Providers · Beta

Set hard limits around each Azure OpenAI deployment.

Connect one Azure OpenAI deployment. Keep its endpoint and key out of application code, then set a separate budget and rate limit for each workload.

Create a free workspace Try the no-card Test Lab

How the connection works

How Azure OpenAI works with the gateway

Keep the deployment behind one alias

Applications call the gateway's conventional Chat Completions endpoint with a workload key and model alias. The gateway supplies the Azure resource endpoint, deployment name, API version, and encrypted resource key.

Set limits below Azure quota

Azure allocates quota by subscription, region, model, and deployment type. Add a smaller dollar budget, request and token rates, and concurrency limit for each workload instead of giving every app the deployment's full allowance.

Check the resource without inference

The connection test reads the resource's current model catalog with the saved key and does not send a prompt. Then run a bounded smoke test against the exact deployment name and API version before production use.

Current shared controls

What every supported connection includes

Encrypted BYOK credentials that remain hidden after setup Stable model aliases and compatible route targets Organization and key budgets, rate limits, and concurrency limits Observe, Shadow, and Enforce modes with metadata-only evidence

Test the exact Azure resource, deployment name, API version, Chat Completions payload, and streaming behavior before production approval.

Client boundary

AIGHQ_BASE_URL=https://api.aigatewayhq.com/v1
AIGHQ_API_KEY=from-your-workspace
AIGHQ_MODEL=company-approved-fast

Applications keep a stable gateway URL and model alias for Azure OpenAI. Administrators can change the Azure resource, deployment name, and compatible fallback centrally.

Implemented boundary

Supported protocols

Choose Azure OpenAI and enter the Azure resource root, resource API key, and optional deployment API version. The connection test reads the current model catalog without generating a response. Finish by mapping a gateway alias to the Azure deployment name.

POST /v1/chat/completions through the Azure deployment API OpenAI-format streaming for chat completions GET /v1/models connection test Azure resource root and deployment-name mapping

Compatibility follows the provider's current published interface. Review the provider documentation before approving Azure OpenAI for production.