# LLM model endpoints data residency

**URL:** <https://forums.developer.nvidia.com/t/llm-model-endpoints-data-residency/299709>\
**Category:** NVIDIA Nemotron\
**Tags:** inception, nim\
**Created:** [July 12, 2024, 9:40pm UTC](https://forums.developer.nvidia.com/t/llm-model-endpoints-data-residency/299709 "2024-07-12T21:40:21Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![el18](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@el18](https://forums.developer.nvidia.com/u/el18)\
**Post date:** [July 12, 2024, 9:40pm UTC](https://forums.developer.nvidia.com/t/llm-model-endpoints-data-residency/299709/1 "2024-07-12T21:40:21Z")

</div>

I’m science director at a conversational AI company and we’re exploring whether we can use Nvidia’s NIM API [NVIDIA NIM | llama3-70b](https://build.nvidia.com/meta/llama3-70b) for some of our use-cases. We need to understand the data residency for the API calls that we’re making (e.g. if it’s EU, UK or USA) given we have clients in the UK and the USA. I’ve tried to look through the documentation but have struggled to find the cybersecurity and related privacy terms and conditions, could someone please help?