Anthropic Code Execution vs Runta

Anthropic Code Execution costs $0.05 per vCPU-hour and Runta costs $0.0504 per vCPU-hour. Anthropic Code Execution runs containers.

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

Runta

Isolated computers where AI agents work and keep state.

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

Visit site Runta profile

What is different

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

Field

Anthropic Code Execution

Runta

vCPU, per hour: Anthropic Code Execution: $0.05; Runta: $0.0504
RAM, per GiB-hour: Anthropic Code Execution: Included; Runta: $0.0162
Free tier: Anthropic Code Execution: 1,550 free hours per month; Runta: $50 free credit
Billing: Anthropic Code Execution: Bundled machine time; Runta: Per second
SDKs: Anthropic Code Execution: Python, TypeScript, Go, Java, Ruby; Runta: Python, TypeScript

Full comparison

18 fields, at each provider's list price

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

Runtarunta.com/pricing

Pricing

vCPU, per hour: Anthropic Code Execution: $0.05; Runta: $0.0504
RAM, per GiB-hour: Anthropic Code Execution: Included; Runta: $0.0162
Storage: Anthropic Code Execution: Not listed; Runta: $0.000108 per GiB-hour
Free tier: Anthropic Code Execution: 1,550 free hours per month; Runta: $50 free credit
Paid plan from: Anthropic Code Execution: Not listed; Runta: Pay as you go
Billing: Anthropic Code Execution: Bundled machine time; Runta: Per second

Limits

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

Platform

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

Developer

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

Trust

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

Hourly cost

One sandbox running for one hour

Size

Anthropic Code Execution

Runta

1 vCPU · 2 GiB: Anthropic Code Execution: $0.050; Runta: $0.083
2 vCPU · 4 GiB: Anthropic Code Execution: $0.100; Runta: $0.166
4 vCPU · 8 GiB: Anthropic Code Execution: $0.200; Runta: $0.331

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 $0.166 an hour for 2 vCPU and 4 GiB.

Runta fits when

You use the OpenAI Agents SDK or Claude Code.
You need snapshots.
You need a desktop in the sandbox.

More comparisons

See all comparisons

Anthropic Code Execution

Runta

What is different

Full comparison

Pricing

Limits

Platform

Developer

Trust

Hourly cost

Which one fits

Anthropic Code Execution fits when

Runta fits when

More comparisons

Related

Compare

Pricing

Browse