# Autoscaling is turned on to min replicas as 0. Yet costing money? **URL:** \ **Category:** Inference Endpoints on the Hub\ **Created:** [August 11, 2023, 10:00am UTC](https://discuss.huggingface.co/t/autoscaling-is-turned-on-to-min-replicas-as-0-yet-costing-money/50407 "2023-08-11T10:00:23Z")\ **Posts on this page:** 3\ **Page:** 1
**Author:** ![Kishal](https://avatars.discourse-cdn.com/v4/letter/k/b19c9b/32.png) [@Kishal](https://discuss.huggingface.co/u/Kishal)\ **Post date:** [August 11, 2023, 10:00am UTC](https://discuss.huggingface.co/t/autoscaling-is-turned-on-to-min-replicas-as-0-yet-costing-money/50407/1 "2023-08-11T10:00:23Z")
I have turned on the inactivity after 15 mins. But still it was costing me money when there were no incoming traffic. ---
**Author:** ![amitrethem](https://avatars.discourse-cdn.com/v4/letter/a/b487fb/32.png) [@amitrethem](https://discuss.huggingface.co/u/amitrethem)\ **Post date:** [August 11, 2023, 11:17am UTC](https://discuss.huggingface.co/t/autoscaling-is-turned-on-to-min-replicas-as-0-yet-costing-money/50407/2 "2023-08-11T11:17:11Z")
Hello, Is there any way to raise request as a support defect one? As per HF documentations, we should not be charged if the inference endpoint is idle for more than 15 min. Is this not applicable for CPU and GPU based endpoint? Thanks ---
**Author:** ![michellehbn](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/michellehbn/32/58964_2.png) [@michellehbn](https://discuss.huggingface.co/u/michellehbn)\ **Post date:** [August 11, 2023, 4:54pm UTC](https://discuss.huggingface.co/t/autoscaling-is-turned-on-to-min-replicas-as-0-yet-costing-money/50407/4 "2023-08-11T16:54:06Z")
Hi @Kishal, Thanks for reaching out and sorry to hear about this issue. Could you please send us an email to: [api-enterprise@huggingface.co](mailto:api-enterprise@huggingface.co) ? We’ll need the name of the endpoint in question and any details if possible. We’ll take a look to see what happened. Thanks again!