Usage

Paid plans come with a monthly allowance for metered usage. This page explains what spends it, what doesn't, and how to keep an eye on it. For your exact allowance and current rates, see Settings → Billing.

What's metered

Two things draw down your allowance:

• Models: calls to the metered models (everything above Auto). More capable models and higher reasoning effort cost more, because they do more work per call.
• Sandbox: time on a metered runtime, charged by the minute. A GPU costs more than CPU, and a bigger GPU costs more than a smaller one. The meter runs while a paid runtime is attached to your work, and an idle sandbox is shut down on its own so it doesn't keep charging.

The usage meter also tracks a Tools category for metered tool calls. Editing, branching, and reading output are not metered.

The free floor

Here's the part worth remembering: the Auto model and CPU runtime are never metered, on any plan. Run Auto on a CPU sandbox all day and your allowance doesn't move.

That's deliberate. The everyday loop, where you describe a task and let Auto write and run it on CPU, stays free. Your allowance only comes into play when you reach for something heavier, like a paid model or a GPU.

Your allowance

Paid plans include a monthly allowance for metered usage, and it resets each billing cycle. The free tier has its own smaller allowance for the occasional metered call. When the allowance runs out, metered work stops and you drop back to the free Auto-on-CPU loop, unless you've turned on pay-as-you-go.

Reading the usage meter

The usage meter in Settings → Billing shows where your allowance is going:

• how much of it you've used this cycle,
• a breakdown by category across Models, Sandbox, and Tools,
• which models and which runtimes took the most,
• and a projection of how many days are left at your current rate.

If the projection says you'll run out early, lean on Auto and CPU more, dial back effort, or look at pay-as-you-go.