# Inference API budget, billing limit **URL:** \ **Category:** Site Feedback\ **Created:** [December 30, 2021, 11:43am UTC](https://discuss.huggingface.co/t/inference-api-budget-billing-limit/13239 "2021-12-30T11:43:15Z")\ **Posts on this page:** 20\ **Page:** 1
**Author:** ![louis030195](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/louis030195/32/3591_2.png) [@louis030195](https://discuss.huggingface.co/u/louis030195)\ **Post date:** [December 30, 2021, 11:43am UTC](https://discuss.huggingface.co/t/inference-api-budget-billing-limit/13239/1 "2021-12-30T11:43:15Z")
Hi, it would be nice to be able to limit inference API spending. I like the simple OpenAI system: soft and hard limit. Would be useful, especially when someone makes the mistake of an infinite loop calling the API 😛 ---
**Author:** ![GordonM](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/gordonm/32/32627_2.png) [@GordonM](https://discuss.huggingface.co/u/GordonM)\ **Post date:** [May 9, 2023, 4:30am UTC](https://discuss.huggingface.co/t/inference-api-budget-billing-limit/13239/2 "2023-05-09T04:30:52Z")
Second this - a hard limit to billing would be fantastic ---
**Author:** ![gwpl](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/gwpl/32/17901_2.png) [@gwpl](https://discuss.huggingface.co/u/gwpl)\ **Post date:** [May 13, 2023, 7:52am UTC](https://discuss.huggingface.co/t/inference-api-budget-billing-limit/13239/3 "2023-05-13T07:52:31Z")
Actually hard and soft limit, i.e. to get warnings after exceeding soft limit (so one can e.g. reconsider budget, change app usage or whatever e.g. to stay operational, or increase hard limit before it kicks in) , and ofc hard limit for safety reasons! ---
**Author:** ![sliss-open-ads](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/sliss-open-ads/32/16808_2.png) [@sliss-open-ads](https://discuss.huggingface.co/u/sliss-open-ads)\ **Post date:** [June 13, 2023, 5:53pm UTC](https://discuss.huggingface.co/t/inference-api-budget-billing-limit/13239/4 "2023-06-13T17:53:21Z")
Yes to both - I’d feel safer knowing I’d get en email notification if an improperly configured experiment starts blowing through our budget. ---
**Author:** ![DavidM555](https://avatars.discourse-cdn.com/v4/letter/d/c6cbf5/32.png) [@DavidM555](https://discuss.huggingface.co/u/DavidM555)\ **Post date:** [June 22, 2023, 3:05am UTC](https://discuss.huggingface.co/t/inference-api-budget-billing-limit/13239/5 "2023-06-22T03:05:12Z")
This feature is definitely overdue ---
**Author:** ![JPBianchi](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/jpbianchi/32/20440_2.png) [@JPBianchi](https://discuss.huggingface.co/u/JPBianchi)\ **Post date:** [October 18, 2023, 7:24pm UTC](https://discuss.huggingface.co/t/inference-api-budget-billing-limit/13239/6 "2023-10-18T19:24:39Z")
Think how easy it is to implement ‘if expense \> limit then stop & send email’… it’s not an oversight. ---
**Author:** ![Afterstone](https://avatars.discourse-cdn.com/v4/letter/a/e0b2c6/32.png) [@Afterstone](https://discuss.huggingface.co/u/Afterstone)\ **Post date:** [May 29, 2024, 1:32pm UTC](https://discuss.huggingface.co/t/inference-api-budget-billing-limit/13239/7 "2024-05-29T13:32:07Z")
Any news on this front? The lack of a billing limit makes me afraid to use HF Spaces as a private user. What if my apps go viral and I have to pay hundreds to thousands of dollars? ---
**Author:** ![dopaul](https://avatars.discourse-cdn.com/v4/letter/d/bcef8e/32.png) [@dopaul](https://discuss.huggingface.co/u/dopaul)\ **Post date:** [July 2, 2024, 10:07am UTC](https://discuss.huggingface.co/t/inference-api-budget-billing-limit/13239/8 "2024-07-02T10:07:16Z")
Yes, I agree. I want to build a public app and this is an essential feature. ---
**Author:** ![Seifudean](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/seifudean/32/40389_2.png) [@Seifudean](https://discuss.huggingface.co/u/Seifudean)\ **Post date:** [February 4, 2025, 6:23pm UTC](https://discuss.huggingface.co/t/inference-api-budget-billing-limit/13239/9 "2025-02-04T18:23:59Z")
HF can you please implement this already??? ---
**Author:** ![im93](https://avatars.discourse-cdn.com/v4/letter/i/eb8c5e/32.png) [@im93](https://discuss.huggingface.co/u/im93)\ **Post date:** [April 7, 2025, 11:55pm UTC](https://discuss.huggingface.co/t/inference-api-budget-billing-limit/13239/10 "2025-04-07T23:55:10Z")
April 2025 and still looking for this feature. ---
**Author:** ![FilippTrigub](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/filipptrigub/32/46511_2.png) [@FilippTrigub](https://discuss.huggingface.co/u/FilippTrigub)\ **Post date:** [April 28, 2025, 5:00pm UTC](https://discuss.huggingface.co/t/inference-api-budget-billing-limit/13239/11 "2025-04-28T17:00:45Z")
How is this not a thing… ---
**Author:** ![John6666](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/john6666/32/27664_2.png) [@John6666](https://discuss.huggingface.co/u/John6666)\ **Post date:** [April 29, 2025, 12:37am UTC](https://discuss.huggingface.co/t/inference-api-budget-billing-limit/13239/12 "2025-04-29T00:37:15Z")
Not limited to inference, but it seems like a $100 circuit breaker (variable) has been included by default for the past year or so… I only have a Pro subscription, so I haven’t actually tried it to see if it works… ---
**Author:** ![meganariley](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/meganariley/32/56966_2.png) [@meganariley](https://discuss.huggingface.co/u/meganariley)\ **Post date:** [April 29, 2025, 6:08pm UTC](https://discuss.huggingface.co/t/inference-api-budget-billing-limit/13239/13 "2025-04-29T18:08:26Z")
Hi @John6666, @FilippTrigub, and @im93! This feature now exists for Enterprise Hub organizations for Inference Providers billing! You can check out what setting a limit looks like in the screenshot here: [Pricing and Billing](https://huggingface.co/docs/inference-providers/en/pricing#organization-billing). For more info and to subscribe to Enterprise Hub, head here: [Enterprise Hub - Hugging Face](https://huggingface.co/enterprise). ---
**Author:** ![meganariley](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/meganariley/32/56966_2.png) [@meganariley](https://discuss.huggingface.co/u/meganariley)\ **Post date:** [May 5, 2025, 8:12pm UTC](https://discuss.huggingface.co/t/inference-api-budget-billing-limit/13239/14 "2025-05-05T20:12:00Z")
@John6666 The $100 is the threshold limit and please note it doesn’t act as a spending cap. More info here: [Billing](https://huggingface.co/docs/hub/billing#billing-thresholds--invoicing). ---
**Author:** ![John6666](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/john6666/32/27664_2.png) [@John6666](https://discuss.huggingface.co/u/John6666)\ **Post date:** [May 5, 2025, 9:30pm UTC](https://discuss.huggingface.co/t/inference-api-budget-billing-limit/13239/15 "2025-05-05T21:30:27Z")
Thank you! Is that so…😅 ---
**Author:** ![mark1138](https://avatars.discourse-cdn.com/v4/letter/m/b5e925/32.png) [@mark1138](https://discuss.huggingface.co/u/mark1138)\ **Post date:** [May 6, 2025, 1:49pm UTC](https://discuss.huggingface.co/t/inference-api-budget-billing-limit/13239/16 "2025-05-06T13:49:59Z")
So… In order to be able to set a hard limit I would have to subscribe to Enterprise which is $20/user with a required minimum of 10 users, so $200/month minimum. As a Pro user I have no way of limiting my spend? So if I have any kind of error in code, or make a mistake estimating the resource utilization I need, I could accidentally end up owing Hugging Face thousands, or tens of thousands of dollars? Am I understanding this correctly? ---
**Author:** ![meganariley](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/meganariley/32/56966_2.png) [@meganariley](https://discuss.huggingface.co/u/meganariley)\ **Post date:** [May 6, 2025, 4:51pm UTC](https://discuss.huggingface.co/t/inference-api-budget-billing-limit/13239/17 "2025-05-06T16:51:58Z")
Hi @mark1138 We also email friendly reminders on an account’s inference usage when billing hits certain milestones, like $10, $50, $100, etc. so you can be on the lookout and avoid any billing surprises in the future. 🙂 ---
**Author:** ![mark1138](https://avatars.discourse-cdn.com/v4/letter/m/b5e925/32.png) [@mark1138](https://discuss.huggingface.co/u/mark1138)\ **Post date:** [May 7, 2025, 9:44am UTC](https://discuss.huggingface.co/t/inference-api-budget-billing-limit/13239/18 "2025-05-07T09:44:58Z")
Hi @meganariley Thank you for the quick reply. The reminders certainly make the situation much better and would set my mind more at ease. If there are any internal discussions about adding hard limits for the Pro level, please add my vote. I love everything else about Hugging Face, so that would make it perfect 🙂 ---
**Author:** ![rishisriv-bh](https://avatars.discourse-cdn.com/v4/letter/r/df788c/32.png) [@rishisriv-bh](https://discuss.huggingface.co/u/rishisriv-bh)\ **Post date:** [June 4, 2025, 9:05pm UTC](https://discuss.huggingface.co/t/inference-api-budget-billing-limit/13239/19 "2025-06-04T21:05:52Z")
It would certainly make sense to add this cap. Pro users should not be punished for accidental code error. Could you please consider adding this spending cap feature for pro users? With all the talk of making AI accessible and open-source to everyone from Clem, this seems like a cheap shot on the open source developers who use hugging face. ---
**Author:** ![NMG-hf](https://avatars.discourse-cdn.com/v4/letter/n/5daacb/32.png) [@NMG-hf](https://discuss.huggingface.co/u/NMG-hf)\ **Post date:** [September 24, 2025, 6:29pm UTC](https://discuss.huggingface.co/t/inference-api-budget-billing-limit/13239/20 "2025-09-24T18:29:51Z")
It truly would be amazing to be able to set a hard-limit so I, personally, can have peace of mind and not worry about any accidental and catastrophic overage. I’m very hesitant to use the services and subscribe because of this. What would it take to convince HF to make the decision to introduce hard limits on Pro users? I think it’s the right thing to do. Can you help us understand why this isn’t being considered? I understand it’s available for Enterprise, but I can’t think of any negative outcome for anybody if people were able to set hard limits for any plan. [Next page](https://discuss.huggingface.co/t/inference-api-budget-billing-limit/13239.md?page=2)