WholeTech · Weekly Usage Pacingauto · estimated
DIALED IN
Right on pace to use your full weekly allowance — the target.
28.7%Est. week used
88%Projected by reset
32.8%Of week elapsed
$929API-equiv this week
4.7dUntil reset

The Pace Race · usage vs. the clock

🏁 RESET

Estimated weekly usage racing the clock. When ⚡ Usage trails ⏱ Time, that striped stretch is headroom you've paid for.

⏱ Time elapsed32.8%
⚡ Usage (est.)28.7%
4.1 pts of headroom

Daily spend · API-equivalent

$164
Thu 9
$675
Fri 10
$90
Sat 11

What to improve

94%
sessions active 8+ hours

Background/loop sessions add up fast. Keep long runs intentional; kill idle ones.

82%
subagent-heavy sessions

Each subagent runs its own requests. Spawn deliberately; use a cheaper model for simple ones.

68%
context over 150k tokens

Longer context costs more even when cached. /compact mid-task, /clear when switching tasks.

60%
4+ sessions in parallel

All sessions share one weekly limit. Queue work you don't need all at once.

Manual readings

FedSession $Week %
7:28am CT · Jul 11$147.0927%
12:07am CT · Jul 1126%
~11:21pm Jul 1026%
7:38pm CT · Jul 10$115.0425%
7:28pm CT · Jul 10$113.7424%
7:02pm CT · Jul 10$109.4824%
6:07pm CT · Jul 10$102.4322%
5:48pm CT · Jul 10$95.5521%
5:42pm CT · Jul 10$94.4320%
5:21pm CT · Jul 10$92.5420%
5:19pm CT · Jul 10$90.6920%
4:30pm CT · Jul 1019%
3:18pm CT · Jul 10$83.5818%
2:47pm CT · Jul 10$69.9313%
2:43pm CT · Jul 1011%
2:27pm CT · Jul 10$63.119%
2:03pm · Jul 10$4.418%
10:45am CT · Jul 11$157.1028%

The big number is an estimate: ccusage measures this machine's API-equivalent spend, calibrated to your last real reading (27% at 7:28am CT · Jul 11). It updates hands-free from ccusage — no pasting. It counts this machine only, so paste /usage occasionally to re-calibrate against the true cross-device total. ccusage last read: ~12:00pm CT Jul 11.