# Inference API for Tokenizers

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Finference-api-for-tokenizers%2F26255%3E%5C
**Category:** Beginners\
**Created:** [November 17, 2022, 4:59pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Finference-api-for-tokenizers%2F26255 "2022-11-17T16:59:18Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![cta2106](https://avatars.discourse-cdn.com/v4/letter/c/bbce88/32.png) [@cta2106](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fcta2106)%5C
**Post date:** [November 17, 2022, 4:59pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Finference-api-for-tokenizers%2F26255%2F1 "2022-11-17T16:59:18Z")

</div>

Hi everyone,

I’m trying to deploy my backend on Heroku and running into the 500 MB slug size limit because my code downloads two tokenizers from Huggingface.

Is there an API endpoint that I can ping to tokenize the same way you can do inference?

For reference, the two tokenizers are `BertTokenizerFast.from_pretrained('bert-base-uncased')` and `SentenceTransformer( 'multi-qa-MiniLM-L6-cos-v1' )`

Thanks!