orcarouter/auto virtual model that selects an upstream provider per request, as well as specific provider models using a <provider>/<model> identifier.
By adding this integration, your data may be sent through OrcaRouter to the underlying model provider for certain actions within Arize AX (e.g., prompt playground) and your account may be billed for usage.
Add the Integration Using the Arize Skills
Add an OrcaRouter integration from your coding agent using the Arize Skills:Create a custom model integration named 'my-orcarouter' with my base URL https://api.orcarouter.ai/v1 and API key sk-orca-...
Add the Integration from Arize AX
Select Custom Model Endpoints from the Providers List
Fill Out Your Integration Details
OrcaRouter). Then set your base URL and an OrcaRouter API key from the OrcaRouter dashboard.
Enter the base URL:If you need to send any extra headers to every request, set these. You then need to define the available model deployments. Leave OpenAI default models off and add your OrcaRouter model identifiers as custom model names. Addhttps://api.orcarouter.ai/v1. Do not include endpoint paths like/chat/completionsas these are appended automatically.
orcarouter/auto to use the virtual routing model, or add specific provider models in <provider>/<model> format (e.g. openai/gpt-4.1, anthropic/claude-sonnet-4-6).
Advanced Settings
- Supports Function Calling - Turn this on to allow the integration to use function calling features. This is on by default.
- Authorized Orgs - Configure which organizations have access to this integration.
- Authorized Spaces - Configure which spaces have access to this integration.