Yes, Phoenix's prompt playground supports custom models via OpenAI-compatible endpoints like LiteLLM by setting `OPENAI_BASE_URL` and `OPENAI_API_KEY`. However, adding a custom model in Settings → Models only affects cost tracking and pricing—it does *not* make the model appear in the playground dropdown. The playground model dropdown is populated from a fixed list per provider, and currently does not dynamically include custom entries added in the UI or via regex patterns. You can still use your custom model by manually typing its name in the model field if the UI allows, or by passing it as a string if supported by your Phoenix version (<https://github.com/Arize-ai/phoenix/issues/5427|recent enhancement>).
If your Phoenix UI does not allow free-form model name entry, this is a known limitation. As a workaround, ensure your LiteLLM endpoint is reachable and that the model name exactly matches what LiteLLM expects. For debugging, check browser console logs for UI errors, and verify network requests to your LiteLLM endpoint. For more details, see <https://arize.com/docs/phoenix/prompt-engineering/how-to-prompts/configure-ai-providers|Phoenix docs on configuring AI providers> and <https://github.com/Arize-ai/phoenix/issues/5427|related GitHub issue>.
Would you like more detail on how to enable free-form model entry or on debugging LiteLLM integration?
Sources:
- <https://github.com/Arize-ai/phoenix/issues/5427|Enhancement: Allow for passing in a string as a model name for providers with fixed model lists>
- <https://arize.com/docs/phoenix/prompt-engineering/how-to-prompts/configure-ai-providers|Phoenix docs on configuring AI providers>
