# Custom model.generate() parameters for hosted models

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fcustom-model-generate-parameters-for-hosted-models%2F10598%3E%5C
**Category:** Beginners\
**Created:** [October 7, 2021, 5:06pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fcustom-model-generate-parameters-for-hosted-models%2F10598 "2021-10-07T17:06:08Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![denyslinkov](https://avatars.discourse-cdn.com/v4/letter/d/90ced4/32.png) [@denyslinkov](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fdenyslinkov)%5C
**Post date:** [October 7, 2021, 5:06pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fcustom-model-generate-parameters-for-hosted-models%2F10598%2F1 "2021-10-07T17:06:08Z")

</div>

Is it possible for a hosted model on huggingface to take in additional parameters via API?

For example in python I can do something like

`model.generate(**inputs,num_return_sequences=10,top_k=50,length_penalty=0.3)`

But in the REST API I only see the ability to pass the inputs in, any suggestions?