# Cachedtoken not working recently while using chatCompletion api

**URL:** <https://community.openai.com/t/cachedtoken-not-working-recently-while-using-chatcompletion-api/1077695>\
**Category:** API\
**Tags:** gpt-4, chatgpt\
**Created:** [January 2, 2025, 2:55am UTC](https://community.openai.com/t/cachedtoken-not-working-recently-while-using-chatcompletion-api/1077695 "2025-01-02T02:55:58Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![ajh3734](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/ajh3734/32/511739_2.png) [@ajh3734](https://community.openai.com/u/ajh3734)\
**Post date:** [January 2, 2025, 2:55am UTC](https://community.openai.com/t/cachedtoken-not-working-recently-while-using-chatcompletion-api/1077695/1 "2025-01-02T02:55:58Z")

</div>

CachedToken is not working recently (since Dec.20 2024)

Is there anyone having similar problem or knowing how to solve this problem?

[fyi]

- Prompt length is around 2000~2400 tokens
- Most of prompt is not changing
- Chaning part of prompt is after 1800 token length which means, first 0~1800 tokens are exactly same

 ![image](https://us1.discourse-cdn.com/openai1/original/4X/3/9/d/39d72f99f5d24fe8c86d2f0259baeb28a11800a8.png)

---

<div class="post-metadata">

**Author:** ![pcosta](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/pcosta/32/514129_2.png) [@pcosta](https://community.openai.com/u/pcosta)\
**Post date:** [January 2, 2025, 11:55am UTC](https://community.openai.com/t/cachedtoken-not-working-recently-while-using-chatcompletion-api/1077695/2 "2025-01-02T11:55:27Z")

</div>

I am experiencing the same issues.

A pipeline that used to cache most of its prompt tokens between calls is not caching them any longer. We first identified this issue on December 29th.