# Model configuration in new inference endpoints page

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fmodel-configuration-in-new-inference-endpoints-page%2F68917%3E%5C
**Category:** Inference Endpoints on the Hub\
**Created:** [January 12, 2024, 11:12am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fmodel-configuration-in-new-inference-endpoints-page%2F68917 "2024-01-12T11:12:51Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![chsafouane](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/chsafouane/32/26450_2.png) [@chsafouane](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fchsafouane)%5C
**Post date:** [January 12, 2024, 11:12am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fmodel-configuration-in-new-inference-endpoints-page%2F68917%2F1 "2024-01-12T11:12:52Z")

</div>

I’m deploying my text-generation models using inference endpoints. It seems to me that the settings page has changed as of a day ago.

The old configuration looks like this:

 ![image](https://us1.discourse-cdn.com/hellohellohello/original/3X/6/3/6373037bfda57fb42d5dbdd04de91c5a057ff0b1.png)

The new configuration tab doesn’t allow for the setting of Max Input Length (per Query), Max Number of Tokens (per Query), Max Batch Prefill Tokens & Max Batch Total Tokens

How this can be set up in the new version of the page ?