# Inference turned off for this model?

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Finference-turned-off-for-this-model%2F50669%3E%5C
**Category:** Inference Endpoints on the Hub\
**Created:** [August 14, 2023, 5:25am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Finference-turned-off-for-this-model%2F50669 "2023-08-14T05:25:15Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![niron1](https://avatars.discourse-cdn.com/v4/letter/n/e480ec/32.png) [@niron1](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fniron1)%5C
**Post date:** [August 14, 2023, 5:25am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Finference-turned-off-for-this-model%2F50669%2F1 "2023-08-14T05:25:15Z")

</div>

I wanted to move some of the inference from my servers to HF, but I see that for most models that I use “Inference API has been turned off for this model.” this basically renders the HF inference api useless. am I missing something?  
I am willing to pay for GPU usage, but it’s not clear at all that after putting credit card details in place, this will work.

---

<div class="post-metadata">

**Author:** ![osanseviero](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/osanseviero/32/38738_2.png) [@osanseviero](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fosanseviero)%5C
**Post date:** [August 15, 2023, 9:42am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Finference-turned-off-for-this-model%2F50669%2F2 "2023-08-15T09:42:25Z")

</div>

Hi there! Which model are you using?

Note that the error message is for the free Inference API. For Inference Endpoints, you can use [🤗 Inference Endpoints](https://huggingface.co/docs/inference-endpoints/index), where you can load the model directly, specify your custom code, and pay for GPUs if that’s needed.