Spend controls and billing behavior.

The spend order

Every credit-metered action, managed model usage, web searches, environment hours, and mailboxes, follows the same path.

1. 1Monthly credit grant firstEvery plan includes a monthly credit grant (the amount varies by plan). Usage draws it down first, and it resets with the billing period.
2. 2Topped-up credits nextWhen the grant is exhausted, or during a trial, usage draws from any credits you have topped up.
3. 3Hard stop at zeroWhen both are exhausted, agents pause: LLM calls, web searches, and further environment or mailbox charges stop. Environments and mailboxes stay provisioned, and everything resumes the moment you top up, switch to BYOK, or the grant resets. There is no open-ended metered billing.

Credits and top-ups

A credit is Qoren's single unit of usage, worth $0.001, bought from Account & Billing with a $5-$100 slider. What you pay lands in your balance 1:1, pay $20, get 20,000 credits.

• Topped-up credits never expire and carry across billing periods.
• They cover usage during a trial and beyond your monthly grant.
• Checkout runs through Polar, the payment processor for all Qoren billing.

Bring your own key (BYOK)

Every plan, including the trial, can connect its own OpenRouter key instead of using the managed one. With BYOK you pay OpenRouter directly for model usage, any model is available, and the managed LLM meter no longer applies, OpenRouter's own limits govern. Environments, mailboxes, and web searches still draw credits either way.

• BYOK is OpenRouter-exclusive. The key is validated, stored encrypted, and applied across all your agents.
• Disconnecting reverts to the managed key and re-enables LLM metering against your credit balance.
• The card warns you when a connected key looks free-tier, so agents don't stall mid-run.

Watching spend

The Spending page meters usage where it happens, per agent and per task.

• OpenRouter cost and tokens (in/out) per agent, with 24h / 7d / 30d / all-time windows.
• Sessions broken down by source: scheduled runs, chat, Telegram, Slack, and the rest.
• HTTP request counts per external API the agent calls, usage beyond the model bill stays visible.
• An ≈ marker flags totals that include the provider's estimate before exact costs land.

For agencies

Because each client runs in separate environments, the Spending page's per-client grouping is also your per-client cost report, useful both for your own margins and for showing a client what their agents actually did.