# Responses from chat completion is truncated to 100 tokens

**URL:** <https://discuss.huggingface.co/t/responses-from-chat-completion-is-truncated-to-100-tokens/102892>\
**Category:** Beginners\
**Created:** [August 18, 2024, 7:28pm UTC](https://discuss.huggingface.co/t/responses-from-chat-completion-is-truncated-to-100-tokens/102892 "2024-08-18T19:28:53Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![PatrikKruse](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/patrikkruse/32/30631_2.png) [@PatrikKruse](https://discuss.huggingface.co/u/PatrikKruse)\
**Post date:** [August 18, 2024, 7:28pm UTC](https://discuss.huggingface.co/t/responses-from-chat-completion-is-truncated-to-100-tokens/102892/1 "2024-08-18T19:28:53Z")

</div>

I am using chat completion with Microsofts SemanticKernel and all my responses are truncated to 100 tokens. (No matter what I have max\_new\_tokens set to.)

I have two questions, can I raise the bar above 100 tokens and is there a way to programmatically detect that the response are truncated?