Isorun
$19.36 a month*
Home / AI agent sandboxes / Render Sandboxes
Firecracker microVMs on Render that suspend when idle, billed for active CPU time plus provisioned memory.
Verdict (2026-11-14): Render Sandboxes scores 63/100, #32 of 63 AI agent sandboxes. Strong on isolation, persistence, docs and SDKs. Weak on free tier. Best for: Agent work that waits on model or API calls, since idle CPU is not billed and idle sandboxes suspend.
Skip it if: Public beta, with one region (Oregon) and limits that may change.
Prices checked 2026-11-15.
Render Sandboxes run each sandbox in its own Firecracker microVM, created and driven from the Render CLI, the TypeScript or Python SDK, or the API. CPU is billed at $0.12 per active CPU hour and memory at a fixed hourly rate for the compute plan's RAM while the sandbox runs; a suspended sandbox has no compute charge. By default a sandbox suspends after 15 minutes without commands or file transfers and resumes on the next one, and both the idle and runtime timeouts can be turned off so a sandbox runs indefinitely. The product is in public beta and runs in one region (Oregon).
63/100 in AI agent sandboxes, rank 32 of 63. Parts with no data are left out and the rest is rescaled.
Full Render Sandboxes pricing: plans and costs at four workloads →
$19.36 a month*
$11.73 a month*
$10.14 a month*
$19.00 a month*
$17.95 a month*
$28.44 a month*
$20.00 a month*
$20.00 a month*
Render Sandboxes is not in the public benchmarks we track yet. See all benchmarks.
| Render Sandboxes | |
|---|---|
| Category | agent sandbox, dev box |
| Our score | 63/100 |
| Isolation | Firecracker microVM per sandbox |
| vCPU per hour | $0.12 (active CPU only) |
| Memory per GiB-hour | $0.019 |
| Storage per GiB-month | $0.08 |
| Billing | prorated to the second (Render's general compute billing rule; no separate increment stated for sandboxes) |
| Free tier | No free sandbox usage is stated. The Hobby workspace has no monthly fee, but sandbox compute is billed at the usage rates; Render's free compute plans cover web services, Key Value and Postgres only. |
| Pause and resume | Yes |
| Snapshots | Yes |
| Custom images | Yes |
| Network controls | Yes |
| Max vCPU | 8 vCPU |
| Max memory | 16 GiB |
| Open source | No |
| Self-host | No |
| SDKs and interfaces | TypeScript, Python, CLI, REST API |
| Regions | 1 region during the beta: Oregon. |
| Facts checked | 2026-11-14 |
No reviews yet. Have you used Render Sandboxes? Your review helps other developers choose.
Render Sandboxes scores 63/100, #32 of 63 AI agent sandboxes. Strong on isolation, persistence, docs and SDKs. Weak on free tier. Best for: Agent work that waits on model or API calls, since idle CPU is not billed and idle sandboxes suspend. Facts checked 2026-11-14.
$26.05 a month for 2 vCPU, 4 GiB, 176 hours a month (8 h × 22 days), CPU busy 30%. Free tier: No free sandbox usage is stated. The Hobby workspace has no monthly fee, but sandbox compute is billed at the usage rates; Render's free compute plans cover web services, Key Value and Postgres only.
Firecracker microVM per sandbox.
In AI agent sandboxes, the top-rated are Isorun (78/100), Northflank (78/100), Koyeb Sandboxes (76/100). Render Sandboxes is #32 of 63.
Billing for active CPU time + provisioned memory
$0.12 / active CPU hour | 2 GB RAM | $0.038/hour for provisioned memory | 1c-2g
$0.12 / active CPU hour | 16 GB RAM | $0.304/hour for provisioned memory | 8c-16g
Snapshot storage for $0.08/GB per month
Pro | $25/month + compute
Default limit of 1,000 concurrent sandboxes on Pro, Scale workspaces
billing is prorated to the second
Each Render sandbox runs in its own Firecracker microVM
While a sandbox runs, you pay for the CPU it actively uses and the memory in its compute plan. A suspended sandbox has no compute charges.
Render Sandboxes is in public beta.
1 (Oregon)
40 GB
For a new sandbox, defaults to `900` (15 minutes)
To run a sandbox indefinitely, set both of these timeouts to `0`.