Skip to main content

​
Guide

Configure Onyx to use models served through Portkey.
Portkey can route one endpoint to many vendors. Onyx lists the models that your Portkey gateway exposes after you enter a valid base URL and API key.
1

Set Up Your Portkey Access

Create a Portkey account or deploy a self-hosted Portkey gateway that the Onyx server can reach.Create a Portkey API Key in the Portkey dashboard. Note your gateway API Base URL if you self-host.
2

Navigate to Language Models

Open the Admin Panel from your user profile icon, then open Language Models.
3

Connect Portkey

Under Gateways & Routers, click Connect on the Portkey card.Select the API that Onyx must call on the gateway:
  • Chat Completions API (OpenAI-compatible, default)
  • Responses API (OpenAI-compatible)
  • Messages API (Anthropic-compatible)
Onyx fills in the matching Portkey API Base URL (https://api.portkey.ai/v1 for the OpenAI-compatible APIs, https://api.portkey.ai for the Messages API). Replace it with your own base URL if you self-host Portkey.Paste your Portkey API Key.Set up Portkey dialog with API Base URL, API Key, Display Name, and Models
4

Load Your Models

In the Models section, click Refresh models. Onyx lists the models that Portkey exposes.
5

Choose Visible Models

In the Models section, select the models that users can pick in chat. If a model is missing, open More Models or type its name and click Add Model.Limiting visible models helps when a provider publishes many models and versions of the same model.
6

Set Models Access

Under Models Access, choose All Users & Agents or Named Groups & Agents.With Named Groups & Agents, only Admins and the User Groups and Agents you name can use the models. Named groups need a Business plan or higher.
7

Connect

Click Connect. Onyx tests the provider with one of the selected models before it saves it.
See the Portkey documentation for account setup and billing details.