Azure OpenAI Guardrails

Use Portkey to enforce structured inputs, safe outputs, and usage policies across all Azure OpenAI requests. Configure verdict actions like async checks, request denial, and feedback logging, according to your enforcement needs.

Azure OpenAI Guardrails

Azure OpenAI brings the power of OpenAI’s models like GPT-4, GPT-4o, and Whisper to enterprise environments with enhanced security, compliance, and scalability. But production-grade usage still needs robust controls. With Portkey, you can apply customizable guardrails to every Azure OpenAI request, ensuring safety, compliance, and governance without changing your application code.

Azure OpenAI is commonly used for secure enterprise chatbots, document processing, summarization, code generation, and more. With full support for Azure’s API structure and private endpoints, Portkey lets you enforce guardrails, monitor usage, and route requests intelligently across all Azure OpenAI deployments.

With Portkey, you can:

• Protect your AI stack from security threats with built-in guardrails
• Route requests with precision and zero latency based on guardrail checks
• View guardrails verdicts, latency, and pass/fail status for every check in real time.
• Enforce org-wide AI safety policies across all your teams, workspaces and models.
• Integrate existing guardrail infrastructure through simple webhook calls
• Secure vector embedding requests

Portkey supports all Azure OpenAI models out of the box and can be deployed in hours, not weeks, making it the easiest way to bring enterprise-grade control to your AI stack.

World-Class Guardrail Partners

Integrate top guardrail platforms with Portkey to run your custom policies seamlessly — from content filtering and PII detection to moderation and compliance. Ensure every AI request is safe, auditable, and aligned with your enterprise standards.

Partner Guardrails

• Acuvity: Acuvity is a model-agnostic GenAI security solution. It is built to secure existing and future GenAI models, apps, services, tools, plugins, and more.
• Aporia: Aporia provides state-of-the-art Guardrails for any AI workload. With Aporia, you can set up powerful, multimodal AI Guardrails.
• Lasso Security: Lasso Security protects your GenAI apps from data leaks, prompt injections, and other potential risks, keeping your systems safe and secure.
• Mistral: Mistral moderation service helps detect and filter harmful content across multiple policy dimensions to secure your AI applications.
• Pangea: Pangea AI Guard helps analyze and redact text to prevent model manipulation and malicious content.
• Azure Guardrails: Microsoft Azure offers robust content moderation and PII redaction services that can now be seamlessly integrated with Portkey’s Guardrails ecosystem.
• AWS Bedrock Guardrail: AWS Bedrock provides a comprehensive solution for securing your LLM applications, including content filtering, PII detection, redaction, and more.
• Patronus AI: Patronus excels in industry-specific guardrails for RAG workflows.
• Pillar Security: Pillar Security is an all-in-one platform that empowers organizations to monitor, assess risks, and secure their AI activities.
• Prompt Security: Prompt Security detects and protects against prompt injection, sensitive data exposure, and other AI security threats.

How to add guardrails to Azure OpenAI with Portkey

Adding Portkey Guardrails in production is just a 4-step process:

1. Create Guardrail Checks
2. Create Guardrail Actions
3. Enable Guardrail through Configs
4. Attach the Config to a Request

Guardrail action settings

• Async (TRUE): Run guardrails in parallel to the request.
• Async (FALSE): Run guardrails before request or response.
• Deny Request (TRUE): Block the request or response if any guardrail fails.
• Deny Request (FALSE): Allow the request even if the guardrail fails.
• Send Feedback on Success/Failure: Attach metadata based on guardrail results.

Latest guides and resources

• Guardrails on the Gateway Framework
• Production Guardrails for AI Apps
• Types of AI Guardrails and When to Use Them

Frequently Asked Questions

• Do guardrails add latency to requests?
• Can I block a request if a guardrail fails?
• What happens if I don’t want to block, just observe?
• Are OpenAI Guardrails only for inputs?
• What’s the difference between basic and pro guardrails?

Safeguard your Azure OpenAI requests now.

Whether you're running production workloads or scaling across teams, Portkey’s guardrails give you control without compromise.