### Answer No, Retell AI has not removed custom LLM functionality. The documentation still includes guides for integrating your own custom LLM with Retell AI. [(1) ]() [(2) ]() You can connect your custom LLM via a WebSocket endpoint that Retell initiates when starting a call. [(1) ]() The integration guide explains how to set up a WebSocket server and integrate with an LLM of your choice, including examples for Azure OpenAI and OpenAI. [(2) ]() The documentation does note that Retell's built-in agent frameworks (single prompt, conversation flow) provide more capabilities and built-in tool sets, and recommends using those if possible—only using custom LLM integration if you have specific compliance or use case requirements. [(1) ]() For step-by-step instructions, check out: - [Integrate LLM]() - [LLM WebSocket]() - [Integrate Function Calling]()

​ To learn more, see the sources I considered: [[1] LLM WebSocket](https://docs.retellai.com/api-references/llm-websocket) [[2] Integrate LLM](https://docs.retellai.com/integrate-llm/integrate-llm) ​

Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.