Release Date: July 2025Feature Status: Production ReadyBreaking Changes: None

Feature Summary

HyperFlow now supports Azure OpenAI, providing enterprise-grade access to OpenAI models through Microsoft Azure.

This enables enhanced security, compliance, and regional deployment options for organizations with strict data governance requirements.

What's New

Azure OpenAI Integration

Full support for Azure-hosted OpenAI models including:

• Chat models: GPT-4o, GPT-4o-mini, GPT-3.5-turbo via Azure deployments
• Embedding models: text-embedding-3-large/small, ada-002
• Dual authentication: API key or Microsoft Entra ID (Azure AD)
• Enterprise features: Private endpoints, network isolation, SLAs

Key Differences

• Deployment-based: Use Azure deployment names instead of model names
• No model discovery: Manual deployment configuration required
• Enhanced security: Support for managed identities and RBAC

Configuration

1. Azure Setup

1. Create Azure OpenAI resource in Azure Portal
2. Create model deployments in Azure AI Studio
3. Note endpoint URL and deployment names

2. HyperFlow Configuration

Add appropriate secrets depending on authentication scheme selected for the deployment: