Anthropic Code Execution vs xShellz Agent Shell

Anthropic Code Execution costs $0.05 per vCPU-hour. Anthropic Code Execution runs containers. xShellz Agent Shell runs gVisor and has no session limit.

Updated Oct 23, 2026

Anthropic Code Execution

Sandboxed Python and bash containers that Claude runs through the Anthropic API.

Isolation: Container
Free tier: 1,550 free hours per month
Max session: Not listed

Visit site Anthropic Code Execution profile

xShellz Agent Shell

Always-on Linux boxes for AI agents, isolated with gVisor.

Isolation: gVisor
Free tier: Free plan, 1 box with 0.5 vCPU and 512 MB
Max session: No limit

Visit site xShellz Agent Shell profile

What is different

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

Field

Anthropic Code Execution

xShellz Agent Shell

Free tier: Anthropic Code Execution: 1,550 free hours per month; xShellz Agent Shell: Free plan, 1 box with 0.5 vCPU and 512 MB
Largest sandbox: Anthropic Code Execution: 1 vCPU · 5 GiB; xShellz Agent Shell: 4 vCPU · 4 GiB
Isolation: Anthropic Code Execution: Container; xShellz Agent Shell: gVisor
SDKs: Anthropic Code Execution: Python, TypeScript, Go, Java, Ruby; xShellz Agent Shell: Python, JavaScript / TypeScript, Go, Java, Ruby, Rust

Full comparison

18 fields, at each provider's list price

Anthropic Code Executionplatform.claude.com/docs/en/about-claude/pricingplatform.claude.com

xShellz Agent Shellxshellz.com/pricingxshellz.com

Pricing

vCPU, per hour: Anthropic Code Execution: $0.05; xShellz Agent Shell: Not listed
RAM, per GiB-hour: Anthropic Code Execution: Included; xShellz Agent Shell: Included
Storage: Anthropic Code Execution: Not listed; xShellz Agent Shell: Free
Free tier: Anthropic Code Execution: 1,550 free hours per month; xShellz Agent Shell: Free plan, 1 box with 0.5 vCPU and 512 MB
Paid plan from: Anthropic Code Execution: Not listed; xShellz Agent Shell: $10 / month
Billing: Anthropic Code Execution: Bundled machine time; xShellz Agent Shell: Bundled machine time

Limits

Max session: Anthropic Code Execution: Not listed; xShellz Agent Shell: No limit
Idle stop: Anthropic Code Execution: Not listed; xShellz Agent Shell: Not listed
Largest sandbox: Anthropic Code Execution: 1 vCPU · 5 GiB; xShellz Agent Shell: 4 vCPU · 4 GiB
Concurrent sandboxes: Anthropic Code Execution: Not listed; xShellz Agent Shell: Up to 5

Platform

Isolation: Anthropic Code Execution: Container; xShellz Agent Shell: gVisor
GPU: Anthropic Code Execution: Not listed; xShellz Agent Shell: Not listed
Snapshots: Anthropic Code Execution: Not listed; xShellz Agent Shell: Not listed
Pause and resume: Anthropic Code Execution:; xShellz Agent Shell:

Developer

SDKs: Anthropic Code Execution: Python, TypeScript, Go, Java, Ruby; xShellz Agent Shell: Python, JavaScript / TypeScript, Go, Java, Ruby, Rust
Integrations: Anthropic Code Execution: Not listed; xShellz Agent Shell: MCP, Claude Code

Trust

License: Anthropic Code Execution: Not listed; xShellz Agent Shell: Not listed
BYOC: Anthropic Code Execution: Not listed; xShellz Agent Shell: Not listed

Hourly cost

One sandbox running for one hour

Size

Anthropic Code Execution

xShellz Agent Shell

1 vCPU · 2 GiB: Anthropic Code Execution: $0.050; xShellz Agent Shell: Not listed
2 vCPU · 4 GiB: Anthropic Code Execution: $0.100; xShellz Agent Shell: Not listed
4 vCPU · 8 GiB: Anthropic Code Execution: $0.200; xShellz Agent Shell: Not listed

Compute only, at list rates.

Open the calculator

Which one fits

Based on the fields above

Anthropic Code Execution fits when

You need SOC 2 Type II and ISO 27001.

xShellz Agent Shell fits when

You use MCP or Claude Code.
You need GDPR.

More comparisons

See all comparisons

Anthropic Code Execution

xShellz Agent Shell

What is different

Full comparison

Pricing

Limits

Platform

Developer

Trust

Hourly cost

Which one fits

Anthropic Code Execution fits when

xShellz Agent Shell fits when

More comparisons

Related

Compare

Pricing

Browse