The Retell Community is where innovators, call center leaders, and AI enthusiasts come together to share ideas, learn best practices, and explore the future of voice automation. Join to connect with peers, get early access to product updates, and collaborate on building human-like AI voice experiences that transform customer service.

Retell AI

<@1145576664366055464> what means Lower value (LLM temperature) yields better function call results?

Thanks for tagging me <@1362178263006581176>. I'll look through relevant sources and get back to you shortly.

### Answer
 

LLM temperature controls the randomness of the response [(1) ](<https://docs.retellai.com/api-references/get-retell-llm>) [(2) ](<https://docs.retellai.com/api-references/create-retell-llm>) [(3) ](<https://docs.retellai.com/api-references/list-retell-llms>) . The value ranges from 0 to 1 . A lower value means more deterministic output, while a higher value means more random output .

For function calling specifically, a lower temperature is recommended because it produces more consistent and predictable results . When the LLM needs to decide whether to call a function and what parameters to use, you want it to follow patterns reliably rather than introduce randomness that could lead to incorrect function calls or malformed parameters.

If the temperature is unset, the default value of 0 will apply .

​
To learn more, see the sources I considered:

[[1] Get Retell LLM](https://docs.retellai.com/api-references/get-retell-llm)
[[2] Create Retell LLM](https://docs.retellai.com/api-references/create-retell-llm)
[[3] List Retell LLMs](https://docs.retellai.com/api-references/list-retell-llms)
​

Feel free to tag <@1145576664366055464> with additional questions. I also appreciate feedback, it helps me improve.