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

### Answer Retell AI does support integrating with various LLM providers through its Custom LLM feature. When you set up a WebSocket server for a custom LLM, you have full control over which inference provider you use—including Cerebras, Fireworks, Together AI, or any other provider. [(1) ]() The documentation provides examples for Azure OpenAI, OpenAI, and OpenRouter, but explicitly states: "Feel free to modify it with all the customization you need, like using different LLM & provider." So the platform doesn't restrict you to specific inference providers—you can connect to any LLM backend you choose by implementing the WebSocket integration and pointing your code to your preferred provider's API. If you're looking for a pre-built, no-code integration with those specific providers (without setting up a custom LLM server) , that capability isn't documented in the available sources. You may want to submit this as a feature request or reach out to the team for clarification on their roadmap.

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