401 Error: Invalid Credentials in Authorization Header (Flan-T5-Large Inference API)

Beginners
1

I have already done the following:

:white_check_mark: Created an API token on Hugging Face
:white_check_mark: Checked that my token has “Make calls to inference providers” permission
:white_check_mark: Tried regenerating a new token and replacing it in my script
:white_check_mark: Confirmed that my Hugging Face account is active and not restricted

This is the error message i get: I have already done the following:

This is the error message i get:

import requests

HF_TOKEN = “JOUW_NIEUWE_API_TOKEN”

API_URL = “https://api-inference.huggingface.co/models/google/flan-t5-large”

HEADERS = {“Authorization”: f"Bearer {HF_TOKEN}"}

response = requests.get(API_URL, headers=HEADERS)

print(“Response status code:”, response.status_code)

print(“Response JSON:”, response.json())

1 Like
2

It works for me.

Response status code: 200

Meybe try:

pip install -U huggingface_hub
3

Is it possible that it does work only with a pro membership?

1 Like
4

I don’t know… even models that don’t seem to be like that have the same behavior. Maybe the whole thing is buggy.

HF_TOKEN = "my token"
import requests
#API_URL = "https://api-inference.huggingface.co/models/google/flan-t5-large"
API_URL = "https://api-inference.huggingface.co/models/Qwen/Qwen2.5-3B"
HEADERS = {"Authorization": f"Bearer {HF_TOKEN}"}
response = requests.get(API_URL, headers=HEADERS)
print("Response status code:", response.status_code)
print("Response JSON:", response.json())
5

You mean the language model might be buggy

1 Like
6

No, not the model itself, but the system of the Hugging Face Inference API. It looks like it’s being renovated.

7

I did all of that but still don’t work if i message me telegram bot it only react on /start but the ai language model doesn’t work

1 Like
8

Hmm, I don’t know who is in charge.
website@huggingface.co