AWS Bedrock AgentCore vs Azure Container Apps dynamic sessions
Choose AWS Bedrock AgentCore for teams already on AWS that need IAM- and VPC-integrated code execution for agents; choose Azure Container Apps dynamic sessions for Azure-native apps running LLM-generated Python or Node code with egress off by default. AWS Bedrock AgentCore uses MicroVM (Runtime) isolation; Azure Container Apps dynamic sessions uses Hyper-V VM isolation.
Key differences between AWS Bedrock AgentCore and Azure Container Apps dynamic sessions
- Isolation: AWS Bedrock AgentCore uses MicroVM (Runtime); Azure Container Apps dynamic sessions uses Hyper-V VM.
- Session length: Up to 8 h (AWS Bedrock AgentCore) versus 220 s / exec (Azure Container Apps dynamic sessions).
- SDKs and interfaces: Only AWS Bedrock AgentCore lists Python (AgentCore SDK), AWS SDKs and AWS CLI. Only Azure Container Apps dynamic sessions lists REST API, Azure CLI, LangChain, LlamaIndex and Semantic Kernel.
What they have in common
- Both companies are based in the United States.
- Both are cloud or model provider services.
- Neither is open source.
AWS Bedrock AgentCore vs Azure Container Apps dynamic sessions at a glance
| Attribute | AWS Bedrock AgentCore | Azure Container Apps dynamic sessions |
|---|---|---|
| What it is | AWS’s managed agent platform: a Code Interpreter tool for running agent-generated code and a Runtime that hosts each agent session in its own microVM. | 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. |
| Type | Cloud or model provider service | Cloud or model provider service |
| Isolation | Runtime: a dedicated microVM per user session with isolated CPU, memory and filesystem, sanitized after the session. Code Interpreter: documented as a containerized environment within AgentCore | Hyper-V isolation; each session is isolated by a Hyper-V boundary |
| Open source | No | No |
| Self-host / BYOC | No / Not documented | No / No |
| SDKs | Python (AgentCore SDK), AWS SDKs, AWS CLI | REST API, Azure CLI, LangChain, LlamaIndex, Semantic Kernel |
| Cold start (vendor claim) | No numeric claim; Runtime v2 restores from snapshots for consistent cold starts | Prewarmed pools allocate sessions in milliseconds (no specific figure) |
| Max session | Code Interpreter: 15 min default, up to 8 hours. Runtime microVMs: up to 8 hours, stop after 15 min idle | Code interpreter: 220 s per execution; sessions deleted after a 5–60 min idle cooldown |
| Persistence | State persists between executions within a session; Runtime can persist filesystem across stop/resume (managed session storage in preview). Large files via S3 | Session reuse by identifier; files in /mnt/data for the session’s life. Snapshots are not documented; sessions are ephemeral |
| Snapshots / pause | Not documented / Not documented | Not documented / Not documented |
| GPU | Not documented for Code Interpreter or Runtime microVMs; the separate Runtime “Instances” compute type is described for agents that need GPUs | Not documented |
| Networking | Code Interpreter network modes: Sandbox (isolated) or Public; VPC connectivity supported | Per-pool egress setting; egress disabled by default |
| Pricing | Code Interpreter: $0.0895 per vCPU-hour + $0.00945 per GB-hour, billed per second; CPU billed on actual consumption (not during I/O wait), memory on peak | 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 |
| Free tier | No product-specific free tier is listed; general AWS new-customer credits apply | None stated for dynamic sessions |
| Compliance | HIPAA eligible and pursuing FedRAMP per the AWS FAQ; AWS reports an internal assessment against programmes including ISO, PCI and SOC, with third-party audits in upcoming cycles | Not documented |
| Regions | 15 AWS Regions across North America, South America, Europe and Asia Pacific | 38 Azure regions listed in the docs |
| Company headquarters | Seattle, Washington, United States | Redmond, Washington, United States |
| Good fit for | Teams already on AWS that need IAM- and VPC-integrated code execution for agents | Azure-native apps running LLM-generated Python or Node code with egress off by default |
Verified November 14, 2026 from each provider’s documentation. Cold-start figures are vendor claims, not our measurements.
Which should you choose?
Reasons to choose AWS Bedrock AgentCore
- You are already on AWS and want IAM, VPC and CloudTrail integration
- You need long-running sessions (up to 8 hours)
- You want consumption-based CPU billing that skips I/O wait
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
Trade-offs to check first
- AWS Bedrock AgentCore: AWS-only; no self-hosting or other clouds
- AWS Bedrock AgentCore: Code Interpreter isolation is documented only as “containerized”
- 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
Both are worth piloting with your own image and region. See the full AWS Bedrock AgentCore profile and Azure Container Apps dynamic sessions profile, or the complete comparison.
More comparisons
- AWS Bedrock AgentCore vs E2B
- AWS Bedrock AgentCore vs Google Agent Platform Code Execution
- AgentBay vs AWS Bedrock AgentCore
- AWS Bedrock AgentCore vs DigitalOcean Harness Runtime
- Azure Container Apps dynamic sessions vs Google Agent Platform Code Execution
- Azure Container Apps dynamic sessions vs OpenAI Code Interpreter & Hosted Shell
Frequently asked questions
Is AWS Bedrock AgentCore or Azure Container Apps dynamic sessions better for AI agents?
What is the difference between AWS Bedrock AgentCore and Azure Container Apps dynamic sessions?
Which is open source, AWS Bedrock AgentCore or Azure Container Apps dynamic sessions?
How do AWS Bedrock AgentCore and Azure Container Apps dynamic sessions isolate code?
How does AWS Bedrock AgentCore pricing compare with Azure Container Apps dynamic sessions?
Can you self-host AWS Bedrock AgentCore or Azure Container Apps dynamic sessions?
How long can sessions run on AWS Bedrock AgentCore and Azure Container Apps dynamic sessions?
Sources
- docs.aws.amazon.com/bedrock-agentcore/latest/devguide/code-interpreter-tool.html
- docs.aws.amazon.com/bedrock-agentcore/latest/devguide/code-interpreter-resource-session-management.html
- docs.aws.amazon.com/bedrock-agentcore/latest/devguide/runtime-how-it-works.html
- aws.amazon.com/bedrock/agentcore/pricing/
- 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/
Check before you rely on it. Products change quickly, and this page reflects public documentation as of November 14, 2026. Confirm anything that matters in the provider’s own documentation.
Cite this page
Agent Sandboxes. (2026). AWS Bedrock AgentCore vs Azure Container Apps dynamic sessions. agentsandboxes.org. Last reviewed November 14, 2026. https://agentsandboxes.org/compare/aws-agentcore-vs-azure-dynamic-sessions/