Gateway Registration

This feature is available for select Enterprise customers only.

Overview

Gateway Registration connects your self-hosted AI Gateway to the Portkey Control Plane. Once registered, the Data Plane can pull promt templates, routing configs,integrations, API keys etc. The registration flow has three steps:

Register Gateway — provide a name, URL, and environment type
Workspace Provisioning — choose which workspaces can use this gateway
Save the deployment configuration — download and store the generated configuration for your deployment.

Step 1: Register Gateway

Navigate to Admin Settings → Gateway Registration and click Register New Gateway. Fill in the following fields:

Field	Description
Gateway Name	A human-readable label for this gateway (e.g., `dev-ateway`, `prod-gateway`).
Gateway Type	Select if it is Production or Non Production gateway deployment.

Step 2: Workspace Provisioning

Workspace Provisioning is available on the Hybrid Enterprise plan only.

Choose which workspaces in your organisation will have access to this gateway.

Workspace Access Options

Allow All Workspaces
Allow Specific Workspaces

All current and future workspaces in your organisation can route traffic through this gateway. No further configuration is needed.

Click Next to continue.

Step 3: Save the deployment configuration

Download the values.yaml configuration file generated for your deployment.

Save this configuration before leaving. It will not be accessible again after you navigate away from this screen. Use the Download values.yaml button to save a local copy.

Gateway Overview

After registration, you can manage your gateway from Admin Settings → Gateway Registration → [Gateway Name]. The overview page shows:

Status badge (active / inactive) — updated when you run Verify Connection.
Workspace Control tab — edit workspace access permissions after registration.
Last Sync — elapsed time since the most recent sync between the data plane and control plane.

Deployment Steps

For Helm chart deployment details, refer to the values.yaml reference.

Connect to the Gateway

Once your gateway is running and registered, verify it is reachable and routing requests correctly.

curl '<GATEWAY_BASE_URL>/v1/chat/completions' \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer <OPENAI_API_KEY>" \
  -H "x-portkey-provider: openai" \
  -H "x-portkey-api-key: <PORTKEY_API_KEY>" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [{"role": "user", "content": "What is a fractal?"}]
  }'

Replace the following before running:

Placeholder	Value
`GATEWAY_BASE_URL`	The DNS record pointing to your deployed gateway
`OPENAI_API_KEY`	Your OpenAI API key
`PORTKEY_API_KEY`	Your Portkey API key

Introduction

Product

Self-Hosting

Support

Overview

Step 1: Register Gateway

Step 2: Workspace Provisioning

Workspace Access Options

Step 3: Save the deployment configuration

Gateway Overview

Deployment Steps

Connect to the Gateway

Portkey is now PRISMA AIRS AI Gateway. See it in action.

​Overview

​Step 1: Register Gateway

​Step 2: Workspace Provisioning

​Workspace Access Options

​Step 3: Save the deployment configuration

​Gateway Overview

​Deployment Steps

​Connect to the Gateway

Portkey is now PRISMA AIRS AI Gateway. See it in action.

Overview

Step 1: Register Gateway

Step 2: Workspace Provisioning

Workspace Access Options

Step 3: Save the deployment configuration

Gateway Overview

Deployment Steps

Connect to the Gateway