# Inference API stopped working

**URL:** <https://discuss.huggingface.co/t/inference-api-stopped-working/150492>\
**Category:** Inference Endpoints on the Hub\
**Created:** [April 15, 2025, 1:33am UTC](https://discuss.huggingface.co/t/inference-api-stopped-working/150492 "2025-04-15T01:33:40Z")\
**Posts on this page:** 1\
**Showing post:** 22

<div class="post-metadata">

**Author:** ![AtherionGG](https://avatars.discourse-cdn.com/v4/letter/a/f14d63/32.png) [@AtherionGG](https://discuss.huggingface.co/u/AtherionGG)\
**Post date:** [April 23, 2025, 11:46pm UTC](https://discuss.huggingface.co/t/inference-api-stopped-working/150492/22 "2025-04-23T23:46:09Z")

</div>

Mine stopped for a while too getting 503:  
“503 Server Error: Service Temporarily Unavailable for url: [https://router.huggingface.co/hf-inference/models/black-forest-labs/FLUX.1-schnell](https://router.huggingface.co/hf-inference/models/black-forest-labs/FLUX.1-schnell)”

I looked that you could set a provider.  
I changed the parameters to the following and it worked.

```auto
from huggingface_hub import InferenceClient

client = InferenceClient(
    provider="fal-ai",
    api_key="hf_xxxxxxxxxxxxxxxxxxxxxxxx",
)

```

Which you can find if you click `view code` on the model card.

Looks like maybe the router code is not functioning properly. I could only speculate but potential issue there.

---

_[View the full topic](https://discuss.huggingface.co/t/inference-api-stopped-working/150492)._