Serverless GPU and microVM sandboxes for AI agents, coding loops, and RL rollouts with $30/mo free Starter credits, elastic burst billing, and filesystem/memory snapshots.

Visit Modal Sandboxes

At a glance

  • From $30/mo
  • DR 81

Best for GPU-heavy coding agents, RL rollouts, and teams using elastic burst limits to avoid idle-wait overbilling.

Serverless gVisor and VM sandboxes with massive GPU parallelism and elastic idle billing ($4.44 per 1,000 85%-idle runs), offset by a 3x non-preemptible rate multiplier and OAuth+card signup gate.

Pros

  • Elastic burst floor drops idle LLM-wait compute to $0.0207/hr ($4.44 per 1,000 5-min runs)
  • Supports both gVisor (GPUs) and full VM sandboxes (512 GiB root, Docker-in-Sandbox)
  • 1 TiB/mo free egress on Starter and massive parallel GPU scale up to 5,000 containers on Team

Cons

  • CPU Sandboxes carry a 3x multiplier over base Modal Function rates ($0.07074/vCPU-hr)
  • Hard-reserving cores causes a 9.2x idle-wait cost jump vs elastic default floor
  • OAuth-only signup (no email/password) and credit card required to unlock $30/mo Starter credits

Pricing

From $30/mo

$0/mo Starter ($30/mo free credits, card req), $250/mo Team ($100/mo credits), 3x base rate on CPU Sandboxes ($0.07074/vCPU-hr)

Modal Sandboxes run untrusted AI-generated code, coding agents, and heavy GPU workloads inside isolated serverless containers (gvisor) and microVMs (vm, up to 512 GiB root with Docker-in-Sandbox).

Modal Sandboxes pricing and compute plans

What stands out in our November 2026 audit

Modal owns the heavy GPU and reinforcement-learning end of the sandbox market, combining fast parallel containers with H100/A100/B200 burst capacity, Filesystem Snapshots (30-day TTL), and Memory Snapshots (7-day TTL).

The 3x Sandbox Multiplier and Idle-Tax Math

Buried in Modal's sandbox pricing FAQ is a crucial billing detail: because CPU Sandboxes are non-preemptible, they are billed at 3x base Modal Function CPU and memory list rates ($0.07074/vCPU-hr and $0.023976/GiB-hr).

Modal Sandboxes pricing FAQ detailing 3x non-preemptible multiplier

Modal's saving grace for LLM agents is its elastic floor (max(request, actual)). On the default 0.125 physical core / 128 MiB floor, a sandbox waiting on LLM tokens costs only $0.0207/hr ($4.44 across 1,000 five-minute 85%-idle agent runs). If you hard-reserve 1 core / 2 GiB, idle cost jumps 9.2x to $0.1894/hr ($19.78 per 1,000 runs).

Signup friction & pricing

  • Starter ($0/mo + $30/mo free credits): 3 seats, 100 containers + 10 GPUs, 1 TiB/mo free egress. Requires GitHub/Google/SSO OAuth plus a credit card on file.
  • Team ($250/mo + usage): $100/mo free credits, 5,000 containers + 50 GPUs, 10 TiB/mo egress.
  • Verified signup gate (Nov 23, 2026): modal.com/signup offers zero email/password signup (OAuth only) and loads invisible hCaptcha.

Modal signup screen showing OAuth-only registration

Verdict

Modal is the strongest pick when your coding agents or RL evals need massive parallel bursts, GPUs, or Docker-in-Sandbox microVMs. Just stick to elastic bursting instead of hard-reserving cores so the 3x non-preemptible multiplier does not wreck your idle-wait bill.

Editorial Standards & Proof

Reviewed 2026-11-22
Ilias Ism
Reviewed byIlias IsmFounder & Lead Reviewer

Software engineer and founder (15+ years building web apps). Every listing is verified against live product checks, official pricing pages, and real usage limits before publication.

Product checks
Live domain, active software, and editorial review passed
Editorial independence
Zero paid verdicts; pros, cons, and limits are checked directly
Last updated

Share:

Similar to Modal Sandboxes