Limits and billing
Rate limits, prepaid credit, spend caps and automatic top-up.
Rate limits
Rate limits apply per key, to requests and tokens per minute. Every response includes:
| Header | Meaning |
|---|---|
x-qlo-ratelimit-limit | The limit that applies to this key |
x-qlo-ratelimit-remaining | What is left in the current window |
x-qlo-ratelimit-reset | When the window resets |
A 429 response also carries retry-after, in seconds.
New organizations start with conservative rate and daily spend limits, which rise automatically as the account builds history. You can also set your own daily spend cap under Settings.
Prepaid credit
Qloud bills per token from prepaid credit.
- Before a request runs, Qloud reserves enough credit for the longest reply it could produce.
- When it finishes, you are charged for the tokens actually used and the rest of the reservation is released at once.
- Input, cached input and output tokens are priced separately.
Setting max_tokens keeps the reservation small, which matters when your balance is low: a request whose reservation your credit cannot cover is refused with 402 insufficient_credits.
Credit is non-refundable. See the Terms of Service.
Automatic top-up
Turn on automatic top-up under Billing to recharge your saved card when credit falls below a threshold you choose. It stays on until you turn it off.