# 404 Errors When Using Inference API with Public Models
**URL:**
**Author:**  [@graceMkal](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FgraceMkal)%5C
**Post date:** [July 8, 2025, 8:08pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2F404-errors-when-using-inference-api-with-public-models%2F162263%2F1 "2025-07-08T20:08:21Z")
I’m trying to use the Inference API for the model [`meta-llama/Meta-Llama-3-70B-Instruct`](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct), and to test my setup, I’ve been making requests to public models like `gpt2`, `bert-base-uncased`, and `facebook/bart-large-mnli`. However, I consistently receive 404 errors.
Here’s what I’ve already tried:
- Generated new API tokens
- Switched networks and tested via mobile hotspot
- Used both `curl` and Python’s `requests` library
- Tried with multiple well-known public models
I desperately need help. I don’t understand why this is happening. My accounts are not flagged does anyone know if there’s a configuration issue preventing me from using the Inference API?
---
**Author:**  [@meganariley](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fmeganariley)%5C
**Post date:** [July 8, 2025, 9:32pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2F404-errors-when-using-inference-api-with-public-models%2F162263%2F2 "2025-07-08T21:32:02Z")
Hi @graceMkal This issue sounds similar: [404 to any API i tried - #6 by meganariley](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2F404-to-any-api-i-tried%2F161937%2F6).
[meta-llama/Meta-Llama-3-70B-Instruct · Hugging Face](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct) is available to use with many great inference providers like Together AI, Featherless AI, Hyperbolic, and Novita. Check out our documentation on Inference Providers for more info: [Inference Providers](https://huggingface.co/docs/inference-providers/en/index).
Another option is using this model with [Inference Endpoints](https://huggingface.co/docs/inference-endpoints/index) instead.
To see which models are available to use with HF Inference, check out our filtered search [here](https://huggingface.co/models?inference_provider=hf-inference&sort=trending).
You can also [subscribe to PRO](https://huggingface.co/subscribe/pro)! Perks include: 20x more inference usage, 8x ZeroGPU quota, 10x private storage capacity 🚀 Check out [PRO Account - Hugging Face](https://huggingface.co/pro) for details.
---
**Author:**  [@Amber14L](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FAmber14L)%5C
**Post date:** [July 9, 2025, 10:01am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2F404-errors-when-using-inference-api-with-public-models%2F162263%2F3 "2025-07-09T10:01:21Z")
> [@graceMkal](#):
>
> I’m trying to use the Inference API for the model [`meta-llama/Meta-Llama-3-70B-Instruct`](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct), and to test my setup, I’ve been making requests to public models like `gpt2`, `bert-base-uncased`, and `facebook/bart-large-mnli`. However, I consistently receive 404 errors.
>
> Here’s what I’ve already tried:
>
> - Generated new API tokens
> - Switched networks and tested via mobile hotspot
> - Used both `curl` and Python’s `requests` library
> - Tried with multiple well-known public models
>
> I desperately need help. I don’t understand why this is happening. My accounts are not flagged does anyone know if there’s a configuration issue preventing me from using the Inference API?
Wrong URL format → use: `/static-proxy?url=https%3A%2F%2Fapi-inference.huggingface.co%2Fmodels%2F%7Bmodel_id%7D%60
Missing or incorrect API token in headers
The model (like LLaMA 3) isn’t available via the public Inference API
Try with `gpt2` and make sure your token is set correctly.