# Deploy model on HF Space for production

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fdeploy-model-on-hf-space-for-production%2F15597%3E%5C
**Category:** Spaces\
**Created:** [March 11, 2022, 3:41am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fdeploy-model-on-hf-space-for-production%2F15597 "2022-03-11T03:41:26Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![dnth](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/dnth/32/17144_2.png) [@dnth](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fdnth)%5C
**Post date:** [March 11, 2022, 3:41am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fdeploy-model-on-hf-space-for-production%2F15597%2F1 "2022-03-11T03:41:26Z")

</div>

I have a model deployed on Space with Gradio. This makes the model extremely accessible with the exposed inference API.

However, is it recommended if I use the API for in production environment? What are the pros/cons compared to hosting the model on AWS, Azure or GCP? Any thoughts?