Anthropic Code Execution vs inis.run

Anthropic Code Execution costs $0.05 per vCPU-hour. Anthropic Code Execution runs containers. inis.run runs full VMs and limits a session to 24 hours.

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

inis.run

Isolated Linux sandboxes for AI-generated code.

Isolation: Full VM
Free tier: €1.00 free trial credit, no card required
Max session: 24 hours

Visit site inis.run profile

What is different

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

Field

Anthropic Code Execution

inis.run

Free tier: Anthropic Code Execution: 1,550 free hours per month; inis.run: €1.00 free trial credit, no card required
Largest sandbox: Anthropic Code Execution: 1 vCPU · 5 GiB; inis.run: 4 vCPU · 8 GiB
Isolation: Anthropic Code Execution: Container; inis.run: Full VM
SDKs: Anthropic Code Execution: Python, TypeScript, Go, Java, Ruby; inis.run: Python, TypeScript

Full comparison

18 fields, at each provider's list price

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

inis.runinis.run/pricing

Pricing

vCPU, per hour: Anthropic Code Execution: $0.05; inis.run: Not listed
RAM, per GiB-hour: Anthropic Code Execution: Included; inis.run: Included
Storage: Anthropic Code Execution: Not listed; inis.run: Paused sessions and persistent volumes cost about €0.07 per GB per month. Paused sessions are billed for storage, not compute.
Free tier: Anthropic Code Execution: 1,550 free hours per month; inis.run: €1.00 free trial credit, no card required
Paid plan from: Anthropic Code Execution: Not listed; inis.run: Pay as you go
Billing: Anthropic Code Execution: Bundled machine time; inis.run: Bundled machine time

Limits

Max session: Anthropic Code Execution: Not listed; inis.run: 24 hours
Idle stop: Anthropic Code Execution: Not listed; inis.run: Not listed
Largest sandbox: Anthropic Code Execution: 1 vCPU · 5 GiB; inis.run: 4 vCPU · 8 GiB
Concurrent sandboxes: Anthropic Code Execution: Not listed; inis.run: Up to 10

Platform

Isolation: Anthropic Code Execution: Container; inis.run: Full VM
GPU: Anthropic Code Execution: Not listed; inis.run: No
Snapshots: Anthropic Code Execution: Not listed; inis.run:
Pause and resume: Anthropic Code Execution:; inis.run:

Developer

SDKs: Anthropic Code Execution: Python, TypeScript, Go, Java, Ruby; inis.run: Python, TypeScript
Integrations: Anthropic Code Execution: Not listed; inis.run: Vercel AI SDK, LangChain, OpenAI Agents SDK, MCP

Trust

License: Anthropic Code Execution: Not listed; inis.run: Not listed
BYOC: Anthropic Code Execution: Not listed; inis.run: In your own cloud account, from €30,000/year

Hourly cost

One sandbox running for one hour

Size

Anthropic Code Execution

inis.run

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

Compute only, at list rates.

Open the calculator

Which one fits

Based on the fields above

inis.run fits when

You want each sandbox to be a full VM.
You use the Vercel AI SDK, LangChain, the OpenAI Agents SDK or MCP.
You need snapshots.
You need the sandboxes in your own cloud account.

More comparisons

See all comparisons

Anthropic Code Execution

inis.run

What is different

Full comparison

Pricing

Limits

Platform

Developer

Trust

Hourly cost

Which one fits

inis.run fits when

More comparisons

Related

Compare

Pricing

Browse