Agent platform
Microsoft Azure
Managed Foundry agents with hosted execution, identity and tool integrations.
Own model keyPlan dependent
Published plans1
Last checked2026-10-23
Source statusSources reviewed
The essentials
What Microsoft Azure offers
Microsoft Azure is listed here as platform infrastructure for AI agent workloads. Managed Foundry agents with hosted execution, identity and tool integrations.
Pricing and deployment
East US retail consumption reference: $0.0994/vCPU-hour and $0.0118/GiB-hour, effective February 1, 2026. Region, contract discounts and connected services change the total.
Choosing this service
Evaluate the execution model, persistence requirements and connected services before choosing a deployment. A platform base fee or compute rate is not a complete model-usage budget.
Specifications below distinguish documented features from information not disclosed in the reviewed sources. Official links and the review date are provided for checking current terms.
Subscription & usage
Choose a plan. Check the scope.
These plans can serve different access methods. Model usage and resource charges may be additional.
Foundry hosted agents — East US metering
SubscriptionUsage-based
East US: $0.0994/vCPU-hour + $0.0118/GiB-hour; models and tools extra.
Included
Managed Foundry agents with hosted execution, identity and tool integrations.
Extra usage
East US hosted vCPU $0.0994/hour; hosted memory $0.0118/GiB-hour. Models, tools, storage and connected Azure services are additional.
Full conditions & limits
Pricing
- Pricing model
- Published
- Base subscription amount (not total cost)
- 0
- Currency
- USD
- Billing interval
- Usage only
- Subscription scope
- East US: $0.0994/vCPU-hour + $0.0118/GiB-hour; models and tools extra.
- Annual commitment / upfront payment
- East US retail consumption reference: $0.0994/vCPU-hour and $0.0118/GiB-hour, effective February 1, 2026. Region, contract discounts and connected services change the total.
- Setup fee
- Not disclosed in the reviewed official sources; confirm with the provider before purchase.
- Included usage
- Managed Foundry agents with hosted execution, identity and tool integrations.
- Overage rates
- East US hosted vCPU $0.0994/hour; hosted memory $0.0118/GiB-hour. Models, tools, storage and connected Azure services are additional.
- Model costs and BYOK conditions
- Model API usage and third-party tools are additional unless explicitly included by the selected offer.
- Free trial / credits / expiry
- Not disclosed in the reviewed official sources; confirm with the provider before purchase.
- Cancellation and refunds
- Not disclosed in the reviewed official sources; confirm with the provider before purchase.
- Tax treatment
- Not disclosed in the reviewed official sources; confirm with the provider before purchase.
Resources and limits
- CPU allocation and billing basis
- Configured per session; charged across active sessions.
- RAM
- Configured per session; charged across active sessions.
- GPU / VRAM
- Not disclosed in the reviewed official sources; confirm with the provider before purchase.
- Storage and persistence
- Persistent session filesystem via $HOME and /files; connected storage can add charges.
- Network egress
- Other Azure service and networking charges can apply
- Agent limit
- Not disclosed in the reviewed official sources; confirm with the provider before purchase.
- Concurrency
- Not disclosed in the reviewed official sources; confirm with the provider before purchase.
- Execution quota
- Not disclosed in the reviewed official sources; confirm with the provider before purchase.
- Maximum session / execution duration
- Idle timeout: 2–60 minutes, default 15; this is not a maximum active-request duration.
- Request rate limit
- Not disclosed in the reviewed official sources; confirm with the provider before purchase.
- Continuous execution / idle behavior
- Compute deprovisions at idle timeout and restores persisted state when a session resumes.
- Retention
- Session permanently deleted after 30 days of inactivity.
Plan controls
- Support
- Not disclosed in the reviewed official sources; confirm with the provider before purchase.
- Contractual SLA / availability target
- Not disclosed in the reviewed official sources; confirm with the provider before purchase.
- Plan-specific security and compliance
- Dedicated agent identity and VM isolation per session; private networking requires compatible project setup.
- Eligibility and restrictions
- Not disclosed in the reviewed official sources; confirm with the provider before purchase.
Evidence
- Official pricing source
- Official source
- Last checked (UTC date)
- 2026-10-23
- Price effective date, if explicitly published
- 2026-02-01
- Source interpretation and caveats
- Representative plan only, not the complete provider catalog. Prices are a dated reference; check official checkout for current regional terms.
Under the hood
Explore the specifications
Open a category for the details. Capabilities may depend on the selected plan.
Company & deploymentService model, use cases and limitations
Company and service
- Official website
- Official source
- Pricing page
- Official source
- Documentation
- Official source
- Hosting category
- Agent platform
- Deployment model
- Managed platform; customer deploys and configures the agent workload.
- Best suited to
- Managed Foundry agents with hosted execution, identity and tool integrations.
- Important limitations
- East US retail consumption reference: $0.0994/vCPU-hour and $0.0118/GiB-hour, effective February 1, 2026. Region, contract discounts and connected services change the total.
Compatibility & toolsModels, memory, MCP and integrations
Compatibility and tools
- Frameworks / SDKs
- Foundry Agent Service and supported agent frameworks.
- Languages / runtimes
- Not disclosed in the reviewed official sources; confirm with the provider before purchase.
- Model compatibility
- Model availability and credentials depend on the selected framework and model provider.
- Bring your own model API key
- Conditional / plan dependent
- Memory and sessions
- Session filesystem persists in $HOME and /files across idle/resume.
- MCP: client / server / hosting distinction
- Documented MCP and tool integrations; individual tool charges may apply.
- Schedules and triggers
- Not disclosed in the reviewed official sources; confirm with the provider before purchase.
- Browser execution
- Not disclosed in the reviewed official sources; confirm with the provider before purchase.
- Code execution / sandbox
- Execution facilities depend on the selected runtime and configured tools.
- App integrations / authentication
- Configure supported tools and provider credentials; third-party services can add charges.
Infrastructure & operationsRegions, scaling, networking and recovery
Infrastructure and operations
- Available deployment regions
- East US pricing reference; documented hosted-agent locations also include UAE North, West Europe, UK South, Japan East and Australia East. Consult the full official availability list.
- Scaling and idle behavior
- Session-based provisioning and scale-to-zero; CPU and RAM describe one session.
- Git / deployment workflow
- Container image in Azure Container Registry; versioned hosted agent deployment.
- Private network / static IP / egress controls
- Private networking options depend on service configuration and regional availability.
- Backups and recovery
- Not disclosed in the reviewed official sources; confirm with the provider before purchase.
- Logs, tracing, metrics and evaluations
- Application Insights and OpenTelemetry integration.
Security & supportIsolation, access controls and support
Security and support
- Isolation model
- Per-session VM-isolated sandbox with stateful resume.
- Secrets management
- Not disclosed in the reviewed official sources; confirm with the provider before purchase.
- SSO / roles / audit logging
- Microsoft Entra identity and Azure access controls; availability depends on deployment.
- Compliance evidence and scope
- Not disclosed in the reviewed official sources; confirm with the provider before purchase.
- Support channels
- Not disclosed in the reviewed official sources; confirm with the provider before purchase.
Evidence, not assumptions
Sources & verification
Reviewed 2026-10-23 UTC. “Not disclosed” means a value was not confirmed in these sources, not that a capability is unavailable.