# How to use AI models with custom tokenizers

**URL:** <https://meta.discourse.org/t/how-to-use-ai-models-with-custom-tokenizers/391238>\
**Category:** Support\
**Tags:** ai\
**Created:** [December 13, 2025, 10:41pm UTC](https://meta.discourse.org/t/how-to-use-ai-models-with-custom-tokenizers/391238 "2025-12-13T22:41:28Z")\
**Posts on this page:** 1\
**Showing post:** 2

<div class="post-metadata">

**Author:** ![Falco](https://sea3.discourse-cdn.com/meta/user_avatar/meta.discourse.org/falco/32/179432_2.png) [@Falco](https://meta.discourse.org/u/Falco)\
**Post date:** [December 14, 2025, 12:02am UTC](https://meta.discourse.org/t/how-to-use-ai-models-with-custom-tokenizers/391238/2 "2025-12-14T00:02:19Z")

</div>

TL;DR pick the closest tokenizer and set the maximum context to some thousands less to allow for the difference to not affect you.

---

_[View the full topic](https://meta.discourse.org/t/how-to-use-ai-models-with-custom-tokenizers/391238)._