# 404 Error When Calling the Hugging Face Inference API via Dify **URL:** \ **Category:** Inference Endpoints on the Hub\ **Created:** [May 31, 2025, 6:51pm UTC](https://discuss.huggingface.co/t/404-error-when-calling-the-hugging-face-inference-api-via-dify/157486 "2025-05-31T18:51:26Z")\ **Posts on this page:** 4\ **Page:** 1
**Author:** ![f62masa](https://avatars.discourse-cdn.com/v4/letter/f/3d9bf3/32.png) [@f62masa](https://discuss.huggingface.co/u/f62masa)\ **Post date:** [May 31, 2025, 6:51pm UTC](https://discuss.huggingface.co/t/404-error-when-calling-the-hugging-face-inference-api-via-dify/157486/1 "2025-05-31T18:51:26Z")
Dear Hugging Face Support Team, I hope you are doing well. We are integrating the **Dify** knowledge-base tool with the Hugging Face Inference API to generate embeddings (feature-extraction pipeline). We now consistently receive the following 404 error: ```auto 404 Client Error: Not Found for url: https://api-inference.huggingface.co/pipeline/feature-extraction/intfloat/multilingual-e5-large-instruct (Request ID: Root=1-683b4db9-1e980b4c755dcffd2fc32730; bdc8fc2e-733e-4d9b-afee-955f5c940bdb) ``` **Until about two weeks ago this model could be registered and used without any issues, but it suddenly started returning 404 errors.** Model page: [intfloat/multilingual-e5-large-instruct · Hugging Face](https://huggingface.co/intfloat/multilingual-e5-large-instruct) ### Steps to reproduce 1. In Dify, select **Hugging Face Inference API** as the embedding model. 2. Enter an access token **with only the `read` scope**. 3. Specify the model name **intfloat/multilingual-e5-large-instruct**. 4. Save the settings and run a test → the 404 error appears. ### What we have already checked - Although the token has only the `read` scope, another model (e.g., `sentence-transformers/all-MiniLM-L6-v2`) works fine through the same API. - The model page is accessible via the web interface. ### Questions 1. Has the feature-extraction endpoint for this model been disabled, or has the endpoint URL format changed? 2. If the endpoint has changed, could you share the current correct URL format? 3. Are there any other possible causes or misconfigurations we should investigate? Your guidance would be greatly appreciated. Thank you very much for your time and support. ---
**Author:** ![John6666](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/john6666/32/27664_2.png) [@John6666](https://discuss.huggingface.co/u/John6666)\ **Post date:** [June 1, 2025, 4:59am UTC](https://discuss.huggingface.co/t/404-error-when-calling-the-hugging-face-inference-api-via-dify/157486/2 "2025-06-01T04:59:44Z")
For feature-extraction: > **[sentence-transformers/all-MiniLM-L6-v2 · Updated feature-extraction API URL](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2/discussions/116)** > > Hello! ---
**Author:** ![indraw111](https://avatars.discourse-cdn.com/v4/letter/i/b5a626/32.png) [@indraw111](https://discuss.huggingface.co/u/indraw111)\ **Post date:** [June 2, 2025, 7:52am UTC](https://discuss.huggingface.co/t/404-error-when-calling-the-hugging-face-inference-api-via-dify/157486/3 "2025-06-02T07:52:01Z")
I’m encountering a 404 error when trying to access the chat completion endpoint for `google/gemma-2-27b-it`. Could you please confirm if this model’s API endpoint is still active or if there’s a new endpoint I should use? Here is the error message I get: bash SalinEdit ```auto 404 Client Error: Not Found for url: https://router.huggingface.co/google/gemma-2-27b-it/v1/chat/completions ``` Thanks for the help! ---
**Author:** ![John6666](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/john6666/32/27664_2.png) [@John6666](https://discuss.huggingface.co/u/John6666)\ **Post date:** [June 2, 2025, 10:51am UTC](https://discuss.huggingface.co/t/404-error-when-calling-the-hugging-face-inference-api-via-dify/157486/4 "2025-06-02T10:51:04Z")
> **[google/gemma-2-27b-it · Hugging Face](https://huggingface.co/google/gemma-2-27b-it)** > > We’re on a journey to advance and democratize artificial intelligence through open source and open science. seems not deployed. Try: > [@Inference API stopped working](https://discuss.huggingface.co/t/inference-api-stopped-working/150492/52): > > Hi @BehNas and @RichLivMyB4 What model are you trying to use with the HF Inference API? You can find all models supported by the HF Inference API provider here: [Models - Hugging Face](https://huggingface.co/models?inference_provider=hf-inference&sort=trending).