See how much the service was used and what that use cost over a period.
Operator consoleAvailable
Analytics answers "how much was the service used, and what did it cost?" for a period you choose. It adds up all sessions. It does not show one customer. For one customer, use Users. For one session, use Sessions.
Totals, a daily chart and two breakdowns. The model names here are made up.
What you see
The time buttons run from 6h to 1y. The page opens on 7d.
Three cards: Total Spend, Total Tokens and LLM Calls. A token is a small piece of text. It is the unit the service counts in. An LLM call is one request to the AI.
Daily Spend is a bar for each day. Point at a bar to see that day's cost and number of calls.
Cost by Model lists each AI setting with its calls, spend, tokens, and how many of those tokens were sent in (Prompt) and written back (Completion).
By Agent lists each kind of helper with its sessions, requests and average duration.
A section with nothing in it says No activity in this window.
Spend is our cost
All money on this page is what the AI work cost Haruno. It is not what customers paid. For income and profit, see Financials.
Long windows
The service answers this page for up to 30 days. If 90d or 1y shows an error, switch to 30d.
Who can use it
Every operator can read it. Nothing on it can be changed.
What a person in sales or product can ask an operator
"How has usage changed over the last month?" Pick 30d and read the daily chart.
"Which kind of AI use costs the most?" Read the Cost by Model table.