Skip to content
where do irun this.

Code & AI agent sandboxes: read the guide

Vercel Sandbox

HostedSandbox

The safest way to run code you didn’t write

HomepageDocsPricingRepository

Scanned 12 Oct 2026 · Schema v5 · features v21

From
$20/mo per seat

Hobby free personal/non-commercial; Pro $20 per developer seat/month plus usage ($20 included usage credit); Enterprise custom. Sandbox meters active CPU, allocated memory, creations, data transfer, snapshots and Drives.

Free tier
Not documented

Hobby: 5 active CPU-hours/month, 420 GB-memory-hours/month, 5,000 creations/month, 20 GB transfer/month, 15 GB lifetime snapshot storage; 15 GB lifetime Drive storage and 30 GB reads/writes/month.

Isolation
Firecracker microVM

shares only the hypervisor

Regions
19

Stockholm, Sweden · Mumbai, India · Paris, France · Cleveland, USA · Cape Town, South Africa · Dublin, Ireland +13

Capabilities
22 / 61

3 partial · 36 fail · 0 not assessed

Agent readiness
9/11 · 9.5/11

read · drive, pre-login surface

Advertised for

Untrusted/AI generated code · Coding agent execution · Isolated tests and app previews · Linux commands and privileged Docker/FUSE

Built for

Developers, then technical

  • · SDK/CLI code-first setup
  • · Untrusted code / Firecracker isolation
  • · Active CPU and memory metering

01 Pricing Hobby free personal/non-commercial; Pro $20 per developer seat/month plus usage ($20 included usage credit); Enterprise custom. Sandbox meters active CPU, allocated memory, creations, data transfer, snapshots and Drives.

Tier EntryHobbyProTopEnterprise
Price $0/month$20/developer seat/month + usageper seatCustom
Includes Personal/non-commercial; 10 concurrent, 45-minute sessions, up to 4 vCPU.10,000 concurrent; 24-hour sessions; 8 vCPU max; $20 shared usage credit.10,000 concurrent; 24-hour sessions; 32 vCPU max; negotiated terms.
Transfer20 GB——
Storage15 GB——
vCPU hours5 h——
Instances5000——
Memory gb hours420 h——
Storage overage —$0.08/GB—
vCPU hours overage —$0.128/h—
Sandbox overage —$0.0000006 per sandbox—
Memory gb hours overage —$0.0212/h—

Free tier: Hobby: 5 active CPU-hours/month, 420 GB-memory-hours/month, 5,000 creations/month, 20 GB transfer/month, 15 GB lifetime snapshot storage; 15 GB lifetime Drive storage and 30 GB reads/writes/month.

active vCPU-hour; provisioned GB-memory-hour; Sandbox creation; GB transfer; snapshot/Drive GB-month; Drive read/write GB·Card required: unconfirmed·vercel.com

Overages: iad1: $0.128/active CPU-hour; $0.0212/GB-memory-hour; $0.60/million creations; Pro Sandbox transfer included in Flat Rate CDN (lowest capacity includes 1 TB/month shared traffic), Enterprise published transfer $0.15/GB; $0.08/GB-month snapshots; Drive $0.05/GB-month + $0.0015/GB reads + $0.004/GB writes. CPU/memory/Drive rates vary by region.

02 Runtime Each fact carries its source; dots show confidence. Open a row for the evidence.

Isolation & lifecycle

Isolation primitive
Firecracker microVMshares only the hypervisor
Persistence
Filesystem auto-snapshot on stop/timeout; resume starts a new session from snapshot. Persistence is default; opt-out discards filesystem. Processes need onResume restart.
Snapshots / forks
Manual and automatic filesystem snapshots; fork starts new Sandbox from snapshot; snapshot retention configurable.

Resources & limits

Storage
64 GB ephemeral NVMe with SDK 3.0+ or custom images (deprecated runtimes 32 GB); session filesystem persisted by snapshots; reusable regional Drives beta (up to 4 mounted); OCI images via VCR; external object stores mounted via FUSE.
Limits & quotas
Hobby 10 concurrent, 45-minute sessions, up to 4 vCPU; Pro/Enterprise 10,000 concurrent, 24-hour sessions, up to 8/32 vCPU; 2 GB RAM/vCPU; 15 exposed ports; 64 GB ephemeral disk on SDK 3.0+/custom images; default session timeout 5 minutes. Persistent Sandbox lifetime spans sessions.
GPU
No

Access

Deploy interface
Sandbox SDKs, sandbox CLI, REST /v2/sandboxes, project dashboard and OAuth Vercel MCP Sandbox tools.
SDK languages
JavaScript/TypeScriptPython

Network & secrets

Egress controls
allow-all, deny-all or domain allowlists; dynamically update policy; credential brokering and HTTPS header transformations; Secure Compute traffic follows configured policy.
Secrets
Host-controlled credential brokering injects headers outside untrusted code; Sandbox management OIDC/access tokens; caller-provided env for processes.
Bring your own cloud
No

Placement & use

Jurisdiction
19 Sandbox regions; default iad1; per-sandbox selection on every plan; failover regions Pro/Enterprise.
Advertised workloads
Untrusted/AI generated codeCoding agent executionIsolated tests and app previewsLinux commands and privileged Docker/FUSE

03 Capabilities 22 pass · 3 partial · 36 fail · 61 of 61 assessed

  • Supported
  • Partially supported
  • Not supported
  • Not assessed

Compute & storage 5/11

Persistent diskStorage that survives restart/stop (not ephemeral-only).
Supported
Object storageManaged S3-compatible / blob object store the platform PROVIDES to a user's workloads (buckets, presigned URLs). DISTINCT from persistent-disk (block/volume attached to an instance) and from a self-host dependency (source.self_host.deps[]=["object-storage"] is an infra dep to RUN an OSS tool — the opposite direction). SCOPE varies and matters: native first-class (Railway Buckets, Cloudflare R2) vs a sibling SKU / extension (Fly Tigris, Bunny Storage, DigitalOcean Spaces) — record which in the evidence quote / note. Admitted v15.
Not supported
Snapshots / forkingSnapshot or copy-on-write fork of a running instance (filesystem-only counts). Whether the snapshot also restores memory + running processes is recorded separately by memory-snapshot (v19).
Supported
Live-state (memory) snapshotsA snapshot / checkpoint / pause captures a running instance's MEMORY and PROCESS state and restores it, so running processes continue where they left off instead of a freshly booted instance with the same files. Counts whether user-triggered (snapshot, checkpoint, pause-to-storage) or used to restore pre-initialised state (memory snapshots for fast cold starts). Distinct from snapshots-forks (any snapshot or fork, including filesystem-only; a product passing that key may still fail this one) and from scale-to-zero (an idle-cost property; suspension may or may not keep memory). Actor multiplexing (see scale-to-zero) records its live-state half here — only when the suspended actor's MEMORY/process state is what comes back, not a freshly booted worker with the actor's files.
Not supported
Scale to zeroIdle instances suspend at no / negligible cost. ACTOR MULTIPLEXING (many suspended stateful actors sharing a small pool of pre-warmed workers, woken on request — Agent Substrate, AX, kagent; Rivet's hibernating actors) has NO key of its own (proposal REJECTED v20) — score the idle-cost half HERE and the live-state half under memory-snapshot; the oversubscription ratio / density is a performance characteristic the registry does not key.
Supported
GPU computeGPU-backed instances available.
Not supported
Multi-regionCompute placeable in more than one geographic region.
Supported
Sandbox templates / custom imagesBuild reusable sandbox/VM images from an OCI image or Dockerfile (a base you fork instances from).
Supported
Cloud-init / ignition configCustomise a VM / microVM / instance at boot via cloud-init (or ignition) user-data — the same boot-metadata interface as AWS/Azure/GCP. Inject packages, users, SSH keys, files, and run-commands declaratively at launch. Distinct from sandbox-templates (a PREBUILT image you fork instances from) — this is PER-LAUNCH declarative customisation, not a baked image.
Not supported
Desktop / computer-use sandboxA virtual desktop (GUI) for LLM computer-use — browser + desktop automation, often via noVNC/VNC.
Not supported
Selectable isolation runtimeThe user chooses the isolation runtime per workload / environment / sandbox from more than one option (e.g. microVM vs gVisor vs plain container, native namespaces vs gVisor, gVisor vs VM). Records the CHOICE; the isolation_primitive facet still records the best-evidenced primary. A platform that switches runtime automatically without a user choice (e.g. gVisor forced for GPU) does not pass on that alone.
Not supported

Networking & delivery 4/9

Automatic HTTPSTLS endpoints provisioned automatically per workload.
Supported
Built-in reverse proxyPlatform routes external traffic to workload services.
Supported
Custom domainsBring-your-own domain via CNAME/DNS.
Not supported
Public preview URLsShareable per-deploy / per-branch URLs.
Supported
Direct public IPv6Per-instance stable public IPv6 for raw TCP/UDP (beyond a managed HTTPS proxy) — e.g. mosh / raw sockets.
Not supported
Egress controlsConfigurable OUTBOUND network policy — egress firewall / allowlist / egress proxy on traffic LEAVING a workload. Scoped to OUTBOUND only (v15): private-network REACHABILITY between a user's own services is private-networking, not this. Static-egress-IP belongs here (an outbound concept).
Supported
Private networkingA platform-internal private network between a user's OWN services — service-to-service connectivity, VPC, service mesh, and/or service discovery, not exposed to the public internet. DISTINCT from egress-controls (OUTBOUND firewall/allowlist), reverse-proxy (PUBLIC inbound ingress), and direct-ipv6 (per-instance PUBLIC addressing). Admitted v15.
Partially supported
Email send / receiveSend and/or receive email from the workload.
Not supported
Edge KV storeA globally-replicated key-value store read from WITHIN an edge runtime at the PoP (low-latency, eventually-consistent) — Cloudflare Workers KV, Deno KV, Fastly KV Store, Akamai EdgeKV, Vercel Edge Config. Distinct from first-party-db (a managed DATABASE service you provision and connect to) and from http-query-api (HTTP access to an external store) — edge-kv is colocated with the edge compute and read at the edge.
Not supported

Developer access 6/10

Public APIDocumented programmatic API.
Supported
OpenAPI specMachine-readable OpenAPI / Swagger spec published.
Supported
CLIOfficial command-line tool.
Supported
SDKOfficial client library/libraries.
Supported
SSH accessDirect SSH into workloads.
Not supported
Filesystem APIRemote file operations over the API (list/read/write/watch/copy/upload) without SSH.
Supported
Git deployDeploy from a Git repo / push-to-deploy.
Not supported
Private container registryHosted private image registry.
Supported
E2B-compatible APIDrop-in compatibility with the E2B sandbox API/SDKs — existing E2B client code runs against this product by changing the endpoint/domain + key, with no business-code changes. E2B itself passes as the reference implementation. Distinct from public-api / sdk (the product has its own API — this key says it also speaks another vendor's) and from self-host-oss (a self-hosted E2B-compatible server is scored on both).
Not supported
HTTP data APIQuery / read / write the stored DATA over plain HTTP/REST (or GraphQL) WITHOUT the native protocol driver (Postgres wire / Redis RESP) — agent- and edge-friendly data access via fetch(). The DATA plane; distinct from public-api (a control-plane / management API). Auto-generated-from-schema REST/GraphQL (PostgREST, pg_graphql) is a flavour of this.
Not supported

AI & agents 4/12

Built-in coding agentShips a first-party AI coding agent in the product.
Not supported
Agent skillsInstallable / declarable agent skills or tools.
Supported
AI app builderPrompt-to-app / vibe-coding generation surface.
Not supported
MCP serverExposes a Model Context Protocol server for agents.
Supported
MCP clientActs as an MCP client / consumes MCP tools.
Not supported
MCP-server hostingRun/host MCP servers as a workload on the platform (distinct from exposing a first-party MCP control server — that is mcp-server).
Not supported
LLM gatewayRoutes LLM API calls through the platform (multi-provider).
Not supported
BYOK for LLMsBring-your-own LLM provider keys.
Not supported
Model inference API (first-party)A FIRST-PARTY hosted LLM/model inference API — the provider serves its OWN catalogue of (usually open-weight) models behind a (typically OpenAI-compatible) endpoint, billed per token. Distinct from llm-gateway (a multi-PROVIDER proxy/router for YOUR calls to external providers like OpenAI/Anthropic) and from byok-llm (bring your own provider keys) — here the platform IS the inference provider, serving its own models.
Not supported
Autonomous QA agentA first-party AUTONOMOUS AI agent that QA-TESTS a running app / implementation — exercising it like a real user (clicking through flows, checking behaviour) and reporting bugs/defects (often back to a coding agent, or before a human review). Distinct from built-in-agent (a code-AUTHORING agent — this one VERIFIES the result, it does not write the feature; a product can ship both), from ai-guided-code-review (organises a diff for a HUMAN to review — not an autonomous tester), and from observability (runtime metrics/logs, not active testing).
Not supported
Credential-injection proxyThe platform holds real secrets OUTSIDE the workload and injects them on the wire (an egress / broker proxy swaps a placeholder or phantom token for the real credential on matching outbound requests), so code running in the sandbox — e.g. an untrusted agent — never sees or can exfiltrate the real key. Distinct from secrets-management (storage + injection INTO the workload as env vars/files — the workload holds the secret) and from egress-controls (outbound allow/deny POLICY; a product can have an allowlist without injecting credentials, and vice versa).
Supported
Preinstalled coding agentThe platform installs and launches a THIRD-PARTY coding agent (a harnesses.yml entry — Claude Code, Codex, OpenCode, Pi ...) inside a workspace/sandbox it provisions, with the agent's auth wired in (your own account or API key), so you start an agent session rather than an empty box. Distinct from built-in-agent (a FIRST-PARTY agent the vendor ships) and from harnesses[] (which records that a harness CAN target the product, not that the product runs it for you).
Supported

Data 0/4

First-party databasePlatform-provided managed database.
Not supported
Database branchingCopy-on-write branch of a DATABASE (schema + data) as a dev-lifecycle primitive — branch your data like code, usually instant via a metadata operation. Distinct from snapshots-forks (forks a running compute INSTANCE / VM state) and from preview-environments (a full per-PR environment that may USE a DB branch). For a data product a CoW branch maps HERE, not to snapshots-forks.
Not supported
Vector searchFirst-class storage, indexing, and similarity search of vector embeddings — a native vector type/index or a managed vector DB. The data-layer primitive for RAG / semantic retrieval.
Not supported
Ephemeral instant DB (no-signup)Provision a working, usable instance via a single command / HTTP call with NO account, signup, or card — typically time-boxed (expires unless claimed). A zero-onboarding path an agent can hit directly.
Not supported

Platform & operations 1/6

Scheduled tasksCron / scheduled job primitive.
Not supported
Durable workflowsDurable execution / long-running workflow primitive.
Not supported
Preview environmentsA full EPHEMERAL environment spun up per PR / branch — compute + addons + (often) a DB branch — torn down on merge. More than preview-urls (which is just a shareable URL for one deploy).
Not supported
Built-in observabilityFirst-party metrics / logs / tracing / APM / profiling included in the platform (no third-party stack required to see what a workload is doing).
Supported
Managed CI/CD runnersPlatform-hosted, drop-in CI/CD runner VMs (GitHub Actions / GitLab), typically faster and cheaper than the CI vendor's own hosted runners, billed per runner-minute; isolated + ephemeral per job. Distinct from git-deploy (push-to-deploy of an APP) and scheduled-tasks (cron) — this is managed CI COMPUTE you point your existing pipelines at.
Not supported
Project template marketplaceA marketplace / gallery of prebuilt PROJECT STARTER templates (apps or websites) a user clones or launches a new project from and then customises — the "start from a template" surface of a builder / PaaS. Distinct from sandbox-templates (a COMPUTE base IMAGE you fork runtime INSTANCES from — Dockerfile / OCI), from app-builder (the prompt-to-app GENERATION surface — a product can have both), and from one-click OSS-app catalogues / helm-addon-marketplace (deploy a FINISHED app as-is, not a starter you build on).
Not supported

Organisation & security 2/9

Built-in authPlatform-provided authentication / IAM for workloads.
Not supported
SSO / SAMLEnterprise single sign-on.
Partially supported
Secrets managementFirst-class secrets storage / injection.
Supported
TeamsMulti-user team accounts.
Supported
SharingShare a running workload/resource via link (optionally gated).
Partially supported
BYOCRuns inside the customer's own cloud account.
Not supported
Deploy into customers' VPCsA SaaS vendor uses the platform to deploy and operate ITS software inside ITS CUSTOMERS' cloud accounts / VPCs (nested or "customer BYOC"), managed from the vendor's control plane. Distinct from byoc (your own workloads in your own cloud account).
Not supported
Workload identityThe platform gives each workload its own verifiable identity (OIDC token, SPIFFE SVID, cloud IAM federation) that it exchanges for short-lived credentials, so no long-lived static secret is stored or injected. Distinct from secrets-management (stores / injects static secrets) and credential-injection-proxy (swaps real secrets in on the wire).
Not supported
Self-host / OSS coreOpen-source core that can be self-hosted.
Not supported

04 Agent readiness Pre-login surface · counts, not a grade

Can an agent read it?

parse-ability · docs, metadata, machine-readable surfaces

9/11

8 full · 2 partial · 82% of applicable checks

  • llms.txt
    Supported
  • llms-full.txt
    Supported
  • robots.txt AI policy
    Partially supported
  • JSON-LD
    Not supported
  • Sitemap
    Supported
  • Meta tags
    Supported
  • Markdown negotiation
    Supported
  • Content efficiency
    Partially supported
  • Docs discoverable
    Supported
  • Machine-readable pricing
    Supported
  • No anti-bot wall
    Supported

Can an agent drive it?

act-ability · APIs, SDKs, MCP, credentials, webhooks

9.5/11

9 full · 1 partial · 86% of applicable checks

  • Public API
    Supported
  • OpenAPI spec
    Supported
  • MCP server
    Supported
  • SDK packages
    Supported
  • Auth documented
    Supported
  • Self-serve credentials
    Supported
  • Webhooks
    Not supported
  • CLI tool
    Supported
  • Error model
    Supported
  • Rate limits documented
    Partially supported
  • Agent config files
    Supported

05 Coding harnesses Which agents and IDEs are documented to run here

Advertised integrations 5

  • Cursor Anysphere
    Supported

    Sandbox execution integration; not just generic MCP.

  • Hermes Agent Nous Research
    Supported

    Sandbox execution integration.

  • Claude Code Anthropic
    Supported

    Advertised preinstalled execution harness; also documented Vercel MCP management client. Agent-provider login is still required.

  • Codex CLI OpenAI
    Supported

    Advertised preinstalled execution harness; also documented Vercel MCP management client. Agent-provider login is still required.

  • OpenCode opencode
    Supported

    Advertised preinstalled Sandbox execution harness; user authenticates the coding agent.

Plausible compatibility 0

Derived, not stored: the product passes SSH access, so any CLI coding agent is installable inside it. This is plausible compatibility, not a supported integration.

No general shell access documented, so nothing is derived. Absence is not unsupported.

06 Compliance & regions Standards held, with ordinal rigor; never a score

Certifications held 5

  • ISO/IEC 27001
    certifiedhostedVercel vendor/hosted claim; Sandbox-specific audited or regulated-workload eligibility not verified.
  • PCI DSS
    self-attestedhostedVercel vendor/hosted claim; Sandbox-specific audited or regulated-workload eligibility not verified.
  • SOC 2 Type II
    certifiedhostedVercel vendor/hosted claim; Sandbox-specific audited or regulated-workload eligibility not verified.
  • HIPAA
    self-attestedhostedVercel vendor/hosted claim; Sandbox-specific audited or regulated-workload eligibility not verified.
  • GDPR
    self-attestedhostedVercel vendor/hosted claim; Sandbox-specific audited or regulated-workload eligibility not verified.

Regions 19

  • Stockholm, Swedenarn1
  • Mumbai, Indiabom1
  • Paris, Francecdg1
  • Cleveland, USAcle1
  • Cape Town, South Africacpt1
  • Dublin, Irelanddub1
  • Frankfurt, Germanyfra1
  • São Paulo, Brazilgru1
  • Hong Konghkg1
  • Tokyo, Japanhnd1
  • Washington, D.C., USAiad1
  • Seoul, South Koreaicn1
  • Osaka, Japankix1
  • London, United Kingdomlhr1
  • Portland, USApdx1
  • San Francisco, USAsfo1
  • Singaporesin1
  • Sydney, Australiasyd1
  • Montréal, Canadayul1

19 Sandbox regions, not inferred from deployment platform regions; default iad1. Drive region is fixed and must match attached Sandbox.

Legal

Privacy noticeTerms of service

07 Company & presence Facts only, not scored

Company

Headquarters
San Francisco, USA
Founded
—
Team size
Not disclosed
Hiring
Hiring; many open engineering and commercial roles

Activity

Last release
Sandbox Drives public beta changelog; managed images released nightly. Global Vercel changelog latest 2026-10-12 is AI Gateway, not a Sandbox release. vercel.com
Last blog post
Global blog index includes Sandbox GA and Sandbox customers; not a Sandbox-only release feed. vercel.com

Presence 5

Links found on the public surface scanned; not an exhaustive search.

08 Sources & method How this entry was produced

Public surface only

Everything here was read from vercel.com's unauthenticated pages, docs, pricing and repository on 12 Oct 2026. Nothing behind a login was used.

Statuses, not scores

Capabilities are pass, partial or fail against a written rubric (features v21). “Not assessed” means the scan predates the key.

Confidence is separate

Each fact carries its own confidence. Low-confidence facts are shown, never hidden, so you can weigh them.

Schema
scan v5
Features registry
v21
Keys tracked today
61
Assessed on this entry
61
Something wrong on this page?

Nearby in the atlas

All Sandbox products →
where do i run this.

An independent spec sheet for places to run code, and the code your agents write. Facts come from each product's public pages; every capability is a count, never a grade.

Verify

Pages change; so do prices. Verify on the vendor's site before you commit; every product page shows when it was read.

Where Do I Run This © 2026counts, not grades · public pages only