--------------------------------------------------------------------------- HTTPError Traceback (most recent call last) File /Volumes/KODAK/folder_03/rag_system/venv/lib/python3.10/site-packages/huggingface_hub/utils/_errors.py:304, in hf_raise_for_status(response, endpoint_name) 303 try: → 304 response.raise_for_status() 305 except HTTPError as e: File /Volumes/KODAK/folder_03/rag_system/venv/lib/python3.10/site-packages/requests/models.py:1024, in Response.raise_for_status(self) 1023 if http_error_msg: → 1024 raise HTTPError(http_error_msg, response=self) HTTPError: 400 Client Error: Bad Request for url: https://api-inference.huggingface.co/models/openai/gpt-oss-120b/v1/chat/completions The above exception was the direct cause of the following exception: BadRequestError Traceback (most recent call last) Cell In[1], line 16 12 raise ValueError(“HF_API_TOKEN not found in .env file. Please check your .env.”) 14 client = InferenceClient(api_key=hf_token) —> 16 completion = client.chat.completions.create( 17 model=“openai/gpt-oss-120b”, 18 messages=[ 19 { 20 “role”: “user”, 21 “content”: “What is the advantage of AI? Can you list them properly?” 22 } 23 ], 24 ) 26 print(completion.choices[0].message.content) File /Volumes/KODAK/folder_03/rag_system/venv/lib/python3.10/site-packages/huggingface_hub/inference/_client.py:837, in InferenceClient.chat_completion(self, messages, model, stream, frequency_penalty, logit_bias, logprobs, max_tokens, n, presence_penalty, response_format, seed, stop, temperature, tool_choice, tool_prompt, tools, top_logprobs, top_p) 833 # `model` is sent in the payload. Not used by the server but can be useful for debugging/routing. 834 # If it’s a ID on the Hub => use it. Otherwise, we use a random string. 835 model_id = model if not is_url and model.count(“/”) == 1 else “tgi” → 837 data = self.post( 838 model=model_url, 839 json=dict( 840 model=model_id, 841 messages=messages, 842 frequency_penalty=frequency_penalty, 843 logit_bias=logit_bias, 844 logprobs=logprobs, 845 max_tokens=max_tokens, 846 n=n, 847 presence_penalty=presence_penalty, 848 response_format=response_format, 849 seed=seed, 850 stop=stop, 851 temperature=temperature, 852 tool_choice=tool_choice, 853 tool_prompt=tool_prompt, 854 tools=tools, 855 top_logprobs=top_logprobs, 856 top_p=top_p, 857 stream=stream, 858 ), 859 stream=stream, 860 ) 862 if stream: 863 return _stream_chat_completion_response(data) # type: ignore[arg-type] File /Volumes/KODAK/folder_03/rag_system/venv/lib/python3.10/site-packages/huggingface_hub/inference/_client.py:304, in InferenceClient.post(self, json, data, model, task, stream) 301 raise InferenceTimeoutError(f"Inference call timed out: {url}“) from error # type: ignore 303 try: → 304 hf_raise_for_status(response) 305 return response.iter_lines() if stream else response.content 306 except HTTPError as error: File /Volumes/KODAK/folder_03/rag_system/venv/lib/python3.10/site-packages/huggingface_hub/utils/_errors.py:358, in hf_raise_for_status(response, endpoint_name) 354 elif response.status_code == 400: 355 message = ( 356 f”\n\nBad request for {endpoint_name} endpoint:" if endpoint_name is not None else “\n\nBad request:” 357 ) → 358 raise BadRequestError(message, response=response) from e 360 elif response.status_code == 403: 361 message = ( 362 f"\n\n{response.status_code} Forbidden: {error_message}." 363 + f"\nCannot access content at: {response.url}." 364 + "\nIf you are trying to create or update content, " 365 + “make sure you have a token with the `write` role.” 366 ) BadRequestError: (Request ID: Root=1-68ac15f0-7240d458234f8f3e22614d08;3b898b74-1f51-4ebd-9943-d86ce6c8a03a) Bad request: Bad Request: The endpoint is paused, ask a maintainer to restart it
1 Like
Bad request: Bad Request: The endpoint is paused, ask a maintainer to restart it
Looks like it’s under maintenance.
Hi @Pasindu999 thanks for posting! This model is not supported using HF Inference, though it is available to use with one of many other Inference Providers: Together AI, Fireworks, Hyperbolix, Nebius AI, Novita, Cerebras, Groq, and Nscale.
If needed, you can also deploy with Inference Endpoints (dedicated): https://endpoints.huggingface.co.
To see which models are available to use with HF Inference, check out our filtered search here!
Hope this helps 
1 Like