# Misunderstanding about inference endpoint billing

**URL:** <https://discuss.huggingface.co/t/misunderstanding-about-inference-endpoint-billing/57428>\
**Category:** Beginners\
**Created:** [October 4, 2023, 7:39pm UTC](https://discuss.huggingface.co/t/misunderstanding-about-inference-endpoint-billing/57428 "2023-10-04T19:39:31Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![victochai](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/victochai/32/19839_2.png) [@victochai](https://discuss.huggingface.co/u/victochai)\
**Post date:** [October 4, 2023, 7:39pm UTC](https://discuss.huggingface.co/t/misunderstanding-about-inference-endpoint-billing/57428/1 "2023-10-04T19:39:32Z")

</div>

Hi everyone !

I managed to deploy a model and linked it to my infrastructure. During tests, the model has been inferred with only 2 images. Response time was about 10-15s each but I have been billed for 1 minute 40 and more (had to pause the endpoint).  
The documentation states exactly : "  
_Pay for **compute resources uptime by the minute** , billed monthly._

_As low as $0.06 per CPU core/hr and $0.6 per GPU/hr._  
"  
which led me to assume that as long as the endpoint is not being used, I am not being billed. Am I wrong or did I miss something ?  
Good evening 🙂

---

<div class="post-metadata">

**Author:** ![GoldenGen](https://avatars.discourse-cdn.com/v4/letter/g/f14d63/32.png) [@GoldenGen](https://discuss.huggingface.co/u/GoldenGen)\
**Post date:** [October 23, 2024, 10:26pm UTC](https://discuss.huggingface.co/t/misunderstanding-about-inference-endpoint-billing/57428/2 "2024-10-23T22:26:34Z")

</div>

Hello! Did you manage to figure anything out? Same thing happening to me.

---

<div class="post-metadata">

**Author:** ![langhoangal](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/langhoangal/32/40404_2.png) [@langhoangal](https://discuss.huggingface.co/u/langhoangal)\
**Post date:** [February 5, 2025, 12:36am UTC](https://discuss.huggingface.co/t/misunderstanding-about-inference-endpoint-billing/57428/3 "2025-02-05T00:36:20Z")

</div>

The same, After deployment, I tested with 9 request within few minutes. And later (after few hours) I saw the compute time is 46 minutes. I feel unsafe using this service.