​ To learn more, see the sources I considered: [[1] Agent not waiting in between statements/questions despite pauses in prompt](https://discord.com/channels/1186424376300679209/1409973649221619812) [[2] Create Voice Agent](https://docs.retellai.com/api-references/create-agent) ​

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

### Answer This issue has been reported by other users recently, particularly with GPT-4.1. [(1) ]() Recommended solutions: 1. Structure your prompts with explicit "wait for user response" instructions :

1. Ask if there is anything else.
wait for user response

2. If yes, proceed with helping. If no, end the call.
wait for user response

2. Switch LLM models — If you're using GPT-4.1, try switching to GPT-4o or GPT-4o-mini, as this behavior has been reported to occur more frequently on GPT-4.1. 3. Adjust responsiveness settings — You can lower the

responsiveness

value (ranging from 0 to 1) to make the agent wait longer before responding. Lower values mean the agent is less responsive and waits more. [(2) ]() If the issue persists after trying these approaches, it may be worth reaching out to support with your organization ID for further investigation.

Thanks for the follow-up, @Yash. I'll get back to you soon.

​ To learn more, see the sources I considered: [[1] Platform Changelogs | Retell AI](https://www.retellai.com/changelog) [[2] Update Retell LLM](https://docs.retellai.com/api-references/update-retell-llm) ​

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

### Answer ### Answer The available sources don't provide a definitive "best to worst" ranking of all LLMs for Retell AI agents. However, here's what the documentation highlights: Key comparisons covered: [(1) ]() - OpenAI's GPT-4o — Ideal for customer service bots, virtual assistants, and interactive conversational tools requiring rapid and coherent responses. Supports real-time audio interactions through the Realtime API for low-latency, multimodal voice experiences. - Anthropic's Claude — Suited for public-facing voice AI in sensitive industries (mental health, financial advisory) where ethical considerations are paramount. Excels at understanding nuanced and complex instructions. Cost comparison (per minute) : - GPT-4o: $0.06 - GPT-4o-mini: $0.02 - Claude 3.5 Haiku: $0.02 - Claude 3.5 Sonnet: $0.06 Retell LLM — Retell's proprietary low-latency model is fine-tuned specifically for voice interactions, concise replies, and reliable function calls (< 800 ms end-to-end) . The "best" LLM depends on your priorities: - **Speed + cost balance**: GPT-4o or GPT-4o-mini - **Ethical/compliance-heavy use cases**: Claude models - **Voice-optimized latency**: Retell LLM For a deeper dive, check out: [Choosing the Best LLM for Your AI Voice Agents]()

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

​ To learn more, see the sources I considered: [[1] Choosing the Best LLM for Your AI Voice Agents | Retell AI](https://www.retellai.com/blog/choosing-the-best-llm-for-your-voice-ai-agents) ​