Anthropic Code Execution vs Maritime

Anthropic Code Execution costs $0.05 per vCPU-hour. Anthropic Code Execution runs containers. Maritime runs Firecracker microVMs.

Updated Oct 15, 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

Maritime

Hosting for persistent AI agents and Linux desktops, each in its own micro-VM.

Isolation: Firecracker microVM
Free tier: 3 agents, forever
Max session: Not listed

Visit site Maritime profile

What is different

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

Field

Anthropic Code Execution

Maritime

Free tier: Anthropic Code Execution: 1,550 free hours per month; Maritime: 3 agents, forever
Isolation: Anthropic Code Execution: Container; Maritime: Firecracker microVM
SDKs: Anthropic Code Execution: Python, TypeScript, Go, Java, Ruby; Maritime: TypeScript, Python

Full comparison

18 fields, at each provider's list price

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

Maritimemaritime.sh/pricingmaritime.sh

Pricing

vCPU, per hour: Anthropic Code Execution: $0.05; Maritime: Not listed
RAM, per GiB-hour: Anthropic Code Execution: Included; Maritime: Not listed
Storage: Anthropic Code Execution: Not listed; Maritime: $2 per extra 5 GB per machine per month on Starter, $0.75 on Dedicated
Free tier: Anthropic Code Execution: 1,550 free hours per month; Maritime: 3 agents, forever
Paid plan from: Anthropic Code Execution: Not listed; Maritime: $20 / month
Billing: Anthropic Code Execution: Bundled machine time; Maritime: Not listed

Limits

Max session: Anthropic Code Execution: Not listed; Maritime: Not listed
Idle stop: Anthropic Code Execution: Not listed; Maritime: After 5 minutes
Largest sandbox: Anthropic Code Execution: 1 vCPU · 5 GiB; Maritime: Not listed
Concurrent sandboxes: Anthropic Code Execution: Not listed; Maritime: Up to 500

Platform

Isolation: Anthropic Code Execution: Container; Maritime: Firecracker microVM
GPU: Anthropic Code Execution: Not listed; Maritime: Not listed
Snapshots: Anthropic Code Execution: Not listed; Maritime: Not listed
Pause and resume: Anthropic Code Execution:; Maritime:

Developer

SDKs: Anthropic Code Execution: Python, TypeScript, Go, Java, Ruby; Maritime: TypeScript, Python
Integrations: Anthropic Code Execution: Not listed; Maritime: MCP, Claude Code, Claude Agent SDK, OpenAI Agents SDK, Vercel AI SDK

Trust

License: Anthropic Code Execution: Not listed; Maritime: Not listed
BYOC: Anthropic Code Execution: Not listed; Maritime: Not listed

Hourly cost

One sandbox running for one hour

Size

Anthropic Code Execution

Maritime

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

Compute only, at list rates.

Open the calculator

Which one fits

Based on the fields above

Maritime fits when

You want each sandbox in its own microVM.
You use MCP, Claude Code, the Claude Agent SDK, the OpenAI Agents SDK or the Vercel AI SDK.
You need a desktop in the sandbox.

More comparisons

See all comparisons

Anthropic Code Execution

Maritime

What is different

Full comparison

Pricing

Limits

Platform

Developer

Trust

Hourly cost

Which one fits

Maritime fits when

More comparisons

Related

Compare

Pricing

Browse