Runloop

https://runloop.ai

Runloop is a platform for building and deploying AI software-engineering agents, centered on Devboxes — isolated Linux microVMs that run agent-generated code. It targets AI engineering teams that need persistent filesystems, Docker support, and snapshot/suspend/resume lifecycle control for long-running agent workloads.

Pricing model Per-second (and per-hour) usage-based billing on reserved CPU and memory while running
Pricing The headline compute price as the provider states it. Sorting ranks prices stated per vCPU over time, converted to hourly. Other pricing models sort after, unranked. $0.108 per CPU-hour (plus $0.0252 per GB-hour of memory)
Free while idle Whether a stopped, paused, or sleeping sandbox costs nothing.
Elastic Resources flex with what the sandbox actually uses, and the bill follows: yes when the provider bills on active or observed use, no when capacity is reserved or allocated and billed while it runs.
Memory snapshots Whether RAM state survives a pause and resume, not just disk.
Wake on request Whether a stopped sandbox wakes automatically on inbound traffic.
Start / resume Typical time from create or resume to running. Sorting ranks stated times, converted to seconds; claims with no figure sort after, unranked. A few seconds to first command; suspend/resume typically takes seconds, depending on modified data
Max runtime The longest a sandbox may run. Default 1 h, configurable
Isolation The isolation technology between sandboxes. Linux microVM with hardware isolation (two-layer VM + container)
GPUs Whether GPU instances are available for sandboxes.
Docker Whether Docker containers can run inside the sandbox.
SDKs Python, TypeScript

✓ yes · ✕ no · – no cited public fact.

Suspended devboxes continue to incur storage charges until explicitly shut down; snapshots preserve disk state only, not in-memory state.

Sources

Last verified 2026-08-19. Corrections land through the update log.