Shellbox vs Tensorlake Sandboxes

Shellbox costs $0.01 per vCPU-hour and Tensorlake Sandboxes costs $0.07 per vCPU-hour. Shellbox runs Firecracker microVMs and has no session limit. Tensorlake Sandboxes runs Firecracker microVMs, offers GPUs and has no session limit.

Updated

Shellbox

Isolation
Firecracker microVM
Free tier
Not listed
Max session
No limit

Tensorlake Sandboxes

Isolation
Firecracker microVM
Free tier
Free plan, $0 forever
Max session
No limit

What is different

8 fields differ. The rest are the same or not listed.

Shellbox
Tensorlake Sandboxes
vCPU, per hour
Shellbox: $0.01
Tensorlake Sandboxes: $0.07
RAM, per GiB-hour
Shellbox: Included
Tensorlake Sandboxes: $0.015
Storage
Shellbox: A stopped box costs $0.50 per x1 slot per month
Tensorlake Sandboxes: $0.0002 per GiB-hour
Billing
Shellbox: Bundled machine time
Tensorlake Sandboxes: Active CPU time only
Idle stop
Shellbox: After 2 minutes
Tensorlake Sandboxes: After 10 minutes
Largest sandbox
Shellbox: 16 vCPU · 32 GiB
Tensorlake Sandboxes: 16 vCPU · 64 GiB
Concurrent sandboxes
Shellbox: Up to 16
Tensorlake Sandboxes: Up to 1,000
Integrations
Shellbox: Claude Code
Tensorlake Sandboxes: OpenAI Agents SDK

Full comparison

18 fields, at each provider's list price

Pricing

vCPU, per hour
Shellbox: $0.01
Tensorlake Sandboxes: $0.07
RAM, per GiB-hour
Shellbox: Included
Tensorlake Sandboxes: $0.015
Storage
Shellbox: A stopped box costs $0.50 per x1 slot per month
Tensorlake Sandboxes: $0.0002 per GiB-hour
Free tier
Shellbox: Not listed
Tensorlake Sandboxes: Free plan, $0 forever
Paid plan from
Shellbox: Pay as you go
Tensorlake Sandboxes: Pay as you go
Billing
Shellbox: Bundled machine time
Tensorlake Sandboxes: Active CPU time only

Limits

Max session
Shellbox: No limit
Tensorlake Sandboxes: No limit
Idle stop
Shellbox: After 2 minutes
Tensorlake Sandboxes: After 10 minutes
Largest sandbox
Shellbox: 16 vCPU · 32 GiB
Tensorlake Sandboxes: 16 vCPU · 64 GiB
Concurrent sandboxes
Shellbox: Up to 16
Tensorlake Sandboxes: Up to 1,000

Platform

Isolation
Shellbox: Firecracker microVM
Tensorlake Sandboxes: Firecracker microVM
GPU
Shellbox: Not listed
Tensorlake Sandboxes:
Snapshots
Shellbox:
Tensorlake Sandboxes:
Pause and resume
Shellbox:
Tensorlake Sandboxes:

Developer

SDKs
Shellbox: Not listed
Tensorlake Sandboxes: Python, TypeScript
Integrations
Shellbox: Claude Code
Tensorlake Sandboxes: OpenAI Agents SDK

Trust

License
Shellbox: Not listed
Tensorlake Sandboxes: Not listed
BYOC
Shellbox: Not listed
Tensorlake Sandboxes: AWS, GCP, Azure, CoreWeave, Nebius or bare metal

Hourly cost

One sandbox running for one hour

Shellbox
Tensorlake Sandboxes
1 vCPU · 2 GiB
Shellbox: $0.010
Tensorlake Sandboxes: $0.100
2 vCPU · 4 GiB
Shellbox: $0.020
Tensorlake Sandboxes: $0.200
4 vCPU · 8 GiB
Shellbox: $0.040
Tensorlake Sandboxes: $0.400

Compute only, at list rates.

Open the calculator

Which one fits

Based on the fields above

Shellbox fits when

  • You use Claude Code.
  • You want the lower list price: $0.020 against $0.200 an hour for 2 vCPU and 4 GiB.

Tensorlake Sandboxes fits when

  • You need GPUs.
  • You use the OpenAI Agents SDK.
  • You need a desktop in the sandbox.
  • You need the sandboxes in your own cloud account.

More comparisons

See all comparisons

Related