Gemini Enterprise Agent Platform Code Execution vs Runtime

Gemini Enterprise Agent Platform Code Execution costs $0.085 per vCPU-hour and Runtime costs $0.025 per vCPU-hour. Gemini Enterprise Agent Platform Code Execution runs containers and limits a session to 336 hours. Runtime runs Firecracker microVMs and has no session limit.

Updated

Gemini Enterprise Agent Platform Code Execution

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

Runtime

Isolation
Firecracker microVM
Free tier
100 hours of a 1 GB machine in the first 30 days
Max session
No limit

What is different

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

Gemini Enterprise Agent Platform Code Execution
Runtime
vCPU, per hour
Gemini Enterprise Agent Platform Code Execution: $0.085
Runtime: $0.025
RAM, per GiB-hour
Gemini Enterprise Agent Platform Code Execution: $0.009
Runtime: $0.0075
Free tier
Gemini Enterprise Agent Platform Code Execution: 50 vCPU-hours and 100 GiB-hours free per month
Runtime: 100 hours of a 1 GB machine in the first 30 days
Billing
Gemini Enterprise Agent Platform Code Execution: Per second
Runtime: Active CPU time only
Max session
Gemini Enterprise Agent Platform Code Execution: 336 hours
Runtime: No limit
Largest sandbox
Gemini Enterprise Agent Platform Code Execution: 4 vCPU · 4 GiB
Runtime: 16 vCPU · 64 GiB
Isolation
Gemini Enterprise Agent Platform Code Execution: Container
Runtime: Firecracker microVM
Snapshots
Gemini Enterprise Agent Platform Code Execution: No
Runtime:
SDKs
Gemini Enterprise Agent Platform Code Execution: Python
Runtime: JavaScript / TypeScript, Python, Go, Ruby, Java

Full comparison

18 fields, at each provider's list price

Pricing

vCPU, per hour
Gemini Enterprise Agent Platform Code Execution: $0.085
Runtime: $0.025
RAM, per GiB-hour
Gemini Enterprise Agent Platform Code Execution: $0.009
Runtime: $0.0075
Storage
Gemini Enterprise Agent Platform Code Execution: Not listed
Runtime: $0.000119 per GiB-hour after 10 free GiB
Free tier
Gemini Enterprise Agent Platform Code Execution: 50 vCPU-hours and 100 GiB-hours free per month
Runtime: 100 hours of a 1 GB machine in the first 30 days
Paid plan from
Gemini Enterprise Agent Platform Code Execution: Pay as you go
Runtime: Pay as you go
Billing
Gemini Enterprise Agent Platform Code Execution: Per second
Runtime: Active CPU time only

Limits

Max session
Gemini Enterprise Agent Platform Code Execution: 336 hours
Runtime: No limit
Idle stop
Gemini Enterprise Agent Platform Code Execution: Not listed
Runtime: After 5 minutes
Largest sandbox
Gemini Enterprise Agent Platform Code Execution: 4 vCPU · 4 GiB
Runtime: 16 vCPU · 64 GiB
Concurrent sandboxes
Gemini Enterprise Agent Platform Code Execution: Not listed
Runtime: Up to 200

Platform

Isolation
Gemini Enterprise Agent Platform Code Execution: Container
Runtime: Firecracker microVM
GPU
Gemini Enterprise Agent Platform Code Execution: Not listed
Runtime: No
Snapshots
Gemini Enterprise Agent Platform Code Execution: No
Runtime:
Pause and resume
Gemini Enterprise Agent Platform Code Execution:
Runtime:

Developer

SDKs
Gemini Enterprise Agent Platform Code Execution: Python
Runtime: JavaScript / TypeScript, Python, Go, Ruby, Java
Integrations
Gemini Enterprise Agent Platform Code Execution: Not listed
Runtime: OpenAI Agents SDK, Vercel AI SDK, Claude Agent SDK, LangChain, MCP, Claude Code

Trust

License
Gemini Enterprise Agent Platform Code Execution: Not listed
Runtime: Not listed
BYOC
Gemini Enterprise Agent Platform Code Execution: Not listed
Runtime: Not listed

Hourly cost

One sandbox running for one hour

Gemini Enterprise Agent Platform Code Execution
Runtime
1 vCPU · 2 GiB
Gemini Enterprise Agent Platform Code Execution: $0.103
Runtime: $0.040
2 vCPU · 4 GiB
Gemini Enterprise Agent Platform Code Execution: $0.206
Runtime: $0.080
4 vCPU · 8 GiB
Gemini Enterprise Agent Platform Code Execution: $0.412
Runtime: $0.160

Compute only, at list rates.

Open the calculator

Which one fits

Based on the fields above

Runtime fits when

  • A session must run longer than 336 hours.
  • You want each sandbox in its own microVM.
  • You use the OpenAI Agents SDK, the Vercel AI SDK, the Claude Agent SDK, LangChain, MCP or Claude Code.
  • You want the lower list price: $0.080 against $0.206 an hour for 2 vCPU and 4 GiB.

More comparisons

See all comparisons

Related