# How to pin a model on the Hub?

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-to-pin-a-model-on-the-hub%2F34823%3E%5C
**Category:** 🤗Hub\
**Created:** [March 27, 2023, 7:04pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-to-pin-a-model-on-the-hub%2F34823 "2023-03-27T19:04:27Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![jtlicardo](https://avatars.discourse-cdn.com/v4/letter/j/ac8455/32.png) [@jtlicardo](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fjtlicardo)%5C
**Post date:** [March 27, 2023, 7:04pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-to-pin-a-model-on-the-hub%2F34823%2F1 "2023-03-27T19:04:27Z")

</div>

I’ll quote the docs here: `Model pinning is only supported for existing customers.`

Is this referring to having a Pro account, or using the Inference Endpoints paid service ([Inference Endpoints - Hugging Face](https://huggingface.co/inference-endpoints))?

---

<div class="post-metadata">

**Author:** ![radames](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/radames/32/28246_2.png) [@radames](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fradames)%5C
**Post date:** [March 28, 2023, 4:51am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-to-pin-a-model-on-the-hub%2F34823%2F2 "2023-03-28T04:51:03Z")

</div>

hi @jtlicardo! As mentioned in the [documentation](https://huggingface.co/docs/api-inference/usage#pinned-models), model pinning is exclusively available for current API Inference customers. We advise new users looking for a production-ready solution to explore our [Inference Endpoints Service](https://huggingface.co/inference-endpoints).

> If you’re interested in having a model that you can [readily deploy for inference](https://ui.endpoints.huggingface.co/new), take a look at our [Inference Endpoints](https://huggingface.co/inference-endpoints) solution! It is a secure production environment with dedicated and autoscaling infrastructure, and you have the flexibility to choose between CPU and GPU resources.