Anthropic Code Execution vs SF Compute Autoresearch Sandboxes

Anthropic Code Execution costs $0.05 per vCPU-hour. SF Compute Autoresearch Sandboxes bills memory only, at $0.04572 per GiB-hour. Anthropic Code Execution runs containers. SF Compute Autoresearch Sandboxes runs microVMs.

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

SF Compute Autoresearch Sandboxes

Isolated microVMs for AI agents that fork from a saved snapshot, part of SF Compute Autoresearch.

Isolation: MicroVM
Free tier: None
Max session: Not listed

Visit site SF Compute Autoresearch Sandboxes profile

What is different

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

Field

Anthropic Code Execution

SF Compute Autoresearch Sandboxes

vCPU, per hour: Anthropic Code Execution: $0.05; SF Compute Autoresearch Sandboxes: Included
RAM, per GiB-hour: Anthropic Code Execution: Included; SF Compute Autoresearch Sandboxes: $0.04572
Free tier: Anthropic Code Execution: 1,550 free hours per month; SF Compute Autoresearch Sandboxes: None
Billing: Anthropic Code Execution: Bundled machine time; SF Compute Autoresearch Sandboxes: Memory only
Largest sandbox: Anthropic Code Execution: 1 vCPU · 5 GiB; SF Compute Autoresearch Sandboxes: 4 vCPU · 8 GiB
Isolation: Anthropic Code Execution: Container; SF Compute Autoresearch Sandboxes: MicroVM

Full comparison

18 fields, at each provider's list price

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

SF Compute Autoresearch Sandboxesautoresearch.sfcompute.com

Pricing

vCPU, per hour: Anthropic Code Execution: $0.05; SF Compute Autoresearch Sandboxes: Included
RAM, per GiB-hour: Anthropic Code Execution: Included; SF Compute Autoresearch Sandboxes: $0.04572
Storage: Anthropic Code Execution: Not listed; SF Compute Autoresearch Sandboxes: Sandbox snapshots $0.10 per GiB-month of deduplicated bytes, $0.05 per GiB-month in cold storage
Free tier: Anthropic Code Execution: 1,550 free hours per month; SF Compute Autoresearch Sandboxes: None
Paid plan from: Anthropic Code Execution: Not listed; SF Compute Autoresearch Sandboxes: Pay as you go
Billing: Anthropic Code Execution: Bundled machine time; SF Compute Autoresearch Sandboxes: Memory only

Limits

Max session: Anthropic Code Execution: Not listed; SF Compute Autoresearch Sandboxes: Not listed
Idle stop: Anthropic Code Execution: Not listed; SF Compute Autoresearch Sandboxes: Not listed
Largest sandbox: Anthropic Code Execution: 1 vCPU · 5 GiB; SF Compute Autoresearch Sandboxes: 4 vCPU · 8 GiB
Concurrent sandboxes: Anthropic Code Execution: Not listed; SF Compute Autoresearch Sandboxes: Up to 4,096

Platform

Isolation: Anthropic Code Execution: Container; SF Compute Autoresearch Sandboxes: MicroVM
GPU: Anthropic Code Execution: Not listed; SF Compute Autoresearch Sandboxes: Not listed
Snapshots: Anthropic Code Execution: Not listed; SF Compute Autoresearch Sandboxes:
Pause and resume: Anthropic Code Execution:; SF Compute Autoresearch Sandboxes:

Developer

SDKs: Anthropic Code Execution: Python, TypeScript, Go, Java, Ruby; SF Compute Autoresearch Sandboxes: Not listed
Integrations: Anthropic Code Execution: Not listed; SF Compute Autoresearch Sandboxes: MCP, Claude Code

Trust

License: Anthropic Code Execution: Not listed; SF Compute Autoresearch Sandboxes: Not listed
BYOC: Anthropic Code Execution: Not listed; SF Compute Autoresearch Sandboxes: Not listed

Hourly cost

One sandbox running for one hour

Size

Anthropic Code Execution

SF Compute Autoresearch Sandboxes

1 vCPU · 2 GiB: Anthropic Code Execution: $0.050; SF Compute Autoresearch Sandboxes: $0.091
2 vCPU · 4 GiB: Anthropic Code Execution: $0.100; SF Compute Autoresearch Sandboxes: $0.183
4 vCPU · 8 GiB: Anthropic Code Execution: $0.200; SF Compute Autoresearch Sandboxes: $0.366

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 $0.183 an hour for 2 vCPU and 4 GiB.
You want to start without paying.
You need SOC 2 Type II and ISO 27001.

SF Compute Autoresearch Sandboxes fits when

You want each sandbox in its own microVM.
You use MCP or Claude Code.
You need snapshots.
You want one rate for memory, with CPU included.

More comparisons

See all comparisons

Anthropic Code Execution

SF Compute Autoresearch Sandboxes

What is different

Full comparison

Pricing

Limits

Platform

Developer

Trust

Hourly cost

Which one fits

Anthropic Code Execution fits when

SF Compute Autoresearch Sandboxes fits when

More comparisons

Related

Compare

Pricing

Browse