Anthropic Code Execution vs Runloop

Anthropic Code Execution costs $0.05 per vCPU-hour and Runloop costs $0.108 per vCPU-hour. Anthropic Code Execution runs containers. Runloop runs 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

Runloop

Devboxes built for coding agents.

Isolation: MicroVM
Free tier: $50 credit
Max session: Not listed

Visit site Runloop profile

What is different

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

Field

Anthropic Code Execution

Runloop

vCPU, per hour: Anthropic Code Execution: $0.05; Runloop: $0.108
RAM, per GiB-hour: Anthropic Code Execution: Included; Runloop: $0.0252
Free tier: Anthropic Code Execution: 1,550 free hours per month; Runloop: $50 credit
Billing: Anthropic Code Execution: Bundled machine time; Runloop: Per second
Largest sandbox: Anthropic Code Execution: 1 vCPU · 5 GiB; Runloop: 16 vCPU · 64 GiB
Isolation: Anthropic Code Execution: Container; Runloop: MicroVM
SDKs: Anthropic Code Execution: Python, TypeScript, Go, Java, Ruby; Runloop: Python, TypeScript

Full comparison

18 fields, at each provider's list price

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

Runlooprunloop.ai/pricing

Pricing

vCPU, per hour: Anthropic Code Execution: $0.05; Runloop: $0.108
RAM, per GiB-hour: Anthropic Code Execution: Included; Runloop: $0.0252
Storage: Anthropic Code Execution: Not listed; Runloop: $0.00034236 per GiB-hour
Free tier: Anthropic Code Execution: 1,550 free hours per month; Runloop: $50 credit
Paid plan from: Anthropic Code Execution: Not listed; Runloop: Pay as you go
Billing: Anthropic Code Execution: Bundled machine time; Runloop: Per second

Limits

Max session: Anthropic Code Execution: Not listed; Runloop: Not listed
Idle stop: Anthropic Code Execution: Not listed; Runloop: Not listed
Largest sandbox: Anthropic Code Execution: 1 vCPU · 5 GiB; Runloop: 16 vCPU · 64 GiB
Concurrent sandboxes: Anthropic Code Execution: Not listed; Runloop: Not listed

Platform

Isolation: Anthropic Code Execution: Container; Runloop: MicroVM
GPU: Anthropic Code Execution: Not listed; Runloop: Not listed
Snapshots: Anthropic Code Execution: Not listed; Runloop:
Pause and resume: Anthropic Code Execution:; Runloop:

Developer

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

Trust

License: Anthropic Code Execution: Not listed; Runloop: Not listed
BYOC: Anthropic Code Execution: Not listed; Runloop: Deploy to VPC, Enterprise plan

Hourly cost

One sandbox running for one hour

Size

Anthropic Code Execution

Runloop

1 vCPU · 2 GiB: Anthropic Code Execution: $0.050; Runloop: $0.158
2 vCPU · 4 GiB: Anthropic Code Execution: $0.100; Runloop: $0.317
4 vCPU · 8 GiB: Anthropic Code Execution: $0.200; Runloop: $0.634

Compute only, at list rates.

Open the calculator

Which one fits

Based on the fields above

Anthropic Code Execution fits when

You want the lower list price: $0.100 against $0.317 an hour for 2 vCPU and 4 GiB.

Runloop fits when

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

More comparisons

See all comparisons

Anthropic Code Execution

Runloop

What is different

Full comparison

Pricing

Limits

Platform

Developer

Trust

Hourly cost

Which one fits

Anthropic Code Execution fits when

Runloop fits when

More comparisons

Related

Compare

Pricing

Browse