Coroid bills for two separate things, and keeping them apart makes the cost predictable.
Capacity — agent slots, charged per slot per month. A standing commitment that determines how much work can run at once.
Model usage — the tokens your work consumes, either prepaid as credits or billed directly by your own provider. This varies depending on what you actually run.
Coroid applies no markup to provider token rates regardless.
Why separate them?
Bundling them would mean either capping model usage within the capacity price — so heavy users subsidise light ones — or metering everything, making budgeting impossible.
Splitting them ensures the predictable part stays predictable and the variable part remains visible.
Where these items are managed
| Task | Where |
|---|---|
| Change plan | Settings → Billing → Plans & billing |
| Add or remove slots | Settings → Billing → Capacity & credits |
| Top up credits | Settings → Billing → Capacity & credits |
| See what you are using | Settings → Billing → Usage |
| Attribute spend | Settings → Billing → Detailed reports |
| Invoices | Settings → Billing → Billing history |
| Bring your own keys | Settings → Provider keys |
The two questions people commonly ask
"Why is my work slow?" Almost never due to billing. A task's duration depends on the size of the change and your test suite. Slots determine how many tasks run at once. See Capacity and agent slots.
"Why did spend go up?" In order of likelihood: rework increased, a capable profile was assigned to a high-volume agent, or tasks became broader. See Usage and reports.