# How to get Accelerated Inference API for T5 models?

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-to-get-accelerated-inference-api-for-t5-models%2F11972%3E%5C
**Category:** 🤗Hub\
**Created:** [November 17, 2021, 2:29pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-to-get-accelerated-inference-api-for-t5-models%2F11972 "2021-11-17T14:29:09Z")\
**Posts on this page:** 1\
**Showing post:** 4

<div class="post-metadata">

**Author:** ![pierreguillou](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/pierreguillou/32/19626_2.png) [@pierreguillou](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fpierreguillou)%5C
**Post date:** [November 18, 2021, 12:15pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-to-get-accelerated-inference-api-for-t5-models%2F11972%2F4 "2021-11-18T12:15:36Z")

</div>

> [@Narsil](#):
>
> Do you have a customer plan ? Optimizations are not on for non customers, leading to you not seeing the proper header.

Hello @Narsil. If I understand well your answer, **both CPU and GPU Accelerated Inference API are for paid plan** (you call it “customer plan”, I’m right?) which are Pro Plan, Lab and Enterprise in the [HF pricing page](https://huggingface.co/pricing).

### Contributor plan | Try Accelerated Inference API: CPU, no?

However, this not what is written in this [HF pricing page](https://huggingface.co/pricing). As you can see in the screen shot below, **even a Contributor plan** (I’ve got one at [pierreguillou (Pierre Guillou)](https://huggingface.co/pierreguillou)) can **Try Accelerated Inference API: CPU**.

 ![hfprice2](https://us1.discourse-cdn.com/hellohellohello/original/2X/b/b8cf62298cf3a1af154ebf3f077f5eceb946219f.png)

As I did my first test with the T5 base model which is not optimized even in AWS SageMaker (check this [post](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-to-deploy-a-t5-model-to-aws-sagemaker-for-fast-inference%2F11992%2F4) from @philschmid), I did another test with [distilbert-base-uncased-distilled-squad](https://huggingface.co/distilbert-base-uncased-distilled-squad). And, as for the T5 base model, this distilbert one is not CPU Accelerated through the Inference API.

You can check my Colab notebook [HF\_Inference\_API.ipynb](https://colab.research.google.com/drive/12VmR3Eykr6gD9YwUx-ZnMO7ksMWAJeCf?usp=sharing)

### About the the expression “customer plan” or “API customer”

I think the HF team should edit the paragraph [Using CPU-Accelerated Inference (~10x speedup)](/static-proxy?url=https%3A%2F%2Fapi-inference.huggingface.co%2Fdocs%2Fpython%2Fhtml%2Fquicktour.html%23using-cpu-accelerated-inference-10x-speedup) with a clear definition (see screen shot below) and verify the [HF pricing page](https://huggingface.co/pricing), too.

 ![hfprice](https://us1.discourse-cdn.com/hellohellohello/original/2X/5/5e185d8d67bcf15710f5ed8ce94280e3c70636c9.png)

### Conclusion | Contributors on the HF model hub can not test CPU-Accelerated Inference API ☹

But after saying all that, **the reality is that we (the model contributors on the HF model hub) can not test CPU-Accelerated Inference API**. What a pity!

Note: I did not understand you last comment (see below the quote).

> Also keep in mind as mentioned in the docs, that for customers we’re usually able to go beyond the default depending on the load and requirements.

---

_[View the full topic](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-to-get-accelerated-inference-api-for-t5-models%2F11972)._
