# 401 - but my API key should be valid **URL:** \ **Category:** Beginners\ **Created:** [October 15, 2025, 9:43pm UTC](https://discuss.huggingface.co/t/401-but-my-api-key-should-be-valid/169191 "2025-10-15T21:43:24Z")\ **Posts on this page:** 6\ **Page:** 1
**Author:** ![Lejonhjarta](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/lejonhjarta/32/54859_2.png) [@Lejonhjarta](https://discuss.huggingface.co/u/Lejonhjarta)\ **Post date:** [October 15, 2025, 9:43pm UTC](https://discuss.huggingface.co/t/401-but-my-api-key-should-be-valid/169191/1 "2025-10-15T21:43:24Z")
I am completely new to Hugging Face. So I asked Grok to hold my hand while I entered. After a long discussion and many tries Grok kind of gave up and told me to ask here. I have this curl command (windows cmd format): > curl -v [https://api-inference.huggingface.co/models/microsoft/DialoGPT-medium](https://api-inference.huggingface.co/models/microsoft/DialoGPT-medium) ^ > -X POST ^ > -d ‘{“inputs”: “The goal of life is”}’ ^ > -H ‘Authorization: Bearer %KEY\_HF%’ ^ > -H ‘Content-Type: application/json’ ^ > -o temp.html 2\> curl\_debug.txt I am on a free plan. The API key is fresh and should be valid for READ. I get 401. Why? ---
**Author:** ![meganariley](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/meganariley/32/56966_2.png) [@meganariley](https://discuss.huggingface.co/u/meganariley)\ **Post date:** [October 15, 2025, 10:26pm UTC](https://discuss.huggingface.co/t/401-but-my-api-key-should-be-valid/169191/2 "2025-10-15T22:26:22Z")
Hi @Lejonhjarta welcome 👋 We have info on [authentication](https://huggingface.co/docs/inference-providers/en/index#authentication) here. Make sure you’re using a `fine-grained` token with `Make calls to Inference Providers` permissions enabled. Unfortunately, the model [microsoft/DialoGPT-medium · Hugging Face](https://huggingface.co/microsoft/DialoGPT-medium) isn’t deployed with any Inference Provider at this time. On the model page you can click ‘Ask for Provider Support’. Check out our [filtered list](https://huggingface.co/models?inference_provider=all&sort=trending) of 48k+ models deployed with at least one Inference Provider. You can also use DialoGPT-medium with [Inference Endpoints](https://huggingface.co/docs/inference-endpoints/index) instead. We have a guide [Send Your First API Call](https://huggingface.co/docs/inference-providers/en/guides/first-api-call) if you’d like a walkthrough, and make sure to [subscribe to PRO](https://huggingface.co/subscribe/pro?from=support) to unlock 20× included inference credits! Hope this helps! 🤗 ---
**Author:** ![Lejonhjarta](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/lejonhjarta/32/54859_2.png) [@Lejonhjarta](https://discuss.huggingface.co/u/Lejonhjarta)\ **Post date:** [October 15, 2025, 11:03pm UTC](https://discuss.huggingface.co/t/401-but-my-api-key-should-be-valid/169191/3 "2025-10-15T23:03:26Z")
Thanks. I created a new access token with permissions FINEGRAINED (where I checked “inference”). And I switched to the first model in that “filtered list”. set MODEL=zai-org/GLM-4.6 Unfortunately I still get 401. ---
**Author:** ![Lejonhjarta](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/lejonhjarta/32/54859_2.png) [@Lejonhjarta](https://discuss.huggingface.co/u/Lejonhjarta)\ **Post date:** [October 16, 2025, 2:10am UTC](https://discuss.huggingface.co/t/401-but-my-api-key-should-be-valid/169191/4 "2025-10-16T02:10:52Z")
I think I have to give up on Hugging Face. I have not find anything that works on the free tier. So I can not test. And unfortunately I have not find any info about how secure the payment system is. There does not seem to have been any evaluation of that? ---
**Author:** ![meganariley](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/meganariley/32/56966_2.png) [@meganariley](https://discuss.huggingface.co/u/meganariley)\ **Post date:** [October 16, 2025, 10:42pm UTC](https://discuss.huggingface.co/t/401-but-my-api-key-should-be-valid/169191/5 "2025-10-16T22:42:13Z")
Can you please double check that your code snippet looks like this: [zai-org/GLM-4.6 · Hugging Face](https://huggingface.co/zai-org/GLM-4.6?inference_api=true&inference_provider=auto&language=sh&client=curl)? (You can find this on the [model page](https://huggingface.co/zai-org/GLM-4.6) by clicking Deploy \> Inference Providers) Check out our guide here as well: [Inference Providers](https://huggingface.co/docs/inference-providers/index#http--curl) . ---
**Author:** ![thecupcutapk](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/thecupcutapk/32/55342_2.png) [@thecupcutapk](https://discuss.huggingface.co/u/thecupcutapk)\ **Post date:** [November 2, 2025, 4:11am UTC](https://discuss.huggingface.co/t/401-but-my-api-key-should-be-valid/169191/6 "2025-11-02T04:11:35Z")
informative!