Trying to upgrade gpt-4o model in azure maximum quota is assigned and I cannot update it

Hello,

Welcome to Microsoft Q&A,

This is unfortunately a known gotcha with the quota slider in the Azure AI Foundry UI when you change a deployment’s model version. sometimes it “snaps” to your entire remaining GPT-4o quota (e.g., ~29M TPM) and won’t let you drag it back down.

You could set TPM explicitly via API/CLI (bypasses the UI)

1 unit of capacity = 1,000 TPM. Use the 2023-05-01 management API.

REST:

curl -X PUT "https://management.azure.com/subscriptions/<subId>/resourceGroups/<rg>/providers/Microsoft.CognitiveServices/accounts/<aoaiResource>/deployments/<deploymentName>?api-version=2023-05-01" \
  -H "Authorization: Bearer $(az account get-access-token --query accessToken -o tsv)" \
  -H "Content-Type: application/json" \
  -d '{
    "sku": { "name": "Standard", "capacity": 10 },          // 10K TPM
    "properties": { "model": { "format": "OpenAI", "name": "gpt-4o", "version": "2024-11-20" } }
  }'

Azure CLI:

az cognitiveservices account deployment create \
  -g <rg> -n <aoaiResource> --deployment-name <deploymentName> \
  --model-name gpt-4o --model-version "2024-11-20" --model-format OpenAI \
  --sku-name Standard --sku-capacity 10   # 10K TPM

https://free.blessedness.top/en-us/azure/ai-foundry/openai/how-to/quota?tabs=rest

Please upvote and accept the answer if it helps!!