# Getting "502 Server Error: Bad Gateway for url: https://api-inference.huggingface.co/models/meta-llama/Llama-3.2-3B-Instruct" error **URL:** \ **Category:** 🤗Hub\ **Created:** [April 16, 2025, 3:31am UTC](https://discuss.huggingface.co/t/getting-502-server-error-bad-gateway-for-url-https-api-inference-huggingface-co-models-meta-llama-llama-3-2-3b-instruct-error/150740 "2025-04-16T03:31:28Z")\ **Posts on this page:** 9\ **Page:** 1
**Author:** ![sjain132](https://avatars.discourse-cdn.com/v4/letter/s/8c91f0/32.png) [@sjain132](https://discuss.huggingface.co/u/sjain132)\ **Post date:** [April 16, 2025, 3:31am UTC](https://discuss.huggingface.co/t/getting-502-server-error-bad-gateway-for-url-https-api-inference-huggingface-co-models-meta-llama-llama-3-2-3b-instruct-error/150740/1 "2025-04-16T03:31:28Z")
i am accessing llama3.2\_3b instruct model via huggingfacehub. while calling llm.invoke it hangs. Everything was working fine before yesterday ie 15.04.25. Is anyone else also facing this issue. When will this be resolved ---
**Author:** ![sjain132](https://avatars.discourse-cdn.com/v4/letter/s/8c91f0/32.png) [@sjain132](https://discuss.huggingface.co/u/sjain132)\ **Post date:** [April 16, 2025, 3:32am UTC](https://discuss.huggingface.co/t/getting-502-server-error-bad-gateway-for-url-https-api-inference-huggingface-co-models-meta-llama-llama-3-2-3b-instruct-error/150740/2 "2025-04-16T03:32:39Z")
After waiting for sometime an error comes up that says “502 Server Error: Bad Gateway for url: [https://api-inference.huggingface.co/models/meta-llama/Llama-3.2-3B-Instruct](https://api-inference.huggingface.co/models/meta-llama/Llama-3.2-3B-Instruct)” ---
**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 16, 2025, 7:15am UTC](https://discuss.huggingface.co/t/getting-502-server-error-bad-gateway-for-url-https-api-inference-huggingface-co-models-meta-llama-llama-3-2-3b-instruct-error/150740/3 "2025-04-16T07:15:10Z")
It seems to be in a state where it is not working. Only Hugging Face knows whether it can be fixed or not. [website@huggingface.co](mailto:website@huggingface.co) [meta-llama/Llama-3.2-3B-Instruct · Hugging Face](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct) > Inference Providers > The selected billing account doesn’t have any compatible Inference Provider enabled for this model. ---
**Author:** ![KrSrijan](https://avatars.discourse-cdn.com/v4/letter/k/f475e1/32.png) [@KrSrijan](https://discuss.huggingface.co/u/KrSrijan)\ **Post date:** [April 28, 2025, 6:26am UTC](https://discuss.huggingface.co/t/getting-502-server-error-bad-gateway-for-url-https-api-inference-huggingface-co-models-meta-llama-llama-3-2-3b-instruct-error/150740/4 "2025-04-28T06:26:02Z")
It’s not yet fixed, right? I am facing the same issue while accessing this model and the whisper-large-v3 model too! ---
**Author:** ![sjain132](https://avatars.discourse-cdn.com/v4/letter/s/8c91f0/32.png) [@sjain132](https://discuss.huggingface.co/u/sjain132)\ **Post date:** [April 28, 2025, 6:36am UTC](https://discuss.huggingface.co/t/getting-502-server-error-bad-gateway-for-url-https-api-inference-huggingface-co-models-meta-llama-llama-3-2-3b-instruct-error/150740/5 "2025-04-28T06:36:59Z")
No it’s not fixed yet. ---
**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 28, 2025, 6:58am UTC](https://discuss.huggingface.co/t/getting-502-server-error-bad-gateway-for-url-https-api-inference-huggingface-co-models-meta-llama-llama-3-2-3b-instruct-error/150740/6 "2025-04-28T06:58:18Z")
HF’s Inference API has recovered from a major outage, but Llama 3.2 and SmolLM2 have not been deployed since then. These models are used in the Agents Course, causing confusion among users. @michellehbn > [@500 Internal Error - We're working hard to fix this as soon as possible](https://discuss.huggingface.co/t/500-internal-error-were-working-hard-to-fix-this-as-soon-as-possible/150333/32): > > All should be starting to look better now hugs if that’s not the case, please let us know. And a big thanks to everyone for reporting and bearing with us, we appreciate it! ---
**Author:** ![KrSrijan](https://avatars.discourse-cdn.com/v4/letter/k/f475e1/32.png) [@KrSrijan](https://discuss.huggingface.co/u/KrSrijan)\ **Post date:** [April 28, 2025, 7:13am UTC](https://discuss.huggingface.co/t/getting-502-server-error-bad-gateway-for-url-https-api-inference-huggingface-co-models-meta-llama-llama-3-2-3b-instruct-error/150740/7 "2025-04-28T07:13:26Z")
This message is from 13 days ago that things should start looking better now! Yet, llama 3.2 3b is not yet deployed! It’s not an ETA, but still how long they may take to redeploy it! Also, do you have any idea what’s the case with openai/whisper-large-v3 ? even that’s giving me the same 502 bad gateway! ---
**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 28, 2025, 7:15am UTC](https://discuss.huggingface.co/t/getting-502-server-error-bad-gateway-for-url-https-api-inference-huggingface-co-models-meta-llama-llama-3-2-3b-instruct-error/150740/8 "2025-04-28T07:15:43Z")
> do you have any idea what’s the case with openai/whisper-large-v3 ? The operation seems to have changed. > [@Inference API error with Whisper, return\_timestamps parameter](https://discuss.huggingface.co/t/inference-api-error-with-whisper-return-timestamps-parameter/150043/13): > > Right now the problem was finally solved - it is working correctly on the HF website and with API request. However another change appears in API: no more Auto-detection of audio format, content-type needs to be explitely stated. Briefly in my case: previously I could pass the “application/octet-stream” type (raw bytes) and HF would auto detect it as OGG. But now it causes error “Content type “None” not supported.” . So the solution is to explitely state that it is “audio/ogg” content-type. I… ---
**Author:** ![KrSrijan](https://avatars.discourse-cdn.com/v4/letter/k/f475e1/32.png) [@KrSrijan](https://discuss.huggingface.co/u/KrSrijan)\ **Post date:** [April 28, 2025, 7:18am UTC](https://discuss.huggingface.co/t/getting-502-server-error-bad-gateway-for-url-https-api-inference-huggingface-co-models-meta-llama-llama-3-2-3b-instruct-error/150740/9 "2025-04-28T07:18:10Z")
Thanks! I’ll try!