Cua Fleets vs Tenki Sandbox

Cua Fleets costs $0.044625 per vCPU-hour and Tenki Sandbox costs $0.0504 per vCPU-hour. Cua Fleets runs gVisor. Tenki Sandbox runs full VMs.

Updated Oct 14, 2026

Cua Fleets

Hosted Linux and Windows sandboxes for computer-use agents.

Isolation: gVisor
Free tier: Not listed
Max session: Not listed

Visit site Cua Fleets profile

Tenki Sandbox

Disposable Linux VMs for AI agents, driven by SDK or CLI.

Isolation: Full VM
Free tier: $100 credit, one time
Max session: Not listed

Visit site Tenki Sandbox profile

What is different

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

Field

Cua Fleets

Tenki Sandbox

vCPU, per hour: Cua Fleets: $0.044625; Tenki Sandbox: $0.0504
RAM, per GiB-hour: Cua Fleets: $0.0223125; Tenki Sandbox: $0.0162
Storage: Cua Fleets: Free; Tenki Sandbox: $0.000108 per GiB-hour after 5 free GiB
Largest sandbox: Cua Fleets: 8 vCPU · 32 GiB; Tenki Sandbox: 16 vCPU · 64 GiB
Isolation: Cua Fleets: gVisor; Tenki Sandbox: Full VM
Pause and resume: Cua Fleets: No; Tenki Sandbox:
SDKs: Cua Fleets: Python, TypeScript, Rust; Tenki Sandbox: Python, TypeScript, Go
Integrations: Cua Fleets: OpenAI Agents SDK, MCP; Tenki Sandbox: MCP

Full comparison

18 fields, at each provider's list price

Cua Fleetscua.ai/#pricing

Tenki Sandboxtenki.cloud/pricingtenki.cloud

Pricing

vCPU, per hour: Cua Fleets: $0.044625; Tenki Sandbox: $0.0504
RAM, per GiB-hour: Cua Fleets: $0.0223125; Tenki Sandbox: $0.0162
Storage: Cua Fleets: Free; Tenki Sandbox: $0.000108 per GiB-hour after 5 free GiB
Free tier: Cua Fleets: Not listed; Tenki Sandbox: $100 credit, one time
Paid plan from: Cua Fleets: Not listed; Tenki Sandbox: $200 / month
Billing: Cua Fleets: Per second; Tenki Sandbox: Per second

Limits

Max session: Cua Fleets: Not listed; Tenki Sandbox: Not listed
Idle stop: Cua Fleets: Not listed; Tenki Sandbox: Not listed
Largest sandbox: Cua Fleets: 8 vCPU · 32 GiB; Tenki Sandbox: 16 vCPU · 64 GiB
Concurrent sandboxes: Cua Fleets: Not listed; Tenki Sandbox: Up to 100

Platform

Isolation: Cua Fleets: gVisor; Tenki Sandbox: Full VM
GPU: Cua Fleets: Not listed; Tenki Sandbox: Not listed
Snapshots: Cua Fleets: Not listed; Tenki Sandbox:
Pause and resume: Cua Fleets: No; Tenki Sandbox:

Developer

SDKs: Cua Fleets: Python, TypeScript, Rust; Tenki Sandbox: Python, TypeScript, Go
Integrations: Cua Fleets: OpenAI Agents SDK, MCP; Tenki Sandbox: MCP

Trust

License: Cua Fleets: Not listed; Tenki Sandbox: Not listed
BYOC: Cua Fleets: Your AWS, Google Cloud, or Modal account; Tenki Sandbox: Not listed

Hourly cost

One sandbox running for one hour

Size

Cua Fleets

Tenki Sandbox

1 vCPU · 2 GiB: Cua Fleets: $0.089; Tenki Sandbox: $0.083
2 vCPU · 4 GiB: Cua Fleets: $0.179; Tenki Sandbox: $0.166
4 vCPU · 8 GiB: Cua Fleets: $0.357; Tenki Sandbox: $0.331

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.
You need the sandboxes in your own cloud account.
You need SOC 2.

Tenki Sandbox fits when

You want each sandbox to be a full VM.
You want the lower list price: $0.166 against $0.179 an hour for 2 vCPU and 4 GiB.
You need snapshots.
You need pause and resume.

More comparisons

See all comparisons

Cua Fleets

Tenki Sandbox

What is different

Full comparison

Pricing

Limits

Platform

Developer

Trust

Hourly cost

Which one fits

Cua Fleets fits when

Tenki Sandbox fits when

More comparisons

Related

Compare

Pricing

Browse