# Help using inference endpoint with Llama 3.1 405B Instruct **URL:** \ **Category:** Inference Endpoints on the Hub\ **Created:** [August 28, 2024, 2:19pm UTC](https://discuss.huggingface.co/t/help-using-inference-endpoint-with-llama-3-1-405b-instruct/104385 "2024-08-28T14:19:15Z")\ **Posts on this page:** 2\ **Page:** 1
**Author:** ![Around6827](https://avatars.discourse-cdn.com/v4/letter/a/919ad9/32.png) [@Around6827](https://discuss.huggingface.co/u/Around6827)\ **Post date:** [August 28, 2024, 2:19pm UTC](https://discuss.huggingface.co/t/help-using-inference-endpoint-with-llama-3-1-405b-instruct/104385/1 "2024-08-28T14:19:15Z")
Trying to run an example from: [https://huggingface.co/blog/llama31#inference-integrations](https://huggingface.co/blog/llama31#inference-integrations) Works on smaller models, but for 405B the client freezes (waited about 30 min). Did someone successfully queried this model? (I have a PRO account on HF) Update: now I got this Exception has occurred: HfHubHTTPError 429 Client Error: Too Many Requests for url: link) Rate limit reached. You reached PRO hourly usage limit. Use Inference Endpoints (dedicated) to scale your endpoint. requests.exceptions.HTTPError: 429 Client Error: Too Many Requests for url: [api-inference.huggingface.co/models/meta-llama/Meta-Llama-3.1-405B-Instruct-FP8/v1/chat/completions](http://api-inference.huggingface.co/models/meta-llama/Meta-Llama-3.1-405B-Instruct-FP8/v1/chat/completions) ---
**Author:** ![dan7cor](https://avatars.discourse-cdn.com/v4/letter/d/f08c70/32.png) [@dan7cor](https://discuss.huggingface.co/u/dan7cor)\ **Post date:** [August 30, 2024, 9:49pm UTC](https://discuss.huggingface.co/t/help-using-inference-endpoint-with-llama-3-1-405b-instruct/104385/2 "2024-08-30T21:49:36Z")
I have been trying to query the model, but I have been getting the same error: Error code: 503 - {‘error’: ‘Service Unavailable’}. The same code works fine for llama 3.1 8B and 70B. I have access to the models and also pro account on HF