# Is there a way to make a tokenizer using tiktoken lib

**URL:** <https://community.openai.com/t/is-there-a-way-to-make-a-tokenizer-using-tiktoken-lib/950456>\
**Category:** API\
**Tags:** api\
**Created:** [September 21, 2024, 2:42pm UTC](https://community.openai.com/t/is-there-a-way-to-make-a-tokenizer-using-tiktoken-lib/950456 "2024-09-21T14:42:46Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![devpatel232408](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/devpatel232408/32/465191_2.png) [@devpatel232408](https://community.openai.com/u/devpatel232408)\
**Post date:** [September 21, 2024, 2:42pm UTC](https://community.openai.com/t/is-there-a-way-to-make-a-tokenizer-using-tiktoken-lib/950456/1 "2024-09-21T14:42:46Z")

</div>

Hello i am working on a project using Groq and i am using the `mixtral-8x7b-32768` model. So i wanted to count the tokens in the prompts before sending the requests to the model. I wanted to use tiktoken to help me in that, so i explored tiktoken and there was no suitable encoding to support my groq model. Is there a way i can make it support it or is there a better library for this