# Inference API down? **URL:** \ **Category:** Beginners\ **Created:** [June 3, 2024, 7:41am UTC](https://discuss.huggingface.co/t/inference-api-down/89988 "2024-06-03T07:41:25Z")\ **Posts on this page:** 13\ **Page:** 1
**Author:** ![LoGic142](https://avatars.discourse-cdn.com/v4/letter/l/e495f1/32.png) [@LoGic142](https://discuss.huggingface.co/u/LoGic142)\ **Post date:** [June 3, 2024, 7:41am UTC](https://discuss.huggingface.co/t/inference-api-down/89988/1 "2024-06-03T07:41:25Z")
While accessing this([speechbrain/lang-id-voxlingua107-ecapa · Hugging Face](https://huggingface.co/speechbrain/lang-id-voxlingua107-ecapa)) model via Inference API, I am getting the following error - (MaxRetryError(‘HTTPSConnectionPool(host='huggingface.co', port=443): Max retries exceeded with url: /api/models/speechbrain/lang-id-voxlingua107-ecapa (Caused by NameResolutionError(“\: Failed to resolve 'huggingface.co' ([Errno -3] Temporary failure in name resolution)”))’), ‘(Request ID: d978f641-257c-45c4-b95b-c51865344dfe)’) Can someone provide more insight into this error? And how do we solve it? ---
**Author:** ![RitchieP](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/ritchiep/32/24486_2.png) [@RitchieP](https://discuss.huggingface.co/u/RitchieP)\ **Post date:** [June 3, 2024, 8:28am UTC](https://discuss.huggingface.co/t/inference-api-down/89988/2 "2024-06-03T08:28:14Z")
I’m also facing issues with Inference API all of a sudden ---
**Author:** ![votepurchase](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/votepurchase/32/27724_2.png) [@votepurchase](https://discuss.huggingface.co/u/votepurchase)\ **Post date:** [June 3, 2024, 10:03am UTC](https://discuss.huggingface.co/t/inference-api-down/89988/3 "2024-06-03T10:03:26Z")
same here. ---
**Author:** ![jormeijer](https://avatars.discourse-cdn.com/v4/letter/j/4bbf92/32.png) [@jormeijer](https://discuss.huggingface.co/u/jormeijer)\ **Post date:** [June 3, 2024, 10:23am UTC](https://discuss.huggingface.co/t/inference-api-down/89988/4 "2024-06-03T10:23:18Z")
We are also facing issues with the Inference Endpoints ---
**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:** [June 3, 2024, 10:29am UTC](https://discuss.huggingface.co/t/inference-api-down/89988/5 "2024-06-03T10:29:23Z")
Same for hours.😓 ---
**Author:** ![nielsr](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/nielsr/32/39617_2.png) [@nielsr](https://discuss.huggingface.co/u/nielsr)\ **Post date:** [June 3, 2024, 11:06am UTC](https://discuss.huggingface.co/t/inference-api-down/89988/6 "2024-06-03T11:06:24Z")
Thanks for reporting, issue should be fixed now. ---
**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:** [June 3, 2024, 11:09am UTC](https://discuss.huggingface.co/t/inference-api-down/89988/7 "2024-06-03T11:09:12Z")
Fixed. Thank you.😊 ---
**Author:** ![pd-t](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/pd-t/32/27738_2.png) [@pd-t](https://discuss.huggingface.co/u/pd-t)\ **Post date:** [June 3, 2024, 2:33pm UTC](https://discuss.huggingface.co/t/inference-api-down/89988/8 "2024-06-03T14:33:44Z")
@nielsr Does fixed mean that it is now a 500 internal server error? I am currently facing this error with all 3 providers and multiple models. ---
**Author:** ![pd-t](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/pd-t/32/27738_2.png) [@pd-t](https://discuss.huggingface.co/u/pd-t)\ **Post date:** [June 4, 2024, 8:14am UTC](https://discuss.huggingface.co/t/inference-api-down/89988/9 "2024-06-04T08:14:38Z")
@nielsr I have debugged the problem further. The endpoints work as long as they are public. Both with and without scale to zero. If I secure the endpoint and request it without a token, a 401 is returned. So far so good. But if I pass a valid token, I get a 500. Do your integration tests work? ---
**Author:** ![pd-t](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/pd-t/32/27738_2.png) [@pd-t](https://discuss.huggingface.co/u/pd-t)\ **Post date:** [June 4, 2024, 11:43am UTC](https://discuss.huggingface.co/t/inference-api-down/89988/10 "2024-06-04T11:43:09Z")
@nielsr Ok. This is really weird now. For 2 hours I got 401 from the UI creating new endpoints and deleting existing ones (which costed me 12$) or even showing existing instances. Now the instance is visible again. And the Endpoint ist working with toking. So I got a last question: Are you fixing things in production without customer feedback and what kind of availability and stability can I expect from dedicated endpoints? Are they ready for production (\>99,9% availability)? ---
**Author:** ![nielsr](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/nielsr/32/39617_2.png) [@nielsr](https://discuss.huggingface.co/u/nielsr)\ **Post date:** [June 4, 2024, 6:10pm UTC](https://discuss.huggingface.co/t/inference-api-down/89988/11 "2024-06-04T18:10:44Z")
Hi, Yes they should be ready for production (they aim to make putting ML models in production easier with a few clicks). I appreciate your feedback, I’m not part of the Inference Endpoints team but will forward your feedback to them. ---
**Author:** ![rjurney](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/rjurney/32/26529_2.png) [@rjurney](https://discuss.huggingface.co/u/rjurney)\ **Post date:** [June 8, 2024, 12:12am UTC](https://discuss.huggingface.co/t/inference-api-down/89988/12 "2024-06-08T00:12:15Z")
The APIs for the evaluate library are also down for five days. ---
**Author:** ![rjurney](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/rjurney/32/26529_2.png) [@rjurney](https://discuss.huggingface.co/u/rjurney)\ **Post date:** [June 8, 2024, 12:12am UTC](https://discuss.huggingface.co/t/inference-api-down/89988/13 "2024-06-08T00:12:48Z")
Just go here and see the runtime errors: [evaluate-metric (Evaluate Metric)](https://huggingface.co/evaluate-metric)