Code & AI agent sandboxes: read the guide

Blaxel Sandboxes

HostedSandbox

Give a computer to your agent

Homepage Docs Pricing Repository

Scanned 12 Oct 2026 · Schema v5 · features v21

From: —
usage-based wallet; optional custom deployment
Free tier: Not documented
Up to $200 introductory credits; tier 0 permits 10 sandboxes. Promotional credits do not unlock paid quota tiers.
Isolation: Virtual machine
hypervisor, or nothing at all
Regions: 4
Oregon, US · North Virginia, US · London, UK · Frankfurt, Germany
Capabilities: 25 / 61
7 partial · 29 fail · 0 not assessed
Agent readiness: 11/11 · 10/11
read · drive, pre-login surface

Advertised for

Untrusted code execution · Coding agents · Application previews · Data analysis · Background agents

Built for

Developers, then technical

· CLI/SDK/API-first quickstart
· microVMs, sandbox memory and networking vocabulary
· Allocated RAM-second usage pricing

01 Pricing usage-based wallet; optional custom deployment

Tier	EntryPay-as-you-go	Custom
Price	$0 + usage	Contact us
Transfer overage	$0/GB	—
Storage overage	$0.12/GB	—
Memory gb hours overage	$0.0414/h	—

Free tier: Up to $200 introductory credits; tier 0 permits 10 sandboxes. Promotional credits do not unlock paid quota tiers.

GB allocated RAM-second of active execution; storage GB-month·Card required: unconfirmed·blaxel.ai

Overages: Active sandbox $0.0000115/GB RAM-second; snapshot $0.20/GB-month; images $0.045/GB-month; volumes $0.12/GB-month. Egress included; Agent Drive and egress gateways/proxy free during beta.

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

Isolation & lifecycle

Isolation primitive

Virtual machinehypervisor, or nothing at all

Persistence

Standby preserves filesystem, memory and running processes indefinitely; volumes persist independently. Deletion erases sandbox data.

Snapshots / forks

Automatic full-state standby snapshots; manual snapshots, rollback and forks on Carbon are private preview, not recommended for production.

Resources & limits

Storage

Read-only EROFS image plus RAM tmpfs writable layer, roughly 50% RAM reserved when possible; durable volumes and shared Agent Drive; Carbon does not yet support Agent Drive.

Limits & quotas

Tier 0 10 sandboxes; $20 top-up tier 1 50; $50 top-up tier 2 200; contact tier 9 100,000+. Custom up to 256 GB RAM. Top-ups are wallet funds, not flat fees; trailing 30-day top-up controls tier. Idle connection timeout 15 minutes.

GPU

Access

Deploy interface

dockerfilecontainer-imageclisdkapidashboardtemplate

SDK languages

PythonTypeScriptGo

Network & secrets

Egress controls

Proxy domain/method/path policy; network-level firewall enforcement on Mark 3.0. Dedicated egress IPs. Carbon currently lacks firewall and dedicated egress IP features.

Secrets

Environment secrets and on-the-wire proxy credential injection.

Bring your own cloud

Custom plan advertises bring your own compute; implementation and supported customer clouds undisclosed.

Placement & use

Jurisdiction

US legal entity; selectable US, UK and Germany workload locations. Privacy policy describes EU/UK-US transfers.

Advertised workloads

Untrusted code executionCoding agentsApplication previewsData analysisBackground agents

03 Capabilities 25 pass · 7 partial · 29 fail · 61 of 61 assessed

Supported — Documented on the public surface and verified.
Partially supported — Exists with caveats: gated, thin, or enterprise-only.
Not supported — Checked and not offered.
Not assessed — Scanned before this capability was tracked. Not a lack.

Compute & storage 6/11

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.

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).

Partially 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.

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.

Partially 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.

Partially 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.

Partially 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 3/12

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).

Not 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 2/6

Scheduled tasksCron / scheduled job primitive.

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 4/9

Built-in authPlatform-provided authentication / IAM for workloads.

Partially supported

SSO / SAMLEnterprise single sign-on.

Supported

Secrets managementFirst-class secrets storage / injection.

Supported

TeamsMulti-user team accounts.

Supported

SharingShare a running workload/resource via link (optionally gated).

Supported

BYOCRuns inside the customer's own cloud account.

Partially 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

11/11

7 full · 4 partial · 100% of applicable checks

llms.txt
Supported
“https://docs.blaxel.ai/llms.txt — Substantive documentation index; apex copy also rendered.”
llms-full.txt
Supported
“https://docs.blaxel.ai/llms-full.txt — Comprehensive 1,273,945-byte docs dump, retained pointer.”
robots.txt AI policy
Partially supported
“https://blaxel.ai/robots.txt — Rendered HTTP 404: default allow, no explicit AI policy.”
JSON-LD
Partially supported
“https://blaxel.ai/ — Organization and WebSite only; no Product offers.”
Sitemap
Supported
“https://blaxel.ai/sitemap-index.xml — Index links sitemap-0.xml with many public URLs; both rendered XML saved.”
Meta tags
Supported
“https://blaxel.ai/ — Descriptive title, description, OpenGraph metadata in retained HTML.”
Markdown negotiation
Supported
“https://docs.blaxel.ai/Sandboxes/Overview.md — Docs .md variants fetched as text/markdown; apex reader negotiated markdown but direct Python HTTP returned 403.”
Content efficiency
Partially supported
“https://blaxel.ai/ — Rendered visible text/HTML bytes = 4.66%, using text outside scripts/styles.”
Docs discoverable
Supported
“https://blaxel.ai/ — Docs navigation links quickstart, SDK and API reference.”
Machine-readable pricing
Supported
“https://blaxel.ai/pricing — Rendered rate tables contain per-unit rates, plans and quota tier top-up thresholds.”
No anti-bot wall
Partially supported
“https://blaxel.ai/ — Direct urllib apex requests returned HTTP 403; reader/foxcrawl succeeded. No persistent source block remains.”

Can an agent drive it?

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

10/11

8 full · 2 partial · 91% of applicable checks

Public API
Supported
“https://docs.blaxel.ai/api-reference/introduction — REST auth, versioning and pagination documented.”
OpenAPI spec
Supported
“https://raw.githubusercontent.com/blaxel-ai/sandbox/main/sandbox-api/docs/openapi.yml — Public valid OpenAPI document; docs configuration also links controlplane.yml.”
MCP server
Supported
“https://docs.blaxel.ai/skills-mcp — Documented sandbox MCP endpoint and management MCP setup.”
SDK packages
Supported
“https://docs.blaxel.ai/sdk-reference/introduction — Official Python, TypeScript and Go SDKs.”
Auth documented
Supported
“https://docs.blaxel.ai/Security/Access-tokens — API key bearer and OAuth flows with scope/rotation.”
Self-serve credentials
Partially supported
“https://docs.blaxel.ai/Security/Access-tokens — Initial credentials generated from console; subsequent service account OAuth does not make initial signup/key issuance programmatic.”
Webhooks
Not supported
“https://docs.blaxel.ai/llms.txt — OpenAI Agents webhook handler is customer integration, not first-party signed platform event webhooks.”
CLI tool
Supported
“https://docs.blaxel.ai/Get-started — Official CLI install and bl login/deploy.”
Error model
Supported
“https://docs.blaxel.ai/troubleshooting/error-codes — Structured JSON error code, action, retryable status and documentation fields.”
Rate limits documented
Partially supported
“https://docs.blaxel.ai/Security/Quotas — Resource quota tiers documented; API request rate-limit response headers not established.”
Agent config files
Supported
“https://docs.blaxel.ai/skills-mcp — Plugin marketplace/agent skills plus management and sandbox MCP setup; multiple config surfaces.”

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

Advertised integrations 4

Claude Code Anthropic
Supported
“Run Claude Code in a sandbox”
Source docs.blaxel.ai
Codex CLI OpenAI
Supported
“Run Codex in a sandbox”
Source docs.blaxel.ai
Amp Sourcegraph
Supported
“Run Amp in a sandbox”
Source docs.blaxel.ai
OpenClaw Peter Steinberger
Supported
“Run OpenClaw on Blaxel”
Source docs.blaxel.ai

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
certifiedhosted
“ISO 27001 (2022)”
Source compliance.blaxel.ai
HIPAA
self-attestedhosted
“HIPAA”
Source compliance.blaxel.ai
SOC 2 (type unspecified)
certifiedhosted
“SOC 2”
Source compliance.blaxel.ai
CCPA
self-attestedhosted
“CCPA compliant”
Source blaxel.ai
GDPR
self-attestedhosted
“GDPR compliant”
Source blaxel.ai

Regions 4

Oregon, USus-pdx-1
North Virginia, USus-was-1
London, UKeu-lon-1
Frankfurt, Germanyeu-fra-1

Not all regions self-service by default; access may require contacting vendor. Region guide covers Mark 3; Carbon rollout varies by workspace and region.

Legal

Privacy notice Terms of service

07 Company & presence Facts only, not scored

Company

Headquarters: San Francisco, US
Founded: —
Team size: Not disclosed
Hiring: Recruiting via Baseten careers

Activity

Last release: 2026-09-25: Network-level domain filter enforcement docs.blaxel.ai
Last blog post: 2026-09-28: NVIDIA Agent Safety Platform/OpenShell announcement blaxel.ai

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 blaxel.ai'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 →