# 429 for Kokoro-82M model

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2F429-for-kokoro-82m-model%2F155806%3E%5C
**Category:** Intermediate\
**Created:** [May 18, 2025, 11:25pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2F429-for-kokoro-82m-model%2F155806 "2025-05-18T23:25:31Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![adave16](https://avatars.discourse-cdn.com/v4/letter/a/839c29/32.png) [@adave16](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fadave16)%5C
**Post date:** [May 18, 2025, 11:25pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2F429-for-kokoro-82m-model%2F155806%2F1 "2025-05-18T23:25:31Z")

</div>

I am running the Kokoro-82M model in a Google cloud function. The function gets executed between 5-10 times in a day, but I am still getting a 429 rate limit error:

```auto
huggingface_hub.errors.HfHubHTTPError: 429 Client Error: Too Many Requests for url: https://huggingface.co/hexgrad/Kokoro-82M/resolve/main/config.json

```

Getting rate limited for 10 requests daily seems unreasonable to me. I tried authenticating my session with a hugging face token hoping I would no longer get rate limited, but it didn’t help with the issue. Do folks have tips on how to proceed?

I am slightly suspicious this has to do with the fact that the model is executing in the GCP environment. When I execute the same code from my local machine, I can invoke the code dozens of times in a few minutes without running into any rate limit issues.

---

<div class="post-metadata">

**Author:** ![John6666](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/john6666/32/27664_2.png) [@John6666](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FJohn6666)%5C
**Post date:** [May 19, 2025, 12:31am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2F429-for-kokoro-82m-model%2F155806%2F2 "2025-05-19T00:31:19Z")

</div>

Maybe there’s a problem with the blacklist… @meganariley

> <https://github.com/huggingface/transformers/issues/21129>
>
> \### System Info
> 
> transformers==4.25.1
> 
> Code block:
> 
> from transformers import… AutoTokenizer, AutoModelForMaskedLM
> 
> tokenizer = AutoTokenizer.from\_pretrained("flax-community/roberta-base-thai")
> model = AutoModelForMaskedLM.from\_pretrained("flax-community/roberta-base-thai")
> 
> Error:
> 
> OSError: There was a specific connection error when trying to load flax-community/roberta-base-thai:
> 429 Client Error: Too Many Requests for url: https://huggingface.co/flax-community/roberta-base-thai/resolve/main/config.json
> 
> \### Who can help?
> 
> \_No response\_
> 
> \### Information
> 
> \- \[X\] The official example scripts
> \- \[\] My own modified scripts
> 
> \### Tasks
> 
> \- \[X\] An officially supported task in the \`examples\` folder (such as GLUE/SQuAD, ...)
> \- \[\] My own task or dataset (give details below)
> 
> \### Reproduction
> 
> Import package and run code. 
> 
> \### Expected behavior
> 
> No errors expected.

> [@requests.exceptions.HTTPError: 429 Client Error: Too Many Requests](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Frequests-exceptions-httperror-429-client-error-too-many-requests%2F126019)%3A
>
> Hi team. From yesterday, we have been seeing 429 errors when trying to access different models. One example: File “/usr/local/lib/python3.8/site-packages/requests/models.py”, line 1024, in raise\_for\_status raise HTTPError(http\_error\_msg, response=self) requests.exceptions.HTTPError: 429 Client Error: Too Many Requests for url: [https://huggingface.co/meta-llama/Meta-Llama-](https://huggingface.co/meta-llama/Meta-Llama-) 3-8B/resolve/main/config.json