What you see
Pick a window of Last 7 days, Last 30 days, or Last 90 days — 30 by default.
The breakdown can be pivoted by Agent, Model, or Provider.
Where the numbers come from
Every run carries a usage record: the provider, the model, the token breakdown, a cost amount, a currency, and a cost source. The usage is merged from what the worker reports during the run — token events, the run’s output, and its metadata. Each run’s cost then falls into one of three classes.
Runs with no usage record at all contribute runs but no cost.
Why the split is shown rather than hidden. A single “total spend” number silently mixes figures a
provider billed you for with figures KAOP computed from token counts and published rates. Those have
different error bars, and treating them as one is how a cost review ends in an argument. The split is
on the tile so you always know how much of the total is measured and how much is modelled.
When a worker’s own figure is discarded
If a run names a provider KAOP does not price directly and the model’s rate is resolvable, the worker’s own cost figure is discarded and the cost is re-estimated from those rates. That is deliberate: a worker-supplied figure for a provider the platform cannot corroborate is not more trustworthy than a rate-based estimate, and mixing the two conventions within one total is worse than either. Where cache rates are not published for a model, they are derived from its input rate — cached reads at a fraction of it, cache writes at a premium to it.Making your agents’ cost show up
Agents built on the KAOP SDK adapters report token usage automatically. If you build a worker yourself, include a usage object in the run’s output or metadata. Several field aliases are accepted, so most existing usage shapes work unchanged:
Report a cost amount to get reported cost. Report a model plus token counts to get an
estimate. Report neither and the run contributes volume but no spend.
Reading spend through the API
The Spend view is backed by the account activity endpoint, which you can call directly.window_days accepts 1 to 365.
Budgets
A budget caps what an agent — or a workflow — may spend in a time window, and optionally stops new work when the cap is reached.Agent budgets
Set one on the agent itself: open Fleet, select the agent, and go to Govern → Limits & Scaling. The Budget row shows its current state — capped, or not — and expands into the cap form. Budgets are per agent: an agent with no budget is not capped by the others’. The managed LLM gateway’s account budget is separate — see Limits & quotas.Setting one
1
Set a daily and/or a monthly cap
Each window is independent and resets on its own clock in UTC — daily at midnight, monthly on
the first.
2
Choose what happens when a cap is hit
Notify and keep running, or Pause new runs.
What “Pause new runs” does
The behavior is specific, and worth reading before you enable it:- The agent’s schedule, webhook, and channel triggers stop firing until the window resets. A run that was already queued is cancelled.
- A run already in progress is terminated, within roughly a minute of the cap being hit.
- Manual invocation still works. You can always run the agent yourself from the console.
A budget cannot be created for an agent that brings its own model key. KAOP does not see that
agent’s spend, so a cap it could neither measure nor enforce is refused rather than accepted and
quietly ignored.
Workflow budgets
A workflow — the thing a module like Incident management & troubleshooting runs — can carry its own spend cap, independent of any budget set on the agents it invokes. Set it on the workflow’s own Spend limit step: a Daily limit and a Monthly limit, each toggled on independently. When a limit is reached, Pause the workflow skips new incidents — they are not investigated, and a manual retry is skipped too — until the window resets, while an investigation already running finishes; Notify, keep running alerts and keeps investigating.Reaching a budget outside the console
- Chat. Ask the assistant to cap an agent’s spend and it fills in the same budget you would set by hand on the agent’s Govern tab.
-
Infrastructure as code. A self-hosted agent’s budgets are part of its
declared settings, so they can
be committed and reconciled like the rest of the manifest:
The declared list replaces the agent’s budgets on every apply — drop a window from the manifest and it is removed, not merely left alone. Workflow budgets are not declarable this way.
Bringing spend down
1
Find the concentration
Pivot the breakdown by Agent, then by Model. Spend is almost never evenly spread — one
agent or one model usually dominates.
2
Read cost per success, not total
A high-volume agent with a low unit cost is working. A low-volume agent with a high unit cost is
the one to look at.
3
Open the most expensive runs
Each one links to its evidence. An outlier run usually explains itself — a retry storm, an
oversized context, or a tool loop.
4
Settle any change as an experiment
Swapping to a cheaper model is a quality decision, not a billing one. Prove it against real
history before you apply it.
Next steps
Fleet
Cost beside reliability, per agent and per window.
Runs & evidence
A single run’s usage record, and what it did to earn it.
Observability & OTel export
Token volume as an operational signal in your own backend.