# Are InferenceClient()'s down?
**URL:**
**Author:**  [@gtvracer](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fgtvracer)%5C
**Post date:** [July 2, 2025, 7:53am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fare-inferenceclient-s-down%2F161485%2F1 "2025-07-02T07:53:54Z")
For meta-llama and mistral text generation LLM using the InferenceClient(), I’m getting: Bad Request: The endpoint is paused, ask a maintainer to restart it
Is something not working at HF?
---
**Author:**  [@John6666](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FJohn6666)%5C
**Post date:** [July 2, 2025, 10:46am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fare-inferenceclient-s-down%2F161485%2F2 "2025-07-02T10:46:57Z")
Is it explicitly PAUSED? Maybe it’s under maintenance or something… @michellehbn @meganariley
---
**Author:**  [@michellehbn](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fmichellehbn)%5C
**Post date:** [July 2, 2025, 1:22pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fare-inferenceclient-s-down%2F161485%2F3 "2025-07-02T13:22:08Z")
Hi @gtvracer, Thanks for reaching out and for being PRO 🤗 On the model page, you can request provider support of that model if the model is not deployed and available for use through Inference Providers.
As an example, meta-llama/Llama-3.1-8B-Instruct is currently available using providers like Featherless AI, Nscale, SambaNova, Fireworks, Hyperbolic, etc. You can also deploy models with Inference Endpoints (dedicated): [Inference Endpoints](https://huggingface.co/docs/inference-endpoints/index)
To see which models are available to use with HF Inference, check out our filtered search here: [Models - Hugging Face](https://huggingface.co/models?inference_provider=hf-inference&sort=trending)
---
**Author:**  [@anakin87](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fanakin87)%5C
**Post date:** [July 2, 2025, 2:00pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fare-inferenceclient-s-down%2F161485%2F4 "2025-07-02T14:00:54Z")
Ok. Text generation models are no longer available through HF Inference API: [Models - Hugging Face](https://huggingface.co/models?pipeline_tag=text-generation&inference_provider=hf-inference&sort=downloads)
Is this intended?
---
**Author:**  [@szkumar](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fszkumar)%5C
**Post date:** [July 2, 2025, 2:48pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fare-inferenceclient-s-down%2F161485%2F5 "2025-07-02T14:48:30Z")
This would be a massive bummer haha
---
**Author:**  [@gtvracer](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fgtvracer)%5C
**Post date:** [July 2, 2025, 2:54pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fare-inferenceclient-s-down%2F161485%2F6 "2025-07-02T14:54:50Z")
Exception:504 Server Error: Gateway Time-out for url: [/static-proxy?url=https%3A%2F%2Fapi-inference.huggingface.co%2Fmodels%2Fmeta-llama%2FLlama-3.3-70B-Instruct%2Fv1%2Fchat%2Fcompletions%5D(https%3A%2F%2Fapi-inference.huggingface.co%2Fmodels%2Fmeta-llama%2FLlama-3.3-70B-Instruct%2Fv1%2Fchat%2Fcompletions)
---
**Author:**  [@John6666](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FJohn6666)%5C
**Post date:** [July 2, 2025, 3:04pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fare-inferenceclient-s-down%2F161485%2F7 "2025-07-02T15:04:27Z")
Currently, [it appears that _no_ text generation models have been deployed in HF-Inference](https://huggingface.co/models?pipeline_tag=text-generation&inference_provider=hf-inference). However, it seems that [some have been deployed in other Inference Providers](https://huggingface.co/models?pipeline_tag=text-generation&inference_provider=all)…
---
**Author:**  [@gtvracer](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fgtvracer)%5C
**Post date:** [July 2, 2025, 3:38pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fare-inferenceclient-s-down%2F161485%2F8 "2025-07-02T15:38:36Z")
How can HF suddenly withdraw support from InferenceClient’s that worked yesterday, going forward? Without warning or anything? Very unprofessional and very disappointing…
---
**Author:**  [@gtvracer](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fgtvracer)%5C
**Post date:** [July 3, 2025, 12:01am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fare-inferenceclient-s-down%2F161485%2F9 "2025-07-03T00:01:40Z")
Make sure you have your huggingface-hub updated to 0.33.2. It will know how to accept the provider parameter. I used “nebius” for meta-llama models and it worked.
---
**Author:**  [@gtvracer](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fgtvracer)%5C
**Post date:** [July 3, 2025, 12:43am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fare-inferenceclient-s-down%2F161485%2F10 "2025-07-03T00:43:00Z")
use: provider=“together” for mistralai models..
---
**Author:**  [@anakin87](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fanakin87)%5C
**Post date:** [July 3, 2025, 9:46am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fare-inferenceclient-s-down%2F161485%2F11 "2025-07-03T09:46:39Z")
[Almost official news from HF DevRel on Discord](https://discord.com/channels/879548962464493619/1389836118471606364/1390065704723546177)
> yes! these models were sunset as part of us closing down hugging.chat unfortunately
> however there’s quite a lot of models that you can use through our inference providers as a replacement