Usage
What your agents did, what it cost, and every call you can open and listen to.
Usage is the workspace-wide record: how much your agents worked, what that cost, and a line for every call. It sits in the main sidebar, not under an agent, because it covers all of them at once.
Analytics answers how well is my agent doing. Usage answers what did it do, and what am I paying for — and they are different questions.
The last thirty days
The chart at the top is activity over time: replies your agents sent and calls they handled, on the same thirty-day grid so you can see them against each other. A spike in calls the week you ran a campaign should look like one.
Useful for the thing dashboards rarely tell you: when your customers actually get in touch. If the line rises every evening after six, that is when somebody should be reachable.
WhatsApp is billed per message, and it is broken out here in full — marketing, utility, authentication and service counted separately, by country, because they cost very different amounts.
The figure against each line is what you were charged, in your own currency, so it reconciles against your balance and against your own record of what you sent. Everything the workspace sends is counted the same way, whether it came from a campaign, a sequence, the Send Message page or the API.
Note
A message that was not delivered is not charged for. WhatsApp bills for what it delivers. When a failure comes back the charge is credited, so a line you see here is a message that arrived.
Note
Until 1 October 2026, an open 24-hour window makes two things free: the agent's own replies, and any utility template you send while it is open. Templates that start a conversation are charged, and so is authentication in or out of a window. If a number looks higher than you expected, the split here usually shows why — see Windows and what gets charged.
Calls
Every call the workspace answered or placed, newest first: when, who, which agent, whether it connected, how long it ran, and what it cost.
Open one to read the transcript. If the call was recorded, the recording is there too.
Tools shows every tool the agent ran on the call, in order: booking a slot, saving a lead, a custom action. A failed one is marked in red with the reason, and opens to show what the agent sent and what came back. It is the first place to look when an agent said it did something and did not. Passwords, keys and codes are never shown. Tool details are kept for 30 days.
Export gives you the same list as a file that opens in Excel or any spreadsheet: when each call started, its direction, the agent, the other person's number, which of your numbers it rang from (calls the agent placed), how it ended, its length and its cost. After those come what the call was about: its summary, and one column for each detail the agent collected, such as the caller's name or the reason they called. A call that did not collect a detail has an empty cell under it.
To get the caller's name and the reason in the file, add them as details on the agent's Actions page under Collect details here, and keep Summarise each call on, on the Playground. A call whose recording and transcript you deleted shows no summary or details.
A call on OpenAI GPT-Live-1 shows the model by that name and is billed at its own flat rate a minute rather than on a voice plan: its cost is the charge for the call, with no per-minute rate beside it.
Note
A call that shows as failed never connected — a wrong number, a line that rang out, a caller who hung up before the agent spoke. Failed calls cost nothing and are kept so the list is honest about what was attempted.
How a call went
An opened call also shows how it went, in numbers, and whether anything broke:
- How the call went — how long the caller waited for each reply (the typical wait, the slow end, and the slowest), how many pauses of 10 seconds or more there were (or your agent's own "are you still there?" time, if it has one), how often the caller spoke over the agent, and how many replies the agent could not produce or a backup had to produce. A call that was never measured, such as one that never connected, has no figures.
- Where the time went in each turn — open it under How the call went. One row per turn: when the first word of the actual answer was heard, when the first sound of any kind was (a thinking line or an acknowledgement that plays first is not the answer, and the row says so), how long the turn took to be decided, Ear's check, the model's first sentence and the voice. A dash means the step did not happen on that turn. A leading ≈ means a thinking line spoke first and the answer's start is worked out from the audio queued behind it, not heard directly.
- Problems on this call — shown only when something went wrong while the call was live: the agent could not answer, your own model key failed, a reply took more than 5 seconds to start, or the voice connection failed.
Through the API the numbers are quality on
Get Call (answerMs is the time to the first
word of the actual answer, and knowledgeTurns the turns that looked something
up in the agent's knowledge), every turn's timing is
Get Call Timeline, and every problem is sent as a
call.problem webhook while
the call is still going on, so you can alert somebody before it ends.
Recordings
Recording is off unless you turn it on, per agent, on that agent's Playground, in the Sound and recording card. When it is on, the calls that agent answers or places — on your website, and by phone on a number you took from us — are recorded and appear here.
Warning
Recordings are deleted when your plan says — after 30 days on pay-as-you-go, 49 on Pro and 75 on Scale. Download anything you need to keep before then. Once it is deleted it is gone and we cannot get it back.
A caller on your website sees This call is recorded as the call connects. See Recording calls for which phone calls can be.
Telling people they are being recorded is your responsibility, not ours. In most places it has to be said at the start of the call, and the wording that satisfies your regulator is not something we can write for you. Put it in your agent's first words.
Plan credit
Pro and Scale give you usage credit every billing period. It is spent before your own balance, so money you topped up is not touched until the credit is used.
Unused credit rolls over for up to 3 months while your paid subscription remains active. Each period's credit expires at the end of its own 3-month window: credit granted for the period starting 1 January can be spent until 1 April, and the credit granted for February has its own window after that. When you spend, the oldest credit goes first, so what would expire soonest is used before newer credit.
- If you cancel, what is left lasts until the end of the period you have paid for, then expires.
- On a yearly plan the whole year's credit is granted at once, and it lasts the year plus two months.
- Money you topped up never expires. Only the plan's credit does.
Your balance on the billing page shows the credit and your own money together.
Through the API, Get Usage returns creditMicro
(the credit you hold) and creditExpiresAt (the earliest date any of it
expires, or null when there is none).
What is not here
Warning
- Per-customer spend. Usage is per workspace and per channel, not per contact.
- Live figures to the second. Costs settle when a call ends and when Meta confirms a send, so the most recent minutes can lag slightly.
- Your invoice. This is what you used. What you owe is on Settings → Billing, and the two are presented differently on purpose.
Tip
Registered for GST in India? Put your GSTIN in Settings → General, under Billing details. It is recorded on every invoice we issue you from the moment you save it, which is what makes those invoices usable by your accountant. Only an owner or admin can set it, and it takes effect on invoices issued afterwards — so it is worth doing before your first payment rather than after. The GST number is asked of workspaces billed in rupees only.
Invoices in a different name. If your invoices should carry your company's legal name rather than the workspace name, set a Billing name in Settings → General, under Billing details. Left empty, invoices use the workspace name.
