It seems likely that the best way to register model providers like Baseten or TogetherAI in Phoenix鈥攚hen they use the OpenAI-compatible API鈥攊s to configure them as custom OpenAI-compatible providers. You can do this by setting the `OPENAI_BASE_URL` environment variable (server-side) or by specifying the base URL in the prompt playground UI, and by using the provider's API key as the `OPENAI_API_KEY`. This allows you to use multiple OpenAI-compatible endpoints and track the model name in your experiments. However, Phoenix currently overloads the "OpenAI" provider for all OpenAI-compatible endpoints, so you cannot natively distinguish between different OpenAI-compatible providers in the UI or experiment metadata at the same time, though enhancements are being considered to support custom providers and better provider tracking in the future (<https://github.com/Arize-ai/phoenix/blob/main/docs/prompt-engineering/how-to-prompts/configure-ai-providers.md|configure-ai-providers.md>, <https://github.com/Arize-ai/phoenix/issues/7325|issue #7325>).
To track the model name, you can pass any string as the model name in the UI or API, and it will be recorded in the experiment metadata. Tracking the provider is less direct鈥攃urrently, the provider is inferred as "OpenAI" for all OpenAI-compatible endpoints, but future updates may allow explicit custom provider registration (<https://github.com/Arize-ai/phoenix/issues/7325|issue #7325>, <https://github.com/Arize-ai/phoenix/issues/5427|issue #5427>). Would you like more detail or code examples for setting this up?
Sources:
- <https://github.com/Arize-ai/phoenix/blob/main/docs/prompt-engineering/how-to-prompts/configure-ai-providers.md|Configure AI Providers>
- <https://github.com/Arize-ai/phoenix/issues/7325|issue #7325>
- <https://github.com/Arize-ai/phoenix/issues/5427|issue #5427>
