Install#
Setup#
Add your OrcaRouter API key as an environment variable:
Connect your application to Phoenix with the register function:
Run OrcaRouter#
orcarouter/auto selects an upstream provider per request. You can also target a specific provider model using <provider>/<model> format (e.g. openai/gpt-4.1-mini, anthropic/claude-haiku-4-5). To test without a funded account, use a free model such as deepseek/deepseek-v4-flash-free.
Observe#
Now that you have tracing set up, all invocations of the OpenAI client pointed at OrcaRouter will be streamed to your running Phoenix for observability and evaluation.
What Gets Traced#
All OrcaRouter model calls are automatically traced and include:
- Request/response data and timing
- Model name — the resolved upstream model name (e.g.
deepseek-v4-flash-202505), not the virtualorcarouter/autoidentifier - Token usage and cost data
- Error handling and debugging information
Common Issues#
- API Key: Use your OrcaRouter API key (
sk-orca-...), not an OpenAI key - Model Names: Use
orcarouter/autofor adaptive routing, or<provider>/<model>for a specific upstream. See OrcaRouter’s documentation for available models - Insufficient balance:
orcarouter/autoroutes to paid upstream models and requires a funded OrcaRouter wallet. Usedeepseek/deepseek-v4-flash-freeto test without balance - Base URL: Ensure you’re using
https://api.orcarouter.ai/v1as the base URL

