customize
Customize provides an interactive guided workflow for deploying Azure OpenAI models when you need precise control over configuration. Choose your model version, select from available SKUs (GlobalStandard, Standard, ProvisionedManaged, DataZoneStandard), set exact capacity, configure content filtering policies, and enable advanced features like dynamic quota or priority processing. Best for deployments with specific requirements; use the preset skill instead for quick deployment to the optimal region.
Customize guides you through deploying Azure OpenAI models with full control over version, SKU, capacity, and content filtering.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-07-26
Customize guides you through deploying Azure OpenAI models with full control over version, SKU, capacity, and content filtering. Customize provides an interactive guided workflow for deploying Azure OpenAI models when you need precise control over configuration. Choose your model version, select from available SKUs (GlobalStandard, Standard, ProvisionedManaged, DataZoneStandard), set exact capacity, configure content filtering policies, and enable advanced features like dynamic quota or priority processing. Best for deployments with specific requirements; use the preset skill instead for quick deployment to the optimal region.
Use it when
- Customize supports four SKU options for Azure OpenAI deployment: GlobalStandard, Standard, ProvisionedManaged, and DataZoneStandard.
- Yes, Customize supports setting up provisioned throughput unit (PTU) deployment with precise capacity allocation.
Verify before relying
Read SKILL.md below before installing (4 files). Open directory: indexed for reading, not audited.
Install
microsoft/azure-skills/customize · repository language: Python
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
How do I customize Azure OpenAI model deployment?
Customize guides you through an interactive workflow to deploy Azure OpenAI models with full control. You can select your model version, choose from available SKUs (GlobalStandard, Standard, ProvisionedManaged, DataZoneStandard), set exact capacity, configure content filtering policies, and enable advanced features like dynamic quota or priority processing. Use Customize when you need precise control over configuration; use the preset skill for quick deployment to the optimal region.
What SKU options does Customize support for deployment?
Customize supports four SKU options for Azure OpenAI deployment: GlobalStandard, Standard, ProvisionedManaged, and DataZoneStandard. Each SKU offers different capabilities and pricing models. GlobalStandard and Standard provide standard deployment options, ProvisionedManaged enables provisioned throughput unit (PTU) deployment with precise capacity allocation, and DataZoneStandard offers data residency features for specific compliance needs.
Can I set up provisioned throughput units deployment with Customize?
Yes, Customize supports setting up provisioned throughput unit (PTU) deployment with precise capacity allocation. Select the ProvisionedManaged SKU and specify your exact capacity requirements. This approach gives you dedicated throughput with predictable performance and cost, ideal for production workloads with consistent demand patterns.
How does Customize handle content filtering and RAI policies?
Customize lets you select and customize content filtering and Responsible AI (RAI) policies during model deployment. You can configure filtering policies to match your application's safety and compliance requirements, then apply these custom settings directly to your deployment. This ensures your Azure OpenAI model operates within your organization's governance framework.
What advanced deployment options are available in Customize?
Customize offers advanced deployment options including dynamic quota for flexible scaling and priority processing for expedited request handling. You can also configure spillover capabilities for failover scenarios. These features enable you to optimize performance and reliability based on your specific workload characteristics and business requirements.
When should I use Customize versus the preset deployment skill?
Use Customize when you need precise control over model version, SKU selection, capacity allocation, content filtering, and advanced features. Use the preset skill when you want quick deployment to the optimal region without detailed configuration. Customize is best for deployments with specific requirements; preset is ideal for standard deployments prioritizing speed.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
Customize Model Deployment
Interactive guided workflow for deploying Azure OpenAI models with full customization control over version, SKU, capacity, content filtering, and advanced options.
Quick Reference
| Property | Description |
|---|---|
| Flow | Interactive step-by-step guided deployment |
| Customization | Version, SKU, Capacity, RAI Policy, Advanced Options |
| SKU Support | GlobalStandard, Standard, ProvisionedManaged, DataZoneStandard |
| **Best |
(truncated - see the full file via the links below)
File tree — 4 files
skills/microsoft-foundry/models/deploy-model/customize/EXAMPLES.md
skills/microsoft-foundry/models/deploy-model/customize/SKILL.md
skills/microsoft-foundry/models/deploy-model/customize/references/customize-guides.md
skills/microsoft-foundry/models/deploy-model/customize/references/customize-workflow.md
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Deploy Azure OpenAI model with full control over version, SKU, capacity, and RAI policy”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
preset automates Azure OpenAI model deployment by scanning capacity across regions and routing to the best available option. It checks your current region first, then surfaces alternatives if needed, and handles project selection or creation as part of the workflow.
Azure OpenAI 2025 equips you with the latest models—GPT-5, GPT-4.1, o3, and o4-mini—plus Sora video generation and image tools. Get deployment commands, Python and .NET SDK recipes, SKU selection strategies, and patterns for on-your-data retrieval and vector search.
ARM Templates & Bicep provides Azure-native infrastructure-as-code using Bicep's cleaner syntax or traditional ARM JSON. Build modular deployments across resource groups, subscriptions, and management groups with What-If validation before applying changes.
Azure Kubernetes guides you through planning and provisioning AKS clusters for production, distinguishing critical Day-0 decisions (networking, API server access) from post-creation features. It covers SKU selection, pod IP models, security with Entra ID and policies, observability via Managed Prometheus, upgrade strategies, and cost optimization including Spot nodes.
Cloudflare Deploy guides you through deploying applications across Cloudflare's platform—from serverless functions and full-stack sites to databases and AI services. Navigate decision trees to find the right product, then follow detailed setup steps with authentication and troubleshooting support.
This skill creates project-specific design system rules that encode your team's component patterns, naming conventions, and architectural decisions. By analyzing your codebase and generating rules for your AI coding agent, it ensures consistent, high-quality code output when translating Figma designs. Rules are saved to the appropriate file format for Claude Code, Codex CLI, or Cursor.