Investigation units & quotas
Investigation units & quotas
logcat.ai meters AI usage on a single axis: the investigation unit. Every investigation costs some number of units, your account gets a monthly budget, and each investigation draws down against it. A Quick Search and a deep multi-file comparison draw down different amounts.
Uploading and analyzing a file costs no units. Units are spent on search and research.
The unit model
One unit is one Deep Research investigation. Everything else is a fraction or a multiple of that:
| Investigation | Cost in units |
|---|---|
| Deep Research (single file) | 1.0 |
| Quick Search (single file) | 0.1 |
| Quick Search over a bundle / multi-file | 0.25 |
| Delta comparison | 2 per group of 3 files |
| Bundle comparison | 1.0 flat |
A few things to know:
- A Quick Search is a tenth of a unit, so you can triage freely. It costs more over a bundle (0.25) because it searches across every file in the bundle.
- Delta scales with file count. Up to 3 files is 2 units, 4 to 6 files is 4 units, and so on. Every group of three files adds two.
- A bundle comparison is flat. However many files a bundle holds, comparing bundles costs one unit: a bundle counts as one file.
The reset period
If you have a paid subscription, your budget resets on your renewal date each month. If you don’t, it resets with the calendar month. On a trial, you get one fixed 14-day budget that doesn’t refill during the trial.
Your billing page shows your current usage and the exact reset date for your account.
Bonus credit packs stack
If you run out mid-period, a credit pack can be added to your account. Bonus units stack on top of your allowance rather than replacing it, and they’re drawn down alongside your regular units. Storage works the same way. Ask, and it’s applied. See Plans & pricing.
Next
- Why was I limited?: what happens when you hit the cap.
- Plans & pricing: capabilities and allowances.