StopworkStopworkruntime
Metered compute for agents

A budget
you cannot
exceed.

Inference and sandboxes for autonomous agents. Metered per unit, capped per key — and the cap is taken before the call runs, so a runaway agent is refused rather than reconciled.

In the catalog
swork-fast· meteredswork-deep· meteredswork-sandbox· wall timeswork-fast· cappedswork-deep· cappedswork-sandbox· capped
The contract
01

Reserved,
not checked.

02

Hard budgets
per key.

03

Refused,
not reconciled.

Every call holds its worst possible cost before it runs. Two calls cannot both believe there is room, because the room is taken rather than read.

The hold settles afterwards to what was actually used. Settlement can only give money back — an upstream that over-reports is clamped to the hold.

A call that would breach the cap returns a refusal naming the shortfall. Nothing ran, nothing is owed, and there is no invoice to dispute later.

The demonstration

Press it against
the cap.

One key, capped at $2.04
each call: 4,000 in, ceiling 2,000 out
Committed
$0.0000
Held in flight
$0.0000
Spendable
$2.0400
Cap breached
no
The meter

Priced in whole
micro-cents.

A token can cost a millionth of a cent, so cents are not small enough to hold the price and floats are not exact enough to hold the total. Everything here is an integer number of micro-cents, start to finish.

ModelIn µ¢/tokOut µ¢/tokµ¢/sec
swork-fast280
swork-deep6300
swork-sandbox00900
swork-fast, 4,000 in, ceiling 2,000 out

  4,000 × 2   =  8,000 µ¢
  2,000 × 8   =  16,000 µ¢
                  ────────────
  reserved            24,000 µ¢   = $0.2400

⚠ The output figure is the ceiling you declared, not an estimate. Reserving what a call is likely to cost and hoping is the same bug as checking the balance — the call that overruns is precisely the one you needed to stop.