Bring Your Own Model to Foundry Agent Service Is Now Generally Available

2026-04-27 · Source: Microsoft Foundry Blog articles · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Cloud Computing & IT Infrastructure · Depth: Intermediate, short

Summary

Microsoft has announced the general availability of the Bring Your Own Model (BYOM) feature for its Foundry Agent Service, enabling enterprise teams to connect prompt agents to AI models hosted behind their own infrastructure. This includes Azure API Management or any third-party AI model gateway, allowing organizations to maintain control over model traffic for compliance, governance, and security. The BYOM feature supports routing agent requests through existing enterprise gateways, enforcing compliance and governance at the gateway layer, and utilizing any model compatible with the OpenAI Chat Completions API. Setup involves creating a model connection in the Foundry portal or programmatically via Azure CLI, then selecting the connected model when creating a prompt agent.

Key takeaway

For AI/ML Directors evaluating agent development platforms, Foundry Agent Service's BYOM feature significantly enhances flexibility and control. You can now build agents while ensuring all model interactions adhere to your organization's specific compliance, governance, and security policies by routing traffic through your existing enterprise gateways. This reduces the need for re-architecture and allows for seamless integration of diverse AI models.

Key insights

Foundry Agent Service's BYOM feature allows enterprises to integrate custom or third-party AI models via their own gateways.

Principles

• Maintain enterprise control over AI model traffic.
• Enforce existing compliance policies at the gateway.
• Support diverse AI model integrations.

Method

Configure a model connection in the Foundry portal (Operate > Admin) or via Azure CLI, specifying Azure API Management or "Other source," then select this connection when creating a prompt agent in Build > Agents.

In practice

• Route agent requests through Azure API Management.
• Apply existing security policies and rate limits.
• Connect any OpenAI Chat Completions API-compatible model.

Topics

• Bring Your Own Model
• Foundry Agent Service
• Azure API Management
• AI Model Gateways
• OpenAI Chat Completions API

Code references

• microsoft-foundry/foundry-samples

Best for: CTO, VP of Engineering/Data, Director of AI/ML, AI Engineer, MLOps Engineer, AI Architect

Related on AIssential

• Driving Stop-and-Go Business Processes to Closure with Foundry Hosted Agents — Foundry microVMs enable stateful AI agents for long-running business processes without external databases.
• AI Observability Starter Kit for Microsoft Foundry agents — Production-grade AI observability requires instrumented traces, automated quality and safety evaluations, and proactive alerting.
• Introducing Fireworks AI on Microsoft Foundry: Bringing high performance, low latency open model inference to Azure — Fireworks AI on Microsoft Foundry provides high-performance, enterprise-grade open model inference within Azure's unified AI platform.
• Microsoft's AI Futurist explains how he uses Copilot — and the real-world problems enterprises are solving with agents — Microsoft's agent strategy centers on providing a comprehensive platform for context, governance, identity, and secure data access, alongside diverse model choices.
• Mistral bets on ‘build-your-own AI’ as it takes on OpenAI, Anthropic in the enterprise — Mistral Forge is a new platform from the French AI startup Mistral, announced at Nvidia GTC, designed to enable enterprises and governments to build custom AI models trained from scratch on their prop…
• Azure AI Foundry: The Architect’s Blueprint for Building Enterprise AI at Scale — Azure AI Foundry is a platform of ten capabilities requiring deliberate architectural choices and external governance layers for enterprise AI.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Microsoft Foundry Blog articles.