Rate Limit and Privacy for Inference API

Hi this question is about the free public inference API.
I was trying out the VS Code Extension “HF Code Autocomplete” (HF Code Autocomplete - Visual Studio Marketplace)
I created an access token and the extension uses the model bigcode/starcoder

  1. Is data sent to and received back from the hugging face free public inference API thoroughly private (i.e. LLM prompts and completions)? Is it safe to send proprietary and confidential information in prompts?
  2. I did not find clear information on the rate limit for the free tier. The documentation here links to the usage dashboard (Detailed usage and pinned models). In my case it says I am over the free tier limit?

    Would be great to get some clear information on this.

Thanks!

4 Likes