Configure Azure OpenAI with Crew Studio for enterprise LLM connections
Access Azure OpenAI Studio
Azure AI Services > select your deployment > open Azure OpenAI Studio
.Deployments
. If you don’t have one, create a deployment with your desired model.Target URI
and Key
on the right side of the page. Keep this page open, as you’ll need this information.
Configure CrewAI Enterprise Connection
CrewAI Enterprise > LLM Connections
. Name your LLM Connection, select Azure as the provider, and choose the same model you selected in Azure.AZURE_DEPLOYMENT_TARGET_URL
(using the Target URI). The URL should look like this: https://your-deployment.openai.azure.com/openai/deployments/gpt-4o/chat/completions?api-version=2024-08-01-previewAZURE_API_KEY
(using the Key).Add Connection
to save your LLM Connection.Set Default Configuration
CrewAI Enterprise > Settings > Defaults > Crew Studio LLM Settings
, set the new LLM Connection and model as defaults.Configure Network Access
Azure OpenAI > select your deployment
.Resource Management > Networking
.Allow access from all networks
is enabled. If this setting is restricted, CrewAI may be blocked from accessing your Azure OpenAI endpoint.