Capacity Ms

Capacity Discovery

Finds available Azure OpenAI model capacity across all accessible regions and projects. Recommends the best deployment location based on capacity requirements.

Quick Reference

When to Use This Skill

• ✅ User asks "where can I deploy gpt-4o?"
• ✅ User specifies a capacity target: "find a region with 10K TPM for gpt-4o"
• ✅ User wants to compare availability: "which regions have gpt-4o available?"
• ✅ User got a quota error and needs to find an alternative location
• ✅ User asks "best region and project for deploying model X"

After discovery → hand off to preset or customize for actual deployment.

Scripts

Pre-built scripts handle the complex REST API calls and data processing. Use these instead of constructing commands manually.

Workflow

Phase 1: Validate Prerequisites

az account show --query "{Subscription:name, SubscriptionId:id}" --output table

Phase 2: Identify Model and Version

Extract model name from user prompt. If version is unknown, query available versions:

.\scripts\query_capacity.ps1 -ModelName <model-name>

./scripts/query_capacity.sh <model-name>

This lists available versions. Use the latest version unless user specifies otherwise.

Phase 3: Run Discovery

Run the full discovery script with model name, version, and minimum capacity target:

.\scripts\discover_and_rank.ps1 -ModelName <model-name> -ModelVersion <version> -MinCapacity <target>

./scripts/discover_and_rank.sh <model-name> <version> <min-capacity>

💡 The script automatically queries capacity across ALL regions, cross-references with the user's existing projects, and outputs a ranked table sorted by: meets target → project count → available capacity.

Phase 3.5: Validate Subscription Quota

After discovery identifies candidate regions, validate that the user's subscription actually has available quota in each region. Model capacity (from Phase 3) shows what the platform can support, but subscription quota limits what this specific user can deploy.

# For each candidate region from discovery results:
$usageData = az cognitiveservices usage list --location <region> --subscription $SUBSCRIPTION_ID -o json 2>$null | ConvertFrom-Json

# Check quota for each SKU the model supports
# Quota names follow pattern: OpenAI.<SKU>.<model-name>
$usageEntry = $usageData | Where-Object { $_.name.value -eq "OpenAI.<SKU>.<model-name>" }

if ($usageEntry) {
  $quotaAvailable = $usageEntry.limit - $usageEntry.currentValue
} else {
  $quotaAvailable = 0  # No quota allocated
}

# For each candidate region from discovery results:
usage_json=$(az cognitiveservices usage list --location <region> --subscription "$SUBSCRIPTION_ID" -o json 2>/dev/null)

# Extract quota for specific SKU+model
quota_available=$(echo "$usage_json" | jq -r --arg name "OpenAI.<SKU>.<model-name>" \
  '.[] | select(.name.value == $name) | .limit - .currentValue')

Annotate discovery results:

Add a "Quota Available" column to the ranked output from Phase 3:

Regions/SKUs where quotaAvailable = 0 should be marked with ❌ in the results. If no region has available quota, hand off to the quota skill for increase requests and troubleshooting.

Phase 4: Present Results and Hand Off

After the script outputs the ranked table (now annotated with quota info), present it to the user and ask:

1. 🚀 Quick deploy to top recommendation with defaults → route to preset
2. ⚙️ Custom deploy with version/SKU/capacity/RAI selection → route to customize
3. 📊 Check another model or capacity target → re-run Phase 2
4. ❌ Cancel

Phase 5: Confirm Project Before Deploying

Before handing off to preset or customize, always confirm the target project with the user. See the Project Selection rules in the parent router.

If the discovery table shows a sample project for the chosen region, suggest it as the default. Otherwise, query projects in that region and let the user pick.

Error Handling

Related Skills

• preset — Quick deployment after capacity discovery
• customize — Custom deployment after capacity discovery
• quota — For quota viewing, increase requests, and troubleshooting quota errors, defer to this skill instead of duplicating guidance