Azure OpenAI Provider

Azure OpenAI Service provides OpenAI models through Microsoft Azure, with enterprise security, compliance, and regional data residency.

Prerequisites

Go to Azure AI Studio or the Azure portal
Create an Azure OpenAI resource
Navigate to Deployments and deploy a model (e.g., gpt-4o)
Note your:
- Resource name (e.g., my-company-openai)
- Deployment name (e.g., gpt-4o)
- API key (found under Keys and Endpoint)

Option 1: Environment variable

export AZURE_OPENAI_API_KEY="your-key-here"
vibecli --provider azure_openai

Option 2: Config file (~/.vibecli/config.toml)

[azure_openai]
enabled = true
api_key = "your-key-here"
api_url = "https://my-company-openai.openai.azure.com"
model = "gpt-4o"

The model field should match your Azure deployment name. The api_url is your resource endpoint.

Available models depend on what you have deployed in your Azure resource:

Model	Strengths	Best for
`gpt-4o`	Strongest reasoning	Complex coding, architecture
`gpt-4o-mini`	Fast and affordable	Daily coding tasks
`o3-mini`	Chain-of-thought reasoning	Hard debugging, logic

Default: gpt-4o

Enterprise compliance – data stays within your Azure tenant and chosen region
Private networking – use with VNETs and private endpoints
Existing Azure infrastructure – integrates with Azure AD, RBAC, and monitoring
Data residency – choose specific Azure regions for data locality requirements

vibecli --provider azure_openai -c "List 3 advantages of using Azure for AI workloads"