# You should never pay for a failed generation

> Zero-risk billing: how automatic refunds work when an upstream task fails before producing a result.

- **Published**: 2026-06-10
- **Tag**: Billing
- **Read time**: 3 min

---

Generative models fail sometimes — a provider hiccup, a moderation block, a timeout. You shouldn't eat the cost when there's no output to show for it.

# How refunds work

- Credits are debited when a task is created.
- If the upstream task fails before producing a result, the debit is reversed automatically.
- Refunds are idempotent — a retried failure never double-refunds.

The result: your effective spend tracks successful output, not attempts.
