[ ABORT TO HUD ]
SEQ. 1
SEQ. 2
SEQ. 3
SEQ. 4
Serverless API Deployments
Pay-Per-Token Model Access
Serverless API deployments are the simplest way to use models. Microsoft hosts the infrastructure - you just call the endpoint.
Deployment Tiers
| Tier | Billing | Best For | Data Processing |
|---|---|---|---|
| Standard | Pay-per-token | Development, variable workloads | Global (any region) |
| Provisioned (PTU) | Reserved capacity | Production, predictable throughput | Specific region |
| Data Zone | Pay-per-token | EU/US data residency compliance | Within zone (EU or US) |
| Batch | 50% discount | Async bulk processing | Non-real-time |
Creating a Serverless Deployment
// Via Azure CLI: az cognitiveservices account deployment create \ --name my-foundry \ --resource-group my-rg \ --deployment-name gpt4o-deploy \ --model-name gpt-4o \ --model-version "2024-11-20" \ --sku-name "Standard" \ --sku-capacity 10
🎯 Pro Tip: Start with Standard tier for development (you only pay for what you use). When you know your production load, switch to Provisioned (PTU) for guaranteed throughput and predictable costs.
⌨ HANDS-ON LABDeploy a Model from the CLI
⭐ +200 XPDeploy a model onto your Foundry resource without touching the portal, then verify it's live.
1Create a model deployment with az cognitiveservices account deployment create (needs --model-name, --model-version and --model-format).
2List the deployments on your account to confirm it's live.
OBJECTIVE 1 / 2 — type "hint" if stuck
FOUNDRY VERIFICATION
QUERY 1 // 2
Which deployment tier offers a 50% cost discount for bulk processing?
Standard
Provisioned
Data Zone
Batch