Which sandbox providers offer “any size you like”?

Choose CPU and memory freely instead of picking from a short list of fixed sizes. Fully: Modal, Morph, Runtime and Tensorlake. With a catch: Blaxel, Cloudflare Sandbox, Daytona, E2B and Vercel Sandbox. Not at all: Agent 37, Boat, InstaBox, Lizard, Sandboxer, Sprites and boxd.

Which sandbox providers offer “large machines”?

Machines of 16 vCPU or 32 GiB memory or more are available. Fully: Boat, InstaBox, Modal, Runtime, Sandboxer, Tensorlake and boxd. With a catch: Agent 37, Blaxel, Daytona, Morph and Vercel Sandbox. Not at all: Cloudflare Sandbox, E2B, Lizard and Sprites.

Which sandbox providers offer “resize while running”?

Change CPU or memory without stopping the machine or losing what is running. Fully: Tensorlake. With a catch: Agent 37, Blaxel, Daytona, InstaBox, Morph and Runtime. Not at all: Boat, Cloudflare Sandbox, E2B, Lizard, Modal, Sandboxer, Sprites, Vercel Sandbox and boxd.

Which sandbox providers offer “gPUs”?

Machines with a graphics processor, for running AI models or other GPU work inside the sandbox. Fully: Daytona and Modal. With a catch: Tensorlake. Not at all: Agent 37, Boat, Cloudflare Sandbox, E2B, InstaBox, Lizard, Runtime, Sandboxer, Sprites, Vercel Sandbox and boxd.

Which sandbox providers offer “choose the region”?

You decide which part of the world the machine runs in. Fully: Agent 37, Daytona, Lizard, Modal, Sandboxer, Tensorlake and Vercel Sandbox. With a catch: Blaxel and E2B. Not at all: Boat, Cloudflare Sandbox, InstaBox, Runtime, Sprites and boxd.

Which sandbox providers offer “runs in the EU”?

At least one region inside the European Union, for EU data rules. Fully: Blaxel, Boat, Daytona, E2B, Lizard, Modal, Sandboxer, Tensorlake, Vercel Sandbox and boxd. With a catch: Agent 37, Cloudflare Sandbox and Sprites. Not at all: InstaBox and Runtime.

Sizes, regions and hardware

The idea

There are two ways to buy a machine. A fixed menu gives you four or five shapes and nothing else; a configurable machine lets you pick vCPU, memory and disk within bounds. A fixed menu is easier to price and compare. A configurable one lets you match the workload, and makes it harder to know what you are paying for.

The second variable is what the size includes. Disk is sometimes a fixed part of the shape, sometimes an allowance you can exceed, and sometimes ephemeral storage that disappears with the session. CPU is sometimes shared, sometimes reserved. Memory is sometimes the billing dimension and sometimes just a ceiling.

Regions are the least negotiable part. A provider with one region is not a global product, and a provider that offers a region may still store backups or control-plane data somewhere else.

Where providers split

The claim on the left, the provider's own words on the right

Fixed menus versus configurable machines

Boat, Sandboxer, Lizard and boxd sell four or three fixed shapes. Sprites sells one: 8 vCPU and 100 GB, with memory assigned automatically. E2B, Vercel, Runtime and Morph let you choose resources within bounds; Blaxel sizes CPU from memory, and InstaBox sells fixed vCPU/RAM pairs by plan.

The difference matters most when your workload is lopsided. A browser agent needs memory more than cores; a compiler needs the reverse. On a fixed menu you buy the nearest shape and pay for what you do not use.

Disk is part of the shape, or it is not

Boat attaches 51 GB to its smallest three sizes and 111 or 251 GB to the larger ones. boxd gives every machine 100 GB and does not let you choose. Vercel gives 64 GB of ephemeral NVMe. E2B includes 10 GiB on Hobby and 20 GiB on Pro, and asks you to contact support beyond that.

Where disk is a separate meter, the capacity you see is not the storage you pay for: Vercel's drives bill on logical used size, and boxd's disk bills on bytes written.

Regions and hardware

Vercel is the outlier with 19 regions. E2B and Blaxel list four, Sandboxer and Lizard two, Agent 37 three, and Runtime one. Boat and boxd are EU-only; InstaBox publishes no region selector and its terms say the United States. Sprites does not let you choose a region: placement is automatic near you, according to a community answer.

No provider in this set publishes a GPU for sandboxes. Several say so explicitly: E2B, Boat, Lizard and Sprites. ARM is not offered either, and only Runtime, Sandboxer, Morph and Vercel document nested virtualisation or /dev/kvm. Morph publishes no region or GPU statement at all.

One worked case

The same job at every provider, from the documented defaults

A lopsided shape, in the EU

A browser agent needs 2 vCPU and 16 GB of memory, plus 20 GB of disk, and the data has to stay in the EU. Most providers sell CPU and memory in a fixed ratio, so the request fits almost nowhere as asked.

Ask
2 vCPU, 16 GB, 20 GB disk, EU region. A browser workload is memory-heavy, so the usual 1:2 or 1:4 ratio overbuys cores.
Quote
On a fixed menu the nearest shape is priced as a whole, so the extra cores are paid for and unused.
Deploy
Region choice decides whether the machine can run where the data must stay.

The menu, not the hourly rate, decides the bill here. A configurable provider sells exactly 2 vCPU and 16 GB; a fixed menu sells 8 vCPU to get the same memory, and an EU-only provider may have no region to choose at all.

What each provider does

Agent 37: Four shapes cap at 4 vCPU; the EU and India regions need the 2.5× vm type.
Blaxel: CPU follows memory: 16 GB buys 6 cores, and anything larger is a custom deployment.
Boat: Only four fixed shapes, largest 16 vCPU / 32 GB / 251 GB, all in Germany, Finland or France with no region choice.
boxd: The ceiling is 8 vCPU / 32 GiB, on German bare metal; a US region is announced but not open.
Cloudflare Sandbox: 16 GB of memory does not fit: the ceiling is 12 GiB, disk stops at 20 GB, and the sandbox cannot be pinned to the EU.
Daytona: 16 GB of memory does not fit: the ceiling is 4 vCPU / 8 GiB, disk stops at 10 GiB, and us or eu are the only regions.
E2B: Memory tops out at 8 GiB, so a 16 GB workload does not fit at any price.
InstaBox: Fixed pairs by plan, up to 32 vCPU / 64 GiB on Team, with one 20 GiB disk that grows live.
Lizard: Large is 8 vCPU / 16 GB / 50 GB, and there is no 2-core 16 GB shape in between.
Modal: No fixed menu: you ask for 1 core and 16 GiB and Modal schedules it, paying 1.15× to pin a broad region or 1.75× for a narrow one.
Morph: vCPU, memory and disk are chosen at creation, so the shape can be exact; the ceiling and the regions are not published.
Runtime: Any combination inside 16 vCPU and 64 GiB, so 2 vCPU / 16 GB is exact, in one Virginia region.
Sandboxer: The xlarge shape is 16 vCPU / 32 GB / 251 GB, with shared vCPU and reserved RAM.
Sprites: One shape, 8 vCPU and a 100 GB storage ceiling, with memory assigned automatically and no region choice.
Vercel Sandbox: Even vCPU counts up to 32, 2 GB of memory per vCPU, so 16 GB means 8 vCPU, in any of 19 regions.
Tensorlake: Pro reaches 16 vCPU / 64 GiB with a 100 GB root disk, but RAM must stay between 1 and 8 GB per vCPU and no region can be chosen.

What to watch for

The details that decide the answer in practice

01
The vCPU ceiling: Agent 37's default type stops at 4, E2B at 8, Vercel at 32 on Enterprise.
02
Whether disk is included, capped or ephemeral, and whether it bills on capacity or on written bytes.
03
Shared versus reserved CPU: a shared 4 vCPU is not four cores.
04
Region choice versus data residency: backups and control-plane data may sit elsewhere.
05
GPU is not available anywhere here, whatever a workload page implies.

Compare all 16

Docs read 28 October 2026

A size is a bundle of CPU, memory and disk, and the bundle decides what you can run. A region decides how far away it is and whose laws it sits under. Neither is as flexible as the word “cloud” suggests.
Provider	Largest shape; regions	Does it?	What that means
Agent 37	4 vCPUthree regions	Partly	Four shapes with a 4 vCPU ceiling on the default type, 2–80 GB of disk by shape, and three regions. EU and India require the 2.5× vm type.Agent 37 docs: Create an instance — shapes, disk ranges and regions ↗ Agent 37's own wordsdocs-confirmed “4 vCPU is the ceiling on every instance type.” Agent 37docs-confirmed
Blaxel	16 GB → 6 cores256 GB custom	Partly	Memory drives CPU: 8 GB gets 4 cores and 16 GB gets 6. Custom deployments go to 256 GB. Four regions, no published GPU.Blaxel docs: Regions ↗ Blaxel's own wordsdocs-confirmed “a sandbox with 8 GB memory is allocated 4 CPU cores, while one with 16 GB memory is allocated 6 CPU cores.” Blaxeldocs-confirmed
Boat	16 vCPU / 32 GBEU only	Partly	Four fixed sizes from 2 vCPU / 4 GB / 51 GB to 16 vCPU / 32 GB / 251 GB. No custom size, no extra disk, EU-only, no region choice.Boat docs: Sizes ↗ Boat's own wordspricing-page “\| xlarge \| $0.200 \| 16 vCPU \| 32 GB \| 251 GB \|” Boatpricing-page
boxd	8 vCPU / 32 GiBone EU region	Partly	Four sizes from 1 vCPU / 4 GiB to 8 / 32, all with a fixed 100 GB disk. One EU region, no GPU, no ARM.boxd docs: Resources and limits ↗ boxd's own wordsdocs-confirmed “This is the largest size a single machine may have, 8 vCPU / 32 GiB unless the boxd team raised it for your org.” boxddocs-confirmed
Cloudflare Sandbox	4 vCPU / 12 GiB / 20 GB	Partly	Six presets from lite to standard-4; custom sizes are capped at 4 vCPU / 12 GiB / 20 GB with at least 3 GiB of memory per vCPU. No GPU, linux/amd64 only, and placement is chosen by Cloudflare near the request.Cloudflare Sandbox docs: Limits and Instance Types ↗ Cloudflare Sandbox's own wordsdocs-confirmed “Maximum vCPU \| 4” Cloudflare Sandboxdocs-confirmed
Daytona	4 vCPU / 8 GiB / 10 GiB	Partly	Default 1 vCPU / 1 GB / 3 GiB; the organisation ceiling is 4 vCPU / 8 GB / 10 GiB, with daytona-large at 4/8/10. Windows presets reach 4/16/50 and GPU sandboxes attach up to 8 GPUs. Two shared regions, us and eu.Daytona docs: Regions (us, eu, earth for GPU) ↗ Daytona's own wordsdocs-confirmed “Organizations get a maximum sandbox resource limit of 4 vCPUs, 8GB RAM, and 10GB disk.” Daytonadocs-confirmed
E2B	8 vCPU / 8 GiBno GPU	Partly	Up to 8 vCPU and 8 GiB, with 10 GiB of disk on Hobby and 20 GiB on Pro. Four regions, no GPU on any plan.E2B docs: Billing & limits (max vCPU, memory, disk per plan) ↗ E2B's own wordsdocs-confirmed “\| Max memory \| 8 GiB \| 8+ GiB \|” E2Bdocs-confirmed
InstaBox	32 vCPU / 64 GiBUS only	Partly	Fixed vCPU/RAM pairs by plan, from 2/4 to 32/64, one 20 GiB disk that grows live. No published region selector; the terms say the United States.InstaBox docs: Limits — machine sizes by plan (no region selector) ↗ InstaBox's own wordsdocs-confirmed “Team: 2/4 up to 32 vCPUs / 64 GiB” InstaBoxdocs-confirmed
Lizard	8 vCPU / 16 GBtwo regions	Partly	Three fixed sizes: Small 2/4/5 GB, Medium 4/8/20 GB, Large 8/16/50 GB. Two regions, no GPU, no live resize.Lizard docs: Limits — sandbox sizes and regions ↗ Lizard's own wordsdocs-confirmed “Large \| 8 \| 16 GB \| 50 GB \| $0.0648/hour” Lizarddocs-confirmed
Modal	No fixed sizes1 core = 2 vCPU	Partly	Fractional physical cores (1 core = 2 vCPUs as documented) and MiB of memory, default 0.125 core / 128 MiB. Disk is a fixed 512 GiB. The maximum shape is unpublished. Regions are selectable at 1.15× broad and 1.75× narrow.Modal docs: Sandbox resources: CPU, memory and disk requests ↗ Modal's own wordsdocs-confirmed “The cpu parameter specifies physical CPU cores (1 core = 2 vCPUs), and memory specifies MiB” Modaldocs-confirmed
Morph	Not published	Partly	vCPU, memory and disk are chosen at creation, with no fixed catalogue. Maximum CPU, RAM and disk per VM, GPU availability, architecture, host locations and selectable regions are not published.Morph docs: Basic Operations — snapshot resource specifications ↗ Morph's own wordsdocs-confirmed “To create a new snapshot, specify the resource specifications like” Morphdocs-confirmed
Runtime	64 GiB1 region	Partly	Any vCPU, memory and disk combination inside 16 vCPU, 64 GiB and 400 GiB. One region in Virginia; shared CPU by default, reserved on request.Runtime docs: The sandbox environment (disk, CPU, memory; one region in Virginia) ↗ Runtime's own wordsdocs-confirmed “At least 128; at most 65,536 (64 GiB) on a paid sandbox, 4,096 without credit” Runtimedocs-confirmed
Sandboxer	16 vCPU / 32 GB2 regions	Partly	Four fixed sizes from 2/4/12 GB to 16/32/251 GB, shared vCPU with reserved RAM. Two regions, no GPU, no ARM.Sandboxer docs: Machines & sizes ↗ Sandboxer's own wordspricing-page “\| xlarge ($100+ plan) \| 16 \| 32 GB \| 251 GB \| 5.56× \| $0.20 \| $146 \|” Sandboxerpricing-page
Sprites	8 vCPUno choice	Partly	One shape: 8 vCPUs and 100 GB of storage, with memory assigned and autoscaled. GPU is explicitly not offered; region selection is unavailable and placement is automatic; CPU architecture is not published.Sprites docs: Lifecycle and Persistence (fixed 8 vCPU, 100 GB; no region selection documented) ↗ Sprites's own wordsdocs-confirmed “8 vCPUs” Spritesdocs-confirmed
Vercel Sandbox	19 regions	Yes	1 or even numbers of vCPUs from 2 to 32 by plan, 2 GB of memory per vCPU, 64 GB of ephemeral NVMe, and 19 regions. No GPU published.Vercel Sandbox docs: Sandbox pricing: resource limits ↗ Vercel Sandbox's own wordsdocs-confirmed “Vercel Sandbox is available in 19 regions. The default region is iad1.” Vercel Sandboxdocs-confirmed
Tensorlake	16 vCPU / 64 GiBno region picker	Partly	Ceilings by plan: Free 1 vCPU / 1 GB / 10 GB, Usage Credits 4 / 16 / 100, Pro 16 / 64 / 100, Enterprise custom. Memory is 1–8 GB per vCPU and disk is 10–100 GB, growth-only. No region selector is published: the docs claim EU data residency, and BYOC puts sandboxes in your own AWS region.Tensorlake docs: Pricing and billing — per-sandbox vCPU, RAM, disk and session limits ↗ Tensorlake's own wordspricing-page “Up to 16 vCPU · 64 GB RAM · 100 GB disk · snapshot + resume” Tensorlakepricing-page

The specific capabilities

Each one checked for every provider, with the catch where a version falls short. All capabilities

Sizes and regions: capabilities by provider
Capability	Agent 37	Blaxel	Boat	boxd	Cloudflare Sandbox	Daytona	E2B	InstaBox	Lizard	Modal	Morph	Runtime	Sandboxer	Sprites	Tensorlake	Vercel Sandbox
Any size you like	Agent 37: No. 4 fixed shapes. You choose from four fixed combinations of cores and memory, and anything else comes back as the nearest shape.	Blaxel: With a catch. memory only, cores follow. You set the memory and the number of cores is decided for you, so you cannot pick a memory-heavy or core-heavy machine.	Boat: No. 4 fixed sizes. There are four fixed sizes and no way to ask for anything between them.	boxd: No. 4 fixed sizes. There are four fixed sizes; naming either cores or memory picks the pair.	Cloudflare Sandbox: With a catch. custom within 4 cores / 12 GiB. You can set your own cores and memory, but only inside a ceiling of 4 cores and 12 GB, and each core needs at least 3 GB.	Daytona: With a catch. presets, custom on request. You pick from fixed sizes, and anything different needs a custom limit arranged through support.	E2B: With a catch. up to 8 cores / 8 GiB. You can choose cores and memory, but only up to 8 of each; more needs a conversation with support.	InstaBox: No. fixed pairs by plan. Each plan sells fixed pairs of cores and memory, and any other combination is refused.	Lizard: No. 3 fixed sizes. There are three fixed sizes and no custom option.	Modal: Yes. any cores and MiB	Morph: Yes. cores, memory, disk	Runtime: Yes. any combination in bounds	Sandboxer: No. 4 fixed sizes. There are four fixed sizes and no custom size.	Sprites: No. one shape. There is one shape: 8 cores, memory assigned automatically, and no choice.	Tensorlake: Yes. any cores and memory	Vercel Sandbox: With a catch. even cores only, 2 GB each. You choose cores in steps of two and each core comes with exactly 2 GB of memory, so memory cannot be set on its own.
Large machines	Agent 37: With a catch. 4 cores; 16 on the VM type. One page caps every machine at 4 cores, while another prices a 16-core, 32 GB machine on the 2.5x VM type, so the large size is unclear.	Blaxel: With a catch. up to 256 GB by arrangement. The standard sizes stop at 16 GB of memory; anything larger is a custom deployment you have to arrange.	Boat: Yes. 16 cores / 32 GB. Only on the $100-a-month plan or above.	boxd: Yes. 8 cores / 32 GiB	Cloudflare Sandbox: No. 4 cores / 12 GiB. The largest machine is 4 cores and 12 GB of memory, so a 16-core or 32 GB machine is not available.	Daytona: With a catch. 4 cores / 8 GiB; more with GPUs. A normal sandbox stops at 4 cores and 8 GB; larger machines only come attached to graphics cards.	E2B: No. 8 cores / 8 GiB. The ceiling is 8 cores and 8 GB of memory, so a 32 GB machine cannot be bought.	InstaBox: Yes. 32 cores / 64 GiB. Only on the $500-a-month plan or above.	Lizard: No. 8 cores / 16 GB. The largest machine is 8 cores and 16 GB, so a 32 GB machine is not offered.	Modal: Yes. no published ceiling	Morph: With a catch. ceiling not published. The plan allows up to 1024 cores across the account, but the largest single machine is not published.	Runtime: Yes. 16 cores / 64 GiB	Sandboxer: Yes. 16 cores / 32 GB. Only on the $100-a-month plan or above.	Sprites: No. 8 cores / 16 GB. The machine is fixed at 8 cores and up to 16 GB of memory, below the 32 GB mark.	Tensorlake: Yes. 16 cores / 64 GB. Only on the $250-a-month plan or above.	Vercel Sandbox: With a catch. 32 cores on Enterprise only. Machines above 8 cores and 16 GB need the Enterprise plan; the self-serve plans stop there.
Resize while running	Agent 37: With a catch. resize, but memory is lost. You can change the size without stopping the machine, but it may move to another host and everything running in memory is lost.	Blaxel: With a catch. memory change resets it. You can change the memory, but the sandbox resets, so anything running is lost.	Boat: No. stop first. Changing the size means stopping the machine and starting it again.	boxd: No. reboot to apply. A size change reboots the machine, so running programs are lost.	Cloudflare Sandbox: No. no resize. The size is fixed when the sandbox is deployed; changing it means deploying again.	Daytona: With a catch. grow only, support must enable. You can add cores and memory while it runs, but you cannot shrink them, and the feature has to be switched on by support first.	E2B: No. fixed at creation. The machine keeps the size it was created with; there is no resize.	InstaBox: With a catch. only while stopped. Cores and memory change only while the machine is stopped, and take effect at its next start; the free plan cannot resize at all.	Lizard: No. fixed size. The size is chosen when the sandbox is created and cannot be changed.	Modal: No. fixed at creation. Resources are fixed when the sandbox is created; changing them means starting a new one.	Morph: With a catch. disk live; cores need reboot. Disk space can grow while the machine runs, but changing cores or memory means restarting it.	Runtime: With a catch. memory, while paused. You can change the memory only while the machine is paused, not while it is working.	Sandboxer: No. stop and recreate. There is no way to change a running machine's size; you create a new one and copy your files across.	Sprites: No. one fixed shape. The shape is fixed, so there is nothing to resize.	Tensorlake: Yes. cores, memory, disk live	Vercel Sandbox: No. fixed for the session. The size is set when the sandbox is created and cannot be changed during its life.
GPUs	Agent 37: No. no GPU. No graphics processor is offered on any machine or plan.	Blaxel: Not published	Boat: No. no GPU. No size has a graphics processor, at any price.	boxd: No. no GPU. There is no graphics processor option.	Cloudflare Sandbox: No. no GPU. There is no graphics processor option; the largest machine is 4 cores of CPU.	Daytona: Yes. up to 8 GPUs	E2B: No. CPU only. There is no graphics processor option in any plan, tool or template.	InstaBox: No. no GPU. No graphics processor is offered on any plan.	Lizard: No. CPUs only. Sandboxes run on processors only; there is no graphics option.	Modal: Yes. up to 8 GPUs	Morph: Not published	Runtime: No. no GPU. Runtime lists a GPU request as an example of something it cannot do.	Sandboxer: No. no GPU. There are no graphics processors.	Sprites: No. no GPU. Sprites are not a graphics environment; Fly sells graphics machines as a separate product.	Tensorlake: With a catch. by request. Graphics machines exist but you have to ask on Slack to be given access, and they cannot be resized or run virtual machines inside.	Vercel Sandbox: No. no GPU. No graphics processor option is published for sandboxes.
Choose the region	Agent 37: Yes. 3 regions	Blaxel: With a catch. 4 regions, not all open. Four regions are listed, but not all of them are available to self-service accounts without asking.	Boat: No. no region choice. Machines run in Germany, Finland or France, and you cannot say which.	boxd: No. one EU region. There is one region, in Germany, and no way to choose another.	Cloudflare Sandbox: No. placement is automatic. Cloudflare puts each sandbox near the request, and a sandbox cannot be pinned to a location.	Daytona: Yes. US or EU	E2B: With a catch. 4 regions, support needed. Four regions exist, but outside the United States you have to contact support to be switched on.	InstaBox: No. no region setting. There is no region setting anywhere in the tools or docs, so you cannot ask for a European machine.	Lizard: Yes. 2 regions	Modal: Yes. broad or narrow regions	Morph: Not published	Runtime: No. one region. Everything runs in one place, in Virginia in the United States.	Sandboxer: Yes. US East or EU Central	Sprites: No. placement automatic. You cannot choose where a Sprite runs; placement is decided for you.	Tensorlake: Yes. US or EU	Vercel Sandbox: Yes. 19 regions
Runs in the EU	Agent 37: With a catch. France, backups in US. There is a French region, but backups and the account's control records are kept in the United States.	Blaxel: Yes. London and Frankfurt	Boat: Yes. Germany, Finland, France	boxd: Yes. Germany	Cloudflare Sandbox: With a catch. EU locations, cannot pin. Cloudflare has European locations, but a sandbox cannot be required to stay in one, so it may run outside the EU.	Daytona: Yes. eu region	E2B: Yes. europe-west1	InstaBox: No. US only. There is no European region and no way to ask for one.	Lizard: Yes. EU West (Limburg)	Modal: Yes. eu regions	Morph: Not published	Runtime: No. US only. Everything runs in Virginia in the United States.	Sandboxer: Yes. Helsinki	Sprites: With a catch. EU possible, not chosen. A Sprite may run in Europe because placement follows you, but you cannot require it to.	Tensorlake: Yes. EU endpoint	Vercel Sandbox: Yes. European regions

YesWith a catchNoNot publishedHover or select a mark to see the catch.

Questions to ask before you sign

Each one targets something the documentation does not answer

What is the largest single machine on my plan, and is the top size self-serve or a sales conversation?
Is disk part of the shape or a separate meter, and does it bill on capacity, written bytes or used bytes?
Is CPU shared or reserved, and what does a shared 4 vCPU actually guarantee?
Which region will the machine run in, and where are backups and control-plane data stored?
Can I get a GPU or an ARM machine, or is that a different product I would have to buy separately?

Common questions

Answered from the capability checks; each links to the provider-by-provider detail and its sources

Which sandbox providers offer “any size you like”?: Choose CPU and memory freely instead of picking from a short list of fixed sizes. Fully: Modal, Morph, Runtime and Tensorlake. With a catch: Blaxel, Cloudflare Sandbox, Daytona, E2B and Vercel Sandbox. Not at all: Agent 37, Boat, InstaBox, Lizard, Sandboxer, Sprites and boxd. See each provider's catch
Which sandbox providers offer “large machines”?: Machines of 16 vCPU or 32 GiB memory or more are available. Fully: Boat, InstaBox, Modal, Runtime, Sandboxer, Tensorlake and boxd. With a catch: Agent 37, Blaxel, Daytona, Morph and Vercel Sandbox. Not at all: Cloudflare Sandbox, E2B, Lizard and Sprites. See each provider's catch
Which sandbox providers offer “resize while running”?: Change CPU or memory without stopping the machine or losing what is running. Fully: Tensorlake. With a catch: Agent 37, Blaxel, Daytona, InstaBox, Morph and Runtime. Not at all: Boat, Cloudflare Sandbox, E2B, Lizard, Modal, Sandboxer, Sprites, Vercel Sandbox and boxd. See each provider's catch
Which sandbox providers offer “gPUs”?: Machines with a graphics processor, for running AI models or other GPU work inside the sandbox. Fully: Daytona and Modal. With a catch: Tensorlake. Not at all: Agent 37, Boat, Cloudflare Sandbox, E2B, InstaBox, Lizard, Runtime, Sandboxer, Sprites, Vercel Sandbox and boxd. See each provider's catch
Which sandbox providers offer “choose the region”?: You decide which part of the world the machine runs in. Fully: Agent 37, Daytona, Lizard, Modal, Sandboxer, Tensorlake and Vercel Sandbox. With a catch: Blaxel and E2B. Not at all: Boat, Cloudflare Sandbox, InstaBox, Runtime, Sprites and boxd. See each provider's catch
Which sandbox providers offer “runs in the EU”?: At least one region inside the European Union, for EU data rules. Fully: Blaxel, Boat, Daytona, E2B, Lizard, Modal, Sandboxer, Tensorlake, Vercel Sandbox and boxd. With a catch: Agent 37, Cloudflare Sandbox and Sprites. Not at all: InstaBox and Runtime. See each provider's catch

Part of The machine. Next: put two or three providers side by side.