Skip to content
GroundboxGroundmail
Groundbox
PricingDocs
Sign inStart free, no card

CI

CI runnersGitHub Actions runnersGitLab runnersGitLab CI, a third of the priceFlexHalf price, when there is roomCI tune-upOne pull request, faster CIInsightsTime, cost and size per jobTest analyticsFlaky and slow testsLogs and terminalsLive logs, a shell on a job

Builds

Build cacheTurborepo, Gradle, sccache, Bazel, NxDocker buildsA remote builderImage registryBeside your runnersStorageS3-compatible buckets

Sandboxes

SandboxesA VM for each agentTime machineSave points, rewind, forkTemplates and volumesBuild the disk oncePreviewsA URL for a portScheduled runsCron for a command

Agents

For agentsKeys, scopes, spend capsAgent computersA desktop for computer use
CI and sandboxes, one bill$20a month, $20 of usage included →
All prices →Benchmark →

Build

DocsQuickstarts and guidesAPI referenceREST endpointsCLIEvery command takes --json

Connect

MCP serverFor coding agentsSDKsTypeScript and PythonAPI explorerSend requests with your key
All docs →contact@groundbox.dev →

Compare

All comparisonsEvery sandbox and CI runner, side by sidevs GitHub-hostedMeasured on 10 open-source projectsvs E2BHalf the hourly price, memory includedMove from RunloopEvery call mapped, step by step

Guides

GitHub Actions runnersSizes, labels and what they costGitHub Actions cacheMake cached steps fastGitHub Actions costHow minutes are billed, with examplesGitLab runnersExecutors, setup, hosted vs your ownGitLab compute minutesCalculator: GitLab.com vs GroundboxAI agent sandboxesWhat to look for when you pick one

Proof and help

BenchmarkMethod, scripts and raw timingsCI cost checkerPoint it at your GitHub org, see what you'd payStatusUptime and start timesTalk to usBook a call with the team
All comparisons →Benchmark →
Products

CI

CI runnersGitHub Actions runnersGitLab runnersGitLab CI, a third of the priceFlexHalf price, when there is roomCI tune-upOne pull request, faster CIInsightsTime, cost and size per jobTest analyticsFlaky and slow testsLogs and terminalsLive logs, a shell on a job

Builds

Build cacheTurborepo, Gradle, sccache, Bazel, NxDocker buildsA remote builderImage registryBeside your runnersStorageS3-compatible buckets

Sandboxes

SandboxesA VM for each agentTime machineSave points, rewind, forkTemplates and volumesBuild the disk oncePreviewsA URL for a portScheduled runsCron for a command

Agents

For agentsKeys, scopes, spend capsAgent computersA desktop for computer use
Developers

Build

DocsQuickstarts and guidesAPI referenceREST endpointsCLIEvery command takes --json

Connect

MCP serverFor coding agentsSDKsTypeScript and PythonAPI explorerSend requests with your key
Resources

Compare

All comparisonsEvery sandbox and CI runner, side by sidevs GitHub-hostedMeasured on 10 open-source projectsvs E2BHalf the hourly price, memory includedMove from RunloopEvery call mapped, step by step

Guides

GitHub Actions runnersSizes, labels and what they costGitHub Actions cacheMake cached steps fastGitHub Actions costHow minutes are billed, with examplesGitLab runnersExecutors, setup, hosted vs your ownGitLab compute minutesCalculator: GitLab.com vs GroundboxAI agent sandboxesWhat to look for when you pick one

Proof and help

BenchmarkMethod, scripts and raw timingsCI cost checkerPoint it at your GitHub org, see what you'd payStatusUptime and start timesTalk to usBook a call with the team
PricingDocs
Start free, no cardSign in
GroundboxGitHub Actions runners and Linux sandboxes for AI agents. One key, one bill.System status

Product

CI runnersSandboxesBuilds and cacheAgent computersPricing

Developers

DocsAPI referenceAPI explorerCLIMCP serverBenchmark

Compare

vs GitHub-hostedvs Blacksmithvs E2Bvs DaytonaAll comparisons

Company

Talk to usSupportcontact@groundbox.devGroundmail ↗
© 2026 Groundbox
TermsPrivacyllms.txt
  1. Home
  2. Compare
  3. Tensorlake

Groundbox vs Tensorlake for agent sandboxes.

Both run sandboxes for agents as Firecracker microVMs that keep memory when paused, and both also run GitHub Actions jobs. Pick Tensorlake for memory snapshots that start many warm copies, CPU billed only while busy, GPU sandboxes, or a SOC 2 Type 2 report. Pick Groundbox for memory included in the CPU price, a lower price per hour while the CPU is busy, and a spend cap and scopes on every API key.

Start free, no cardHow to switch
2 vCPU · 4 GB, one hourlist prices
Groundbox$0.08 / hour
Tensorlake$0.088 to $0.20 / hour

Tensorlake bills CPU only while busy; the bar is the busy end.

sources: groundbox.dev/pricing · docs.tensorlake.ai · checked 2026-11-20

Side by side

Groundbox and Tensorlake
FeatureGroundboxTensorlake
Price, 2 vCPU · 4 GB$0.08 / hour$0.088 to $0.20 / hour
Pause keeps memoryYes, memory and diskYes, memory and running processes
CI runners tooYes, on the same key and billYes, GitHub Actions runners
IsolationFirecracker VMFirecracker microVM
Fork and snapshotsFork a running sandbox; save pointsMemory snapshots and warm copies
Longest session720 hours, renewableNo limit on Pro; 24 hours on credits, 2 hours free
Self-hostNoIn your VPC or on-prem, on Enterprise
GPUsNot offeredH100, by request
Largest size16 vCPU16 vCPU on Pro
SDK languagesTypeScript and PythonPython and TypeScript
Security reportNo SOC 2 reportSOC 2 Type 2; HIPAA on Pro
Free to start$5 of usage, no card1 sandbox, 2-hour sessions, no card

Tensorlake runs sandboxes for agents as Firecracker microVMs with memory snapshots, and also runs GitHub Actions jobs. A rust mark means that side is ahead. Where they are ahead, we say so. Every value of theirs links to the page it is from; “Not published” means their pages do not say. More comparisons: all comparisons.

Who each is for

Pick Tensorlake for

  • memory snapshots that start many warm copies of one sandbox
  • CPU billed only while busy, with a floor of 20% of the cores
  • GPU sandboxes (H100, by request), and in-VPC or on-prem on Enterprise
  • a SOC 2 Type 2 report on every tier, and HIPAA on Pro

Pick Groundbox for

  • memory included in the CPU price ($0.04 per vCPU-hour), on dedicated cores
  • pause, fork and save points of a running sandbox, and an egress allowlist
  • a spend cap and scopes on every API key

Every detail

Every row: Groundbox and Tensorlake
FeatureGroundboxTensorlake
PlansFree: everything, with $5 of usage. $20 / month: $20 of usage included, then pay as you goFree; prepaid usage credits from $5; Pro $250 / month
CPU$0.04 per vCPU-hour, a dedicated core$0.07 per active core-hour on credits, $0.042 on Pro; at least 20% of the cores is billed
MemoryIncluded, up to 4 GB per vCPU$0.015 per GB-hour on credits, $0.009 on Pro, billed apart from CPU
Storage20 GB disk by default, up to 100 GBRoot disk $0.0002 per GB-hour; snapshots $0.07 per GB-month
BillingPer second, no minimumPer second
Sizes1 to 16 vCPU, up to 4 GB per vCPUUp to 4 vCPU on credits and 16 on Pro, 1 to 8 GB per vCPU
Default size2 vCPU, 4 GB RAM, 20 GB disk1 vCPU, 1 GB RAM, 10 GiB disk
Longest session720 hours, renewable; 60 minutes by default2 hours free, 24 hours on credits, no limit on Pro
Sandboxes at once20 once a card is on file1 free, 100 on credits, 1,000 on Pro
IsolationA Firecracker VM, a new one per job or sandboxFirecracker microVMs; GPU sandboxes use gVisor
Pause and resumeYes, memory and disk; $0.05 per GB-month while pausedNamed sandboxes keep files, memory and running processes
Fork and snapshotsFork a running sandbox with its files and processes; save points to rewind toFilesystem or memory snapshots; many warm copies of one sandbox
Egress controlsAn allowlist of hosts per sandboxAllow and deny lists by domain, IP or CIDR, changeable while running
GPUsNot offeredH100, by request
SDKsTypeScript and Python, plus a REST API, CLI and MCP serverPython and TypeScript, plus a CLI
CI runnersGitHub Actions runners on the same key and billGitHub Actions runners, picked with runs-on: tensorlake-medium
Self-hostNoIn your VPC or on-prem, on Enterprise
Security reportsNo SOC 2 reportSOC 2 Type 2 on every tier; HIPAA with a BAA on Pro

A month at list price

One sandbox with 2 vCPU and 4 GiB of memory, running 100 hours in a month:

One sandbox with 2 vCPU and 4 GiB of memory, running 100 hours in a month: Groundbox and Tensorlake
Groundbox$8.00 ($0.04 per vCPU-hour, memory included). On the $20 plan it fits in the $20 of usage included.
Tensorlake$8.80 to $20.00, from CPU at its 20% floor the whole time to CPU busy the whole time

At Tensorlake's usage-credit rates. Its Pro rates are lower ($0.042 per core-hour, $0.009 per GB-hour), with $250 a month on top. Disk is billed apart and not counted. All our prices are on the pricing page.

Speed

We have not measured this service's sandboxes, and we publish no start or fork times for ours, so this page makes no speed claim. The speed figures we do publish are for CI runners, on the benchmark page. Method, scripts and every project's times: the benchmark page.

Switch in four steps

  1. Create an API key in the dashboard. An agent can also sign itself up with groundbox signup and send its person a claim link.
  2. Install an SDK: npm i @groundbox/sdk or pip install groundbox.
  3. Where your code creates a sandbox and runs a command in it, call create_sandbox and run_command. Files, fork, pause and stop have one method each, with the same names as the MCP tools.
  4. Or give the agent the MCP server instead of SDK code: it has the same tools.

Details in the docs: First sandbox, the SDKs and the MCP server.

import { Groundbox } from "@groundbox/sdk";

const groundbox = new Groundbox(); // reads GROUNDBOX_API_KEY
const sandbox = await groundbox.create_sandbox({ cpus: 2 });
const result = await groundbox.run_command(sandbox.id, "uname -a");

Questions

Is Groundbox cheaper than Tensorlake?At list price, one 2 vCPU, 4 GiB sandbox for 100 hours costs $8.00 on Groundbox and $8.80 to $20.00 on Tensorlake, before plan fees and credits. Tensorlake bills CPU only while busy, so a mostly idle sandbox can cost about the same as on Groundbox.
How do I move an agent from Tensorlake to Groundbox?Create an API key, install the TypeScript or Python SDK, and call create_sandbox and run_command where your code makes a sandbox and runs a command. The MCP server has the same tools.
How are sandboxes isolated on Groundbox and on Tensorlake?Each Groundbox sandbox is its own Firecracker VM on dedicated cores. Tensorlake CPU sandboxes are Firecracker microVMs too; its GPU sandboxes use gVisor.
Can a Groundbox sandbox pause and fork?Yes. Pause keeps memory and disk and costs $0.05 per GB-month. Fork copies a running sandbox's files and processes.
How long can a Groundbox sandbox run?It stops after 60 minutes by default. The longest timeout is 720 hours, and it can be renewed. A Tensorlake session lasts up to 2 hours on the free tier and 24 hours on usage credits, with no limit on Pro.
Does Groundbox also run CI?Yes. GitHub Actions runners from $0.003 a minute are on the same API key and bill as sandboxes.

Sources

Tensorlake's facts come from its own pages, read on the day shown. Prices change; their pages are the final word.

  • Tensorlake pricing, checked 2026-11-20
  • Tensorlake docs, checked 2026-11-20
  • Tensorlake docs: billing, checked 2026-11-20
  • Tensorlake docs: sandbox lifecycle, checked 2026-11-20
  • Tensorlake docs: snapshots, checked 2026-11-20
  • Tensorlake docs: networking, checked 2026-11-20
  • Tensorlake docs: GPU sandboxes, checked 2026-11-20
  • Tensorlake docs: quickstart, checked 2026-11-20
  • Tensorlake docs: GitHub Actions, checked 2026-11-20

Also compared

Blaxel vs TensorlakeCloudflare Sandboxes vs TensorlakeCodeSandbox SDK vs TensorlakeDaytona vs TensorlakeE2B vs TensorlakeFly.io Machines vs TensorlakeModal vs TensorlakeNorthflank vs TensorlakeTensorlake vs Vercel SandboxGroundbox vs E2BGroundbox vs BlaxelGroundbox vs ModalSandboxes for agentsPricingFirst sandboxAll comparisons

Try it on your own repo.

Start free, no cardBook a call