primary pages; Modal is a well-known managed AI-compute platform with broad developer use and a documented free tier. Placed at 3 on reported multi-customer traction rather than on a measured figure, kept conservative in the absence of a hard number. The nearest figure Modal publishes is platform-wide rather than per-product - its sandbox comparison page claims Modal "powers infrastructure for over 10,000 teams" and names Lovable and Quora as production users running untrusted code - which is another reported-traction claim rather than a count of Sandboxes use, so no reach figure is recorded.
- https://modal.com/docs/guide/sandbox recorded 2026-06-04
documented production sandbox feature on a widely-used managed platform
- https://modal.com/resources/best-code-execution-sandboxes-ai-agents recorded 2026-08-13
'Modal powers infrastructure for over 10,000 teams, with production users like Lovable and Quora running millions of untrusted code snippets daily'. No Sandboxes-specific user or usage count is given.
- https://modal.com/docs/guide/sandbox recorded 2026-08-13
Sandboxes guide publishes lifecycle, image and timeout documentation and no usage, session or customer count.
Capability
4 medium confidenceStrong, purpose-built agent sandbox: gVisor isolation, arbitrary images and high concurrency. The Sandboxes guide documents arbitrary custom images, named lookup and a 5-minute default lifetime extendable to 24 hours, and Modal’s own comparison page states gVisor isolation and 50,000+ concurrent sessions. It sits just below the Firecracker-microVM frontier (Lambda, Vercel) on isolation strength, so 4 - level with the Ray and Ollama capability anchors. Independent ComputeSDK TTI benchmarks put Modal at a 0.76s median cold-start, 0.82s P95, composite 92.1, 14th by median of 24 providers, against ~470ms and 13th of 19 on the earlier run: slower in absolute terms and unchanged in placement, still mid-field, still short of the sub-0.3s leaders and well clear of the multi-second tail.
- https://modal.com/docs/guide/sandbox recorded 2026-06-04
sandbox lifecycle, custom images, timeouts up to 24h, untrusted-code execution
- https://modal.com/resources/best-code-execution-sandboxes-ai-agents recorded 2026-06-04
gVisor user-space kernel isolation, 50,000+ concurrent sessions (corroborating)
- https://www.computesdk.com/benchmarks/sandboxes/ recorded 2026-07-09
ComputeSDK TTI leaderboard (independent, 100 iters/day, 2026-07-09 run): median time-to-interactive ~470ms sequential / ~570ms burst @100 concurrent; 13th of 19 providers
- https://modal.com/docs/guide/sandbox recorded 2026-08-13
Sandbox lifecycle through the SDK, arbitrary custom images, named/ID lookup, 5-minute default timeout extendable to 24 hours, untrusted-code framing.
- https://modal.com/resources/best-code-execution-sandboxes-ai-agents recorded 2026-08-13
Still states gVisor container isolation for Modal against microVM competitors, and "can scale to 50,000+ concurrent sessions".
- https://www.computesdk.com/benchmarks/sandboxes/ recorded 2026-08-13
ComputeSDK TTI leaderboard, run of 2026-08-07 across 24 providers - Modal median 0.76s, P95 0.82s, P99 0.85s, 100% success, composite 92.1; 14th of 24 by median.
Verified 2026-08-13