# Query endpoint for LLM

**URL:** <https://discuss.huggingface.co/t/query-endpoint-for-llm/59001>\
**Category:** 🤗Transformers\
**Created:** [October 18, 2023, 3:14pm UTC](https://discuss.huggingface.co/t/query-endpoint-for-llm/59001 "2023-10-18T15:14:47Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![GinFreecss23](https://avatars.discourse-cdn.com/v4/letter/g/a87d85/32.png) [@GinFreecss23](https://discuss.huggingface.co/u/GinFreecss23)\
**Post date:** [October 18, 2023, 3:14pm UTC](https://discuss.huggingface.co/t/query-endpoint-for-llm/59001/1 "2023-10-18T15:14:47Z")

</div>

Hello,  
For a personal project Im trying to summarize news articles.  
I have locally launched and played with the following model = “facebook/bart-large-cnn” and it works great.  
However I wanted to know whether there was a free endpoint I could use for that model?  
Ideally I would send it requests, it’d run on HF servers and then send back the query answer.  
This is quite similar to what we can do with the OpenAI GPT api except the latter is pretty expensive.  
If not, can you point me towards a free endpoint?  
Thanks