Credit Usage is dependent on a verity of factors, most prominent being the LLM selected, and the number of AI Tokens used. It is nearly impossible to determine the exact number of AI Tokens a prompt will use, however, estimations can me made based on previous token measurements provided by the LLM.
Assuming an A4 size of paper has 500 words, producing a 100 word summary should range between 1 and 12 Hatz Credits depending on the LLM selected, complexity of the document specifically in regard to word structure, length and count.
A typical chat with Secure AI will cost 1 - 30 Hatz Credits and will change based on LLM selected, the length of the chat, and how complex the interaction is.
Tokens are units of data used by a language model used to process and generate text. Input tokens are the result of the information that is put into the model. Output tokens are the result presented from the model in an accessible format
No. Hatz users are reset to their standard credit amount on the first of every month. Unused credits from the previous month are not rolled into the next.
Hatz Credits are calculated based off of two indicators that roll into one formula:
Hatz Credits are units of measure directly tied to AI usage in the Hatz AI platform. Each Hatz AI user is entitled to a set number of credits that can be shared with users across their tenant. Credits automatically reset at the start of the month.
Hatz uses a credit system to measure AI usage across the Hatz Platform. Hatz Credits can be shared at a company level across all users. Not all team members will use AI the same. Credit based usage allows customers to provide secure AI access to all users. Less frequent users and users doing less complex tasks can gain access to AI without an increase in cost, simultaneously allowing power users to increase usage.