Guide
Configure Onyx to use models served through Bifrost.Onyx reads the models exposed by your Bifrost gateway at its
/v1/models endpoint.
Bifrost can expose models from multiple vendors behind a single endpoint.1
Set Up Your Bifrost Gateway
Make sure your Bifrost deployment is reachable from the Onyx server.You need the Bifrost API Base URL.If your Bifrost deployment requires authentication, also create a Bifrost API Key.
2
Navigate to Language Models
Open the Admin Panel from your user profile icon, then open Language Models.
3
Connect Bifrost
Under Gateways & Routers, click Connect on the Bifrost card.Select the API that Onyx must call on the gateway: Chat Completions API or Responses API.
Use Chat Completions API unless your gateway is set up for the OpenAI Responses API.Enter the API Base URL of your Bifrost gateway, including the API version (for example,
https://bifrost.example.com/v1).If your gateway requires authentication, paste your API Key.4
Load Your Models
In the Models section, click Refresh models.
Onyx lists the models that Bifrost exposes and uses the display names returned by the gateway when available.
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 gateway with one of the selected models before it saves the provider.