# Serverless Inference API Token Limits/Settings

**URL:** <https://discuss.huggingface.co/t/serverless-inference-api-token-limits-settings/127725>\
**Category:** Beginners\
**Created:** [November 25, 2024, 9:02pm UTC](https://discuss.huggingface.co/t/serverless-inference-api-token-limits-settings/127725 "2024-11-25T21:02:23Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![MisterAI](https://avatars.discourse-cdn.com/v4/letter/m/46a35a/32.png) [@MisterAI](https://discuss.huggingface.co/u/MisterAI)\
**Post date:** [November 25, 2024, 9:02pm UTC](https://discuss.huggingface.co/t/serverless-inference-api-token-limits-settings/127725/1 "2024-11-25T21:02:23Z")

</div>

Hi,

As written in Topic Title :  
My request :  
Where can i found information about the Token limits/Settings using Free Serverless Inference API ?

Context :  
Trying automation for testing purposes from [Make.com](http://Make.com) with HF\_Models the responses generated by the models are Incomplete/truncated  
Maybe there are some limits or Maybe there are some settings to do in  
Makemodule : HTTP : make an API Key AUTH Request  
NB : My knowledge is low

NB: Before opening the request I consulted the links below without finding an answer.  
[https://huggingface.co/docs/api-inference/rate-limits](https://huggingface.co/docs/api-inference/rate-limits)  
[https://discuss.huggingface.co/search?q=API%20limit%20token](https://discuss.huggingface.co/search?q=API%20limit%20token)

Any Help Welcome.  
Thank You.

---

<div class="post-metadata">

**Author:** ![MisterAI](https://avatars.discourse-cdn.com/v4/letter/m/46a35a/32.png) [@MisterAI](https://discuss.huggingface.co/u/MisterAI)\
**Post date:** [November 26, 2024, 8:14pm UTC](https://discuss.huggingface.co/t/serverless-inference-api-token-limits-settings/127725/2 "2024-11-26T20:14:46Z")

</div>

**For the record:**  
Useful documentation :  
[https://huggingface.co/docs/api-inference/tasks/text-generation?code=js#api-specification](https://huggingface.co/docs/api-inference/tasks/text-generation?code=js#api-specification)  
[https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1?inference\_api=true](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1?inference_api=true)

It would appear that there is a default limit of 500 tokens.  
I still have to figure out how to send the ‘max\_new\_tokens’ parameter at the same time as my request from a Make module.  
I am continuing my research on  
[https://community.make.com/c/how-to/66](https://community.make.com/c/how-to/66)

regards

---

<div class="post-metadata">

**Author:** ![system](https://us1.discourse-cdn.com/hellohellohello/original/2X/d/de4155eb4aa4108ecb32a1389d7cc37ae69f88b7.png) [@system](https://discuss.huggingface.co/u/system)\
**Post date:** [November 27, 2024, 8:14am UTC](https://discuss.huggingface.co/t/serverless-inference-api-token-limits-settings/127725/3 "2024-11-27T08:14:55Z")

</div>

This topic was automatically closed 12 hours after the last reply. New replies are no longer allowed.