Gemini Enterprise Agent Platform Code Execution vs SF Compute Autoresearch Sandboxes

Gemini Enterprise Agent Platform Code Execution costs $0.085 per vCPU-hour. SF Compute Autoresearch Sandboxes bills memory only, at $0.04572 per GiB-hour. Gemini Enterprise Agent Platform Code Execution runs containers and limits a session to 336 hours. SF Compute Autoresearch Sandboxes runs microVMs.

Updated Oct 23, 2026

Gemini Enterprise Agent Platform Code Execution

Managed sandboxes that run code for AI agents.

Isolation: Container
Free tier: 50 vCPU-hours and 100 GiB-hours free per month
Max session: 336 hours

Visit site Gemini Enterprise Agent Platform 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

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

Field

Gemini Enterprise Agent Platform Code Execution

SF Compute Autoresearch Sandboxes

vCPU, per hour: Gemini Enterprise Agent Platform Code Execution: $0.085; SF Compute Autoresearch Sandboxes: Included
RAM, per GiB-hour: Gemini Enterprise Agent Platform Code Execution: $0.009; SF Compute Autoresearch Sandboxes: $0.04572
Free tier: Gemini Enterprise Agent Platform Code Execution: 50 vCPU-hours and 100 GiB-hours free per month; SF Compute Autoresearch Sandboxes: None
Billing: Gemini Enterprise Agent Platform Code Execution: Per second; SF Compute Autoresearch Sandboxes: Memory only
Largest sandbox: Gemini Enterprise Agent Platform Code Execution: 4 vCPU · 4 GiB; SF Compute Autoresearch Sandboxes: 4 vCPU · 8 GiB
Isolation: Gemini Enterprise Agent Platform Code Execution: Container; SF Compute Autoresearch Sandboxes: MicroVM
Snapshots: Gemini Enterprise Agent Platform Code Execution: No; SF Compute Autoresearch Sandboxes:

Full comparison

18 fields, at each provider's list price

Gemini Enterprise Agent Platform Code Executioncloud.google.com/products/gemini-enterprise-agent-platform/pricingcloud.google.com

SF Compute Autoresearch Sandboxesautoresearch.sfcompute.com

Pricing

vCPU, per hour: Gemini Enterprise Agent Platform Code Execution: $0.085; SF Compute Autoresearch Sandboxes: Included
RAM, per GiB-hour: Gemini Enterprise Agent Platform Code Execution: $0.009; SF Compute Autoresearch Sandboxes: $0.04572
Storage: Gemini Enterprise Agent Platform 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: Gemini Enterprise Agent Platform Code Execution: 50 vCPU-hours and 100 GiB-hours free per month; SF Compute Autoresearch Sandboxes: None
Paid plan from: Gemini Enterprise Agent Platform Code Execution: Pay as you go; SF Compute Autoresearch Sandboxes: Pay as you go
Billing: Gemini Enterprise Agent Platform Code Execution: Per second; SF Compute Autoresearch Sandboxes: Memory only

Limits

Max session: Gemini Enterprise Agent Platform Code Execution: 336 hours; SF Compute Autoresearch Sandboxes: Not listed
Idle stop: Gemini Enterprise Agent Platform Code Execution: Not listed; SF Compute Autoresearch Sandboxes: Not listed
Largest sandbox: Gemini Enterprise Agent Platform Code Execution: 4 vCPU · 4 GiB; SF Compute Autoresearch Sandboxes: 4 vCPU · 8 GiB
Concurrent sandboxes: Gemini Enterprise Agent Platform Code Execution: Not listed; SF Compute Autoresearch Sandboxes: Up to 4,096

Platform

Isolation: Gemini Enterprise Agent Platform Code Execution: Container; SF Compute Autoresearch Sandboxes: MicroVM
GPU: Gemini Enterprise Agent Platform Code Execution: Not listed; SF Compute Autoresearch Sandboxes: Not listed
Snapshots: Gemini Enterprise Agent Platform Code Execution: No; SF Compute Autoresearch Sandboxes:
Pause and resume: Gemini Enterprise Agent Platform Code Execution:; SF Compute Autoresearch Sandboxes:

Developer

SDKs: Gemini Enterprise Agent Platform Code Execution: Python; SF Compute Autoresearch Sandboxes: Not listed
Integrations: Gemini Enterprise Agent Platform Code Execution: Not listed; SF Compute Autoresearch Sandboxes: MCP, Claude Code

Trust

License: Gemini Enterprise Agent Platform Code Execution: Not listed; SF Compute Autoresearch Sandboxes: Not listed
BYOC: Gemini Enterprise Agent Platform Code Execution: Not listed; SF Compute Autoresearch Sandboxes: Not listed

Hourly cost

One sandbox running for one hour

Size

Gemini Enterprise Agent Platform Code Execution

SF Compute Autoresearch Sandboxes

1 vCPU · 2 GiB: Gemini Enterprise Agent Platform Code Execution: $0.103; SF Compute Autoresearch Sandboxes: $0.091
2 vCPU · 4 GiB: Gemini Enterprise Agent Platform Code Execution: $0.206; SF Compute Autoresearch Sandboxes: $0.183
4 vCPU · 8 GiB: Gemini Enterprise Agent Platform Code Execution: $0.412; SF Compute Autoresearch Sandboxes: $0.366

Compute only, at list rates.

Open the calculator

Which one fits

Based on the fields above

Gemini Enterprise Agent Platform Code Execution fits when

You want to start without paying.

SF Compute Autoresearch Sandboxes fits when

You want each sandbox in its own microVM.
You use MCP or Claude Code.
You want the lower list price: $0.183 against $0.206 an hour for 2 vCPU and 4 GiB.
You need snapshots.

More comparisons

See all comparisons

Gemini Enterprise Agent Platform Code Execution

SF Compute Autoresearch Sandboxes

What is different

Full comparison

Pricing

Limits

Platform

Developer

Trust

Hourly cost

Which one fits

Gemini Enterprise Agent Platform Code Execution fits when

SF Compute Autoresearch Sandboxes fits when

More comparisons

Related

Compare

Pricing

Browse