# Acces token dont work
**URL:**
**Author:**  [@Dooorus](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FDooorus)%5C
**Post date:** [January 5, 2025, 5:00pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Facces-token-dont-work%2F134346%2F1 "2025-01-05T17:00:18Z")
i can login using cmd like i always get that my token is wrong but i create 3 tokens 3 were wrong i tried everything can someone help?
---
**Author:**  [@John6666](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FJohn6666)%5C
**Post date:** [January 6, 2025, 1:12am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Facces-token-dont-work%2F134346%2F2 "2025-01-06T01:12:58Z")
The most common errors are listed below, but there are also other cases, such as when the network environment is unusual.
>
>
> \### Describe the bug
>
>
> So my issue is this error, I was working with same 'HF\_t…oken' having the write permission and I am working with Mistral Nemo 12B Instruct , the model was working well from last few days without any issue and today suddenly this error appears .
> This error appears to be persistant, i have refresh the token and also tried with other model too and also check the hugging face interface api server status as well, but the issue remains the same.
>
> \### \*\*Issue\*\*
> \*\*BadRequestError
> huggingface\_hub.utils.\_errors.BadRequestError: (Request ID: Mq1mDWKbogI0AleJS0HJM)\*\*
>
> \*\*Bad request:
> Authorization header is correct, but the token seems invalid\*\*
>
> This is my \`\`\`app.py\`\`\` file, and I have not modified or added any other files:
>
> \`\`\`
> from huggingface\_hub import InferenceClient
> from dotenv import load\_dotenv
>
> \# Load environment variables from .env file
> load\_dotenv()
>
> \# Authenticate with Hugging Face
> HFT = os.getenv('HF\_TOKEN')
> client = InferenceClient(model="mistralai/Mistral-Nemo-Instruct-2407", token=HFT)
>
> \#results
> response = ""
> for message in client.chat\_completion(
> messages=\[system\_role, user\_prompt\],
> max\_tokens=3000,
> stream=True,
> temperature=0.35,
> ):
> response += message.choices\[0\].delta.content
> \`\`\`
>
>
>
> \### Reproduction
>
> \_No response\_
>
> \### Logs
>
> \`\`\`shell
> Traceback (most recent call last):
> File "C:\\Users\\Admin\\Documents\\app\_30082024\\envo\\lib\\site-packages\\huggingface\_hub\\utils\\\_errors.py", line 304, in hf\_raise\_for\_status
> response.raise\_for\_status()
> File "C:\\Users\\Admin\\Documents\\app\_30082024\\envo\\lib\\site-packages\\requests\\models.py", line 1024, in raise\_for\_status
> raise HTTPError(http\_error\_msg, response=self)
> requests.exceptions.HTTPError: 400 Client Error: Bad Request for url: /static-proxy?url=https%3A%2F%2Fapi-inference.huggingface.co%2Fmodels%2Fmistralai%2FMistral-Nemo-Instruct-2407%2Fv1%2Fchat%2Fcompletions
>
> The above exception was the direct cause of the following exception:
>
> Traceback (most recent call last):
> File "C:\\Users\\Admin\\Documents\\app\_30082024\\envo\\lib\\site-packages\\flask\\app.py", line 1498, in \_\_call\_\_
> return self.wsgi\_app(environ, start\_response)
> File "C:\\Users\\Admin\\Documents\\app\_30082024\\envo\\lib\\site-packages\\flask\\app.py", line 1476, in wsgi\_app
> response = self.handle\_exception(e)
> File "C:\\Users\\Admin\\Documents\\app\_30082024\\envo\\lib\\site-packages\\flask\\app.py", line 1473, in wsgi\_app
> response = self.full\_dispatch\_request()
> File "C:\\Users\\Admin\\Documents\\app\_30082024\\envo\\lib\\site-packages\\flask\\app.py", line 882, in full\_dispatch\_request
> rv = self.handle\_user\_exception(e)
> File "C:\\Users\\Admin\\Documents\\\_app\_30082024\\envo\\lib\\site-packages\\flask\\app.py", line 880, in full\_dispatch\_request
> rv = self.dispatch\_request()
> File "C:\\Users\\Admin\\Documents\\app\_30082024\\envo\\lib\\site-packages\\flask\\app.py", line 865, in dispatch\_request
> return self.ensure\_sync(self.view\_functions\[rule.endpoint\])(\*\*view\_args) # type: ignore\[no-any-return\]
> File "C:\\Users\\Admin\\Documents\\app\_30082024\\app5.py", line 78, in process\_file
> per\_data = Model\_PersonalDetails\_Output(resume, client)
> File "C:\\Users\\Admin\\Documents\\app\_30082024\\utility\\llm\_generate.py", line 127, in Model\_PersonalDetails\_Output
> for message in client.chat\_completion(
> File "C:\\Users\\Admin\\Documents\\app\_30082024\\envo\\lib\\site-packages\\huggingface\_hub\\inference\\\_client.py", line 837, in chat\_completion
> data = self.post(
> File "C:\\Users\\Admin\\Documents\\app\_30082024\\envo\\lib\\site-packages\\huggingface\_hub\\inference\\\_client.py", line 304, in post
> hf\_raise\_for\_status(response)
> File "C:\\Users\\Admin\\Documents\\app\_30082024\\envo\\lib\\site-packages\\huggingface\_hub\\utils\\\_errors.py", line 358, in hf\_raise\_for\_status
> raise BadRequestError(message, response=response) from e
> huggingface\_hub.utils.\_errors.BadRequestError: (Request ID: Mq1mDWKbogI0AleJS0HJM)
>
> Bad request:
> Authorization header is correct, but the token seems invalid
> \`\`\`
>
>
> \### System info
>
> \`\`\`shell
> \- huggingface\_hub version: 0.24.6
> \- Platform: Windows-10-10.0.19045-SP0
> \- Python version: 3.10.10
> \- Running in iPython ?: No
> \- Running in notebook ?: No
> \- Running in Google Colab ?: No
> \- Token path ?: C:\\Users\\Admin\\.cache\\huggingface\\token
> \- Has saved token ?: True
> \- FastAI: N/A
> \- Tensorflow: N/A
> \- Torch: 2.4.0
> \- Jinja2: 3.1.4
> \- Graphviz: N/A
> \- keras: N/A
> \- Pydot: N/A
> \- Pillow: 10.4.0
> \- hf\_transfer: N/A
> \- gradio: N/A
> \- tensorboard: N/A
> \- numpy: 1.26.4
> \- pydantic: N/A
> \- aiohttp: N/A
> \- ENDPOINT: https://huggingface.co
> \- HF\_HUB\_CACHE: C:\\Users\\Admin\\.cache\\huggingface\\hub
> \- HF\_ASSETS\_CACHE: C:\\Users\\Admin\\.cache\\huggingface\\assets
> \- HF\_TOKEN\_PATH: C:\\Users\\Admin\\.cache\\huggingface\\token
> \- HF\_HUB\_OFFLINE: False
> \- HF\_HUB\_DISABLE\_TELEMETRY: False
> \- HF\_HUB\_DISABLE\_PROGRESS\_BARS: None
> \- HF\_HUB\_DISABLE\_SYMLINKS\_WARNING: False
> \- HF\_HUB\_DISABLE\_EXPERIMENTAL\_WARNING: False
> \- HF\_HUB\_DISABLE\_IMPLICIT\_TOKEN: False
> \- HF\_HUB\_ENABLE\_HF\_TRANSFER: False
> \- HF\_HUB\_ETAG\_TIMEOUT: 10
> \- HF\_HUB\_DOWNLOAD\_TIMEOUT: 10
> \`\`\`
---
**Author:**  [@Alanturner2](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FAlanturner2)%5C
**Post date:** [January 6, 2025, 1:31am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Facces-token-dont-work%2F134346%2F3 "2025-01-06T01:31:17Z")
You should enter the “Edit permission” of the access tokens and select the “Make calls to the serverless inference API” in “inference”.
---
**Author:**  [@ValdeJunior](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FValdeJunior)%5C
**Post date:** [January 6, 2025, 7:16am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Facces-token-dont-work%2F134346%2F4 "2025-01-06T07:16:32Z")
Follow these instructions!
1. Ensure correct token format
2. Verify Token Permissions
3. Check Token Expiration
4. Set the Token Correctly in CMD
5. Clear Cached Tokens
6. Ensure Correct Command or Environment
7. Check for Proxy or Network Issues
8. Generate New Token
9. Review Logs or Error Messages