### Answer To configure those settings via the API, you'll need to use the following parameters when creating or updating your agent: Max Call Duration (45 minutes = 2,700,000 ms) : - Use the

max_call_duration_ms

parameter [(1) ]() [(2) ]() - The minimum value allowed is 60,000 ms (1 min) , and maximum value allowed is 7,200,000 ms (2 hours) [(1) ]() Ring Duration (45 seconds = 45,000 ms) : - Use the

ring_duration_ms

parameter [(1) ]() [(2) ]() - Valid range is [5000, 90000] ms, so 45,000 ms is within the allowed range [(1) ]() Example payload for creating/updating an agent:

json
{
  "max_call_duration_ms": 2700000,
  "ring_duration_ms": 45000
}

Note:

ring_duration_ms

applies to outbound call ring time and call transfer ring time. [(1) ]() [(2) ]() If you're using the Conversation Flow builder in the dashboard, you can find call duration settings under "Configure Call Settings" in the global settings. [(4) ]()

​ To learn more, see the sources I considered: [[1] Create Voice Agent](https://docs.retellai.com/api-references/create-agent) [[2] Update Voice Agent](https://docs.retellai.com/api-references/update-agent) ​

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

@AI Evy can you give the list of llm models available now

### Answer Based on the available sources, I don't have a complete, current list of all LLM models available in Retell AI. What I can confirm from the documentation: Retell LLM Options (from changelog) : - GPT-3.5-turbo [(1) ]() - GPT-4-turbo Third-party models mentioned: - OpenAI's GPT-4o [(2) ]() - Anthropic's Claude (including Claude 3 Haiku, Claude 3.5 Haiku, Claude 3.5 Sonnet) - Google Gemini [(3) ]() The changelog notes "additional models coming soon" [(1) ]() , so the current list may have expanded beyond what's documented in these sources. For the most up-to-date list of available LLM models, I'd recommend: 1. Checking your Retell dashboard under the LLM configuration settings 2. Reviewing the [Configure LLM Options]() documentation directly [(4) ]() You can also use a Custom LLM via your own websocket if you need a model not natively supported. [(7) ]()

​ To learn more, see the sources I considered: [[1] New LLM Model Options, Modular Pricing, And More](https://www.retellai.com/changelog/new-llm-model-options-modular-pricing-and-more) [[2] 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) [[3] Large Language Model (LLM)](https://www.retellai.com/glossary/large-language-model-llm) [[4] Configure LLM Options](https://docs.retellai.com/build/llm-options) ​

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