Reading Your Usage

The Usage panel sits below the summary on Settings → Billing. It answers one question — what is costing this much — by re-pivoting the same period across the attributes Fours records as consumption happens.

The Usage panel — group-by tabs, filters, the daily spend chart, and the period grouped by resource with quantity, cost and share columns


Choose the month

The period selector at the top of the page drives both panels, so the summary and the usage table always describe the same month. It offers the last 12 months, newest first, with the current month marked (current).

Selecting a closed month shows that month’s settled figures. The credit balance above is always your balance now.

Group the period

The tab strip re-pivots the same consumption. Every pivot totals the same amount.

Group byAnswers
ResourceWhat kind of thing did the money go on — tokens, sandbox, storage
UserWho caused it
AppWhich Insulin app it ran under
ModelWhich model was used
ProviderWhich provider served it
AgentWhich agent or AI feature spent it

Each row shows the cost and the row’s share of the period. Under Resource, the first figure is the Quantity, with its unit. Every other grouping mixes resources measured in different units — tokens with processor-seconds — so there the column is Tokens, input and output tokens alone, and a row with no tokens, such as sandbox or storage spend, shows a dash.

Users are shown by name. A row shows the member’s name (or their email, if their profile has no name), with their user ID beside it. Someone who is not a member of the organization — a former member, say — is shown by the email recorded with their usage, and usage recorded before emails were recorded shows the ID alone. Everyone who can open Settings → Billing sees those recorded emails.

Apps are shown by name. On the App tab a row shows the app’s name with its ID beside it. Apps are named by the same rule as your app list: an app you cannot see, such as a colleague’s private app, or one that has been deleted, reads Private or deleted app · 1a2b3c4d (the first eight characters of its ID), with its full ID still beside it. Its spend still counts.

Sandbox and storage have a provider. Under Provider, sandbox usage appears under daytona and object storage under aws-s3, older months included.

Spend by agent

The Agent tab answers which agent is spending our credit. Each row is an agent or an AI feature, with three more columns:

ColumnShows
Agent IDThe agent’s ID. Two agents can share a name; the ID tells them apart.
TypeBuilt-in — an agent or feature that ships with Fours — or Custom, one made in your organization
LevelOrg for an organization agent or feature, User for one person’s own — the built-in Insulin assistant is User, because each person has their own

Besides your agents, the rows name the AI features that run for your organization: the Console assistant, the App Builder, the Inbox, Knowledge base, and the AI features elsewhere in the Fours console — What is metered lists them. A custom agent you cannot see, such as a colleague’s personal agent, or one that has been deleted, reads Private or deleted agent · 1a2b3c4d (the first eight characters of its ID), with its full ID under Agent ID and a dash for Type and Level; its spend still counts. If Fours cannot look the names up at all, agents and apps show their IDs instead, and built-in agents keep their names.

Rows with nothing to attribute

Some consumption genuinely has no value for the dimension you picked: a scheduled job has no user, a direct API call has no app, sandbox storage has no model. Those rows are named rather than dropped —

GroupingThe unattributed row reads
UserNo user — scheduled and system runs
AppNo app
ModelNo model — sandbox and storage
ProviderNo provider recorded — usage recorded without a provider
AgentNo agent — sandbox, storage and earlier usage — including AI usage from before agents were recorded, so an older month shows most of its spend here

The same period grouped by user, with three named members and an italic 'No user — scheduled and system runs' row carrying the remainder

This is why the pivots reconcile. If unattributed consumption were left out, the by-user view would quietly total less than the by-resource view, and neither would match your bill.

Narrow it with filters

Five multi-select filters — Users, Apps, Agents, Models and Providers — sit under the tabs. Grouping and filtering answer different questions: grouping is what did we spend it on, filtering is what did this team spend it on.

Each filter lists every value that occurs in the period, whatever the table is grouped by, and a selection stays applied as you switch tabs. No filter ever offers someone who never used AI: the lists are built from the period’s own usage, not from your member list. An Agents or Apps choice shows its ID under its name, and typing an ID in the filter’s search finds it.

With any filter applied the panel says so, because a filtered total is a subset of the period, not the whole bill. Clear filters returns to the full period.

The daily spend chart

One bar per day of the period, with the peak day highlighted and labelled above the chart. Days with no spend render as an empty slot rather than being closed up — a chart that bridged a quiet weekend would draw a slope across spending nobody can account for. The chart follows the filters, so a filtered chart and table describe the same spend.

Why the table can look emptier than your balance

The usage breakdown is re-aggregated every couple of hours. The credit balance above it comes straight from the ledger and moves within about a minute of a request.

So this sequence is normal:

  1. You run something expensive.
  2. The Credit balance drops immediately.
  3. The Usage table still shows the period without it.

The panel says as much above the table. If the two disagree, the balance is the current one — the table is catching up, and nothing has been lost or double-counted.

An empty table therefore means nothing has been aggregated for this period yet, which is not the same as you have used nothing.

What this panel does not do

There is no CSV export and no per-request drill-down. The finest grain available here is a grouped row for the period. If you need the underlying detail — to reconcile a specific job or a specific day — contact support@suger.io while the consumption records are still inside their 90-day retention window.

Spotted something wrong or out of date on this page? Tell us and we'll correct it.