Hi everyone, I seem to be encountering a sudden issue with the Hugging Face Inference API. I was successfully using it for image-to-image tasks (specifically with models like stabilityai/stable-diffusion-xl-refiner-1.0), but it abruptly stopped working a short while ago. Now, regardless of which m…

Hi, I think I have the same problem. I’ve published a model Eddy872/zoove-t5 , and everything seems correctly configured: The repository is public I’ve added the proper metadata at the top of the README.md The model works perfectly with the pipeline() method in Python However, the Inference API s…

and still got a 404 I think almost all individual users are in that state right now… Or rather, even the models of well-known companies are showing a 404 error.

Same problem appears today for me with my personal text generation model. Originally, I used old (2.8.1) version of the @huggingface/inference JS package - “Error fetching from Hugging Face API: An error occurred while fetching the blob” while trying to send text input. Updated the package to the …

same for me when using whisper large v3 model using provider=“hf-inference” it wont work it

Anyone has a solution for this? I am presenting my final year project in 2 days and have a model hosted on HF and all of a sudden I can not use it anymore. I would greatly appreciate any help thank you!

Hmm… Is this a different problem from the previous one? @michellehbn

From Hugging Face Discord: Tom Aarsen Hello! I believe some of the inference endpoints currently have “Scale to zero” enabled temporarily, meaning they will go down when there’s no usage for a while. The first request will then be slow/fail, but subsequent ones will work. We’re going to remove …

As for my case of my private model, “Scale to zero” was always the case - yes, I needed to wait for 1-3 mins for the first response. But right now it is 404. The issue described in discord is different.

Hi everyone! Do you have any updates on the fixes for the bugs discussed in this thread?

Inference API stopped working

Inference Endpoints on the Hub

TOOTHED May 7, 2025, 1:24am 44

Whisper is working fine for me, but I use large-v3-turbo without any provider specified. However there were a lot of issues with it last month: Inference API error with Whisper, return_timestamps parameter

Topic		Replies	Views
HF Inference API last few minutes returns the same 404 exception to all models Inference Endpoints on the Hub	45	2764	June 25, 2025
But is there even a single model working here?! Models	4	523	May 10, 2025
Dumb Question: Seeing that my inference API links not working Beginners	1	200	July 10, 2025
Inference API time out? Site Feedback	2	1008	February 28, 2024
500 Internal Error - We're working hard to fix this as soon as possible 🤗Transformers	46	3478	February 1, 2026

Inference API stopped working

Related topics