Azure Container Apps dynamic sessions vs Google Agent Platform Code Execution
Choose Azure Container Apps dynamic sessions for Azure-native apps running LLM-generated Python or Node code with egress off by default; choose Google Agent Platform Code Execution for Google Cloud agents that need stateful, no-network Python execution. Azure Container Apps dynamic sessions uses Hyper-V VM isolation; Google Agent Platform Code Execution uses gVisor isolation.
Key differences between Azure Container Apps dynamic sessions and Google Agent Platform Code Execution
- Isolation: Azure Container Apps dynamic sessions uses Hyper-V VM; Google Agent Platform Code Execution uses gVisor.
- Session length: 220 s / exec (Azure Container Apps dynamic sessions) versus 14-day state (Google Agent Platform Code Execution).
- SDKs and interfaces: Only Azure Container Apps dynamic sessions lists Azure CLI, LangChain, LlamaIndex and Semantic Kernel. Only Google Agent Platform Code Execution lists Python (Agent Platform SDK).
What they have in common
- Both companies are based in the United States.
- Both are cloud or model provider services.
- Neither is open source.
- Both list REST API.
Azure Container Apps dynamic sessions vs Google Agent Platform Code Execution at a glance
| Attribute | Azure Container Apps dynamic sessions | Google Agent Platform Code Execution |
|---|---|---|
| What it is | Azure service that hands out Hyper-V-isolated sessions from prewarmed pools, either as a built-in code interpreter or running your own container image. | Google-managed sandbox API (the docs also refer to it under Vertex AI Agent Engine) that lets agents deployed anywhere run Python or JavaScript in stateful, network-isolated environments. |
| Type | Cloud or model provider service | Cloud or model provider service |
| Isolation | Hyper-V isolation; each session is isolated by a Hyper-V boundary | gVisor-isolated container in a Google-managed tenant project; does not inherit the calling agent’s credentials |
| Open source | No | No |
| Self-host / BYOC | No / No | No / No |
| SDKs | REST API, Azure CLI, LangChain, LlamaIndex, Semantic Kernel | Python (Agent Platform SDK), REST API |
| Cold start (vendor claim) | Prewarmed pools allocate sessions in milliseconds (no specific figure) | Docs: create and execute code “in under a second”; a cold provision can take up to 2 minutes |
| Max session | Code interpreter: 220 s per execution; sessions deleted after a 5–60 min idle cooldown | State retained up to 14 days (configurable TTL) |
| Persistence | Session reuse by identifier; files in /mnt/data for the session’s life. Snapshots are not documented; sessions are ephemeral | Stateful across calls for the TTL; snapshots not supported for Code Execution sandboxes |
| Snapshots / pause | Not documented / Not documented | No / Not documented |
| GPU | Not documented | Not documented |
| Networking | Per-pool egress setting; egress disabled by default | No network access from the code execution sandbox; VPC Service Controls supported |
| Pricing | Code interpreter: $0.03 per session-hour (East US, Azure Retail Prices API), billed in one-hour increments. Custom container sessions billed on the Dedicated plan | $0.085 per vCPU-hour + $0.009 per GiB-hour, rounded to the second |
| Free tier | None stated for dynamic sessions | Not documented |
| Compliance | Not documented | VPC Service Controls, CMEK, data residency at rest and HIPAA per Google’s Agent Platform security table |
| Regions | 38 Azure regions listed in the docs | Not documented |
| Company headquarters | Redmond, Washington, United States | Mountain View, California, United States |
| Good fit for | Azure-native apps running LLM-generated Python or Node code with egress off by default | Google Cloud agents that need stateful, no-network Python execution |
Verified November 14, 2026 (Azure Container Apps dynamic sessions) and November 15, 2026 (Google Agent Platform Code Execution) from each provider’s documentation. Cold-start figures are vendor claims, not our measurements.
Which should you choose?
Reasons to choose Azure Container Apps dynamic sessions
- You build on Azure and want Hyper-V isolation without managing infrastructure
- You want egress disabled by default
- You use LangChain, LlamaIndex or Semantic Kernel
Reasons to choose Google Agent Platform Code Execution
- You want a no-network, gVisor-isolated Python tool
- You need state that lasts days, not minutes
- You are on Google Cloud and need CMEK or VPC Service Controls
Trade-offs to check first
- Azure Container Apps dynamic sessions: 220-second execution limit on the code interpreter
- Azure Container Apps dynamic sessions: Code interpreter sessions are billed in one-hour increments
- Google Agent Platform Code Execution: Python and JavaScript only, with a fixed library set
- Google Agent Platform Code Execution: No network access and no snapshots
Both are worth piloting with your own image and region. See the full Azure Container Apps dynamic sessions profile and Google Agent Platform Code Execution profile, or the complete comparison.
More comparisons
Frequently asked questions
Is Azure Container Apps dynamic sessions or Google Agent Platform Code Execution better for AI agents?
What is the difference between Azure Container Apps dynamic sessions and Google Agent Platform Code Execution?
Which is open source, Azure Container Apps dynamic sessions or Google Agent Platform Code Execution?
How do Azure Container Apps dynamic sessions and Google Agent Platform Code Execution isolate code?
How does Azure Container Apps dynamic sessions pricing compare with Google Agent Platform Code Execution?
Can you self-host Azure Container Apps dynamic sessions or Google Agent Platform Code Execution?
How long can sessions run on Azure Container Apps dynamic sessions and Google Agent Platform Code Execution?
Do Azure Container Apps dynamic sessions and Google Agent Platform Code Execution support snapshots or pause and resume?
Sources
- learn.microsoft.com/en-us/azure/container-apps/sessions
- learn.microsoft.com/en-us/azure/container-apps/sessions-code-interpreter
- learn.microsoft.com/en-us/azure/container-apps/session-pool
- azure.microsoft.com/en-us/pricing/details/container-apps/
- docs.cloud.google.com/gemini-enterprise-agent-platform/scale/sandbox/code-execution-overview
- docs.cloud.google.com/gemini-enterprise-agent-platform/scale/sandbox
- cloud.google.com/products/gemini-enterprise-agent-platform/pricing
- docs.cloud.google.com/gemini-enterprise-agent-platform/scale
Check before you rely on it. Products change quickly, and this page reflects public documentation as of November 15, 2026. Confirm anything that matters in the provider’s own documentation.
Cite this page
Agent Sandboxes. (2026). Azure Container Apps dynamic sessions vs Google Agent Platform Code Execution. agentsandboxes.org. Last reviewed November 15, 2026. https://agentsandboxes.org/compare/azure-dynamic-sessions-vs-google-code-execution/