Cua Fleets vs Lizard Sandboxes

Cua Fleets costs $0.044625 per vCPU-hour and Lizard Sandboxes costs $0.0081 per vCPU-hour. Cua Fleets runs gVisor. Lizard Sandboxes runs Firecracker microVMs and has no session limit.

Updated

Cua Fleets

Isolation
gVisor
Free tier
Not listed
Max session
Not listed

Lizard Sandboxes

Isolation
Firecracker microVM
Free tier
7-day trial with $5 in trial credits
Max session
No limit

What is different

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

Cua Fleets
Lizard Sandboxes
vCPU, per hour
Cua Fleets: $0.044625
Lizard Sandboxes: $0.0081
RAM, per GiB-hour
Cua Fleets: $0.0223125
Lizard Sandboxes: Included
Storage
Cua Fleets: Free
Lizard Sandboxes: Local disk is in the rate. Persistent Volumes $0.14 per GB a month
Billing
Cua Fleets: Per second
Lizard Sandboxes: Bundled machine time
Largest sandbox
Cua Fleets: 8 vCPU · 32 GiB
Lizard Sandboxes: 8 vCPU · 16 GiB
Isolation
Cua Fleets: gVisor
Lizard Sandboxes: Firecracker microVM
Pause and resume
Cua Fleets: No
Lizard Sandboxes:
SDKs
Cua Fleets: Python, TypeScript, Rust
Lizard Sandboxes: TypeScript, Python

Full comparison

18 fields, at each provider's list price

Pricing

vCPU, per hour
Cua Fleets: $0.044625
Lizard Sandboxes: $0.0081
RAM, per GiB-hour
Cua Fleets: $0.0223125
Lizard Sandboxes: Included
Storage
Cua Fleets: Free
Lizard Sandboxes: Local disk is in the rate. Persistent Volumes $0.14 per GB a month
Free tier
Cua Fleets: Not listed
Lizard Sandboxes: 7-day trial with $5 in trial credits
Paid plan from
Cua Fleets: Not listed
Lizard Sandboxes: $19 / month
Billing
Cua Fleets: Per second
Lizard Sandboxes: Bundled machine time

Limits

Max session
Cua Fleets: Not listed
Lizard Sandboxes: No limit
Idle stop
Cua Fleets: Not listed
Lizard Sandboxes: Not listed
Largest sandbox
Cua Fleets: 8 vCPU · 32 GiB
Lizard Sandboxes: 8 vCPU · 16 GiB
Concurrent sandboxes
Cua Fleets: Not listed
Lizard Sandboxes: Up to 100

Platform

Isolation
Cua Fleets: gVisor
Lizard Sandboxes: Firecracker microVM
GPU
Cua Fleets: Not listed
Lizard Sandboxes: Not listed
Snapshots
Cua Fleets: Not listed
Lizard Sandboxes:
Pause and resume
Cua Fleets: No
Lizard Sandboxes:

Developer

SDKs
Cua Fleets: Python, TypeScript, Rust
Lizard Sandboxes: TypeScript, Python
Integrations
Cua Fleets: OpenAI Agents SDK, MCP
Lizard Sandboxes: Not listed

Trust

License
Cua Fleets: Not listed
Lizard Sandboxes: Not listed
BYOC
Cua Fleets: Your AWS, Google Cloud, or Modal account
Lizard Sandboxes: Not listed

Hourly cost

One sandbox running for one hour

Cua Fleets
Lizard Sandboxes
1 vCPU · 2 GiB
Cua Fleets: $0.089
Lizard Sandboxes: $0.008
2 vCPU · 4 GiB
Cua Fleets: $0.179
Lizard Sandboxes: $0.016
4 vCPU · 8 GiB
Cua Fleets: $0.357
Lizard Sandboxes: $0.032

Compute only, at list rates.

Open the calculator

Which one fits

Based on the fields above

Cua Fleets fits when

  • You use the OpenAI Agents SDK or MCP.
  • You need the sandboxes in your own cloud account.
  • You need a sandbox larger than 8 vCPU · 16 GiB.
  • You need SOC 2.

Lizard Sandboxes fits when

  • You want each sandbox in its own microVM.
  • You want the lower list price: $0.016 against $0.179 an hour for 2 vCPU and 4 GiB.
  • You need snapshots.
  • You need pause and resume.

More comparisons

See all comparisons

Related