Pricing Plans

One response from gpt-3.5-turbo (the default) costs 1 message credit.
One response from gpt-4 costs 20 message credits.
You can change which model your brain uses in the brain settings. The difference is because gpt-4 costs 15x (prompt tokens) and 30x (completion tokens) what gpt-3.5-turbo costs on OpenAI.

Yes, just by signing up you get 100 message credits and 3 brains (50MB of storage for each brain). You can use these to test out Quivr and see if it works for you.

You can choose to run Quivr locally for data privacy and data security purposes: our Github repo.
Also, we’ve developed an online app of Quivr. This means that our app, along with data you upload to us, resides online. We use Amazon Web Services (AWS) for storage and computation. Our servers are located in Ireland.

The data stored on our servers is encrypted and no one except Quivr can read it. This allows us to extract useful information from it, which is required for most of our features. This is a common practice for text analytics platform.