Credits
Every data call needs a signed-in account, and each account draws from a monthly credit wallet. Credits are tracked on your account, not per key, so creating extra keys does not create extra allowance. Each of the nine root tools has a fixed price that covers its default sections. Each optional section you add costs 1 more credit. Leaving a default section out does not lower the price.
Through the developer profile or the CLI,
each catalog tool costs 1 credit. Discovery tools and
report_feedback cost none.
A validation error costs nothing, because the credit is debited only after your arguments
validate and the provider is reachable. If the call then fails, the credits are refunded and
the receipt carries a warning saying so. A multi-part tool counts as failed only when every
section failed; if some sections answered, the call is charged and the failed ones are listed
under missing. Each receipt says what happened in credit_cost, credits_used and
credits_remaining (see receipts).
Current pricing lives at
hiveintelligence.xyz/pricing.
What happens at the cap
Requests fail with a quota error naming the cause. Nothing is billed beyond your subscription, and no request silently degrades to worse data. The credit error tells you to upgrade or wait for the next cycle. On the MCP endpoint it also names the exact instant your credits refill, taken from your billing cycle, and sendsRetry-After: 60. On the REST API the same error carries X-Quota-Remaining but no
Retry-After and no refill instant, so read your cycle end from dashboard usage instead.
Your credits reset on a rolling cycle, not on the first of the month. The cycle is anchored to
when your account was created, or to your most recent payment if you are on a paid plan. You
can see the current balance and cycle end on
dashboard usage.
Rate limits
Rate limits are per minute and per plan. Exceeding one returns a rate limit error with headers telling you when to retry. Agents should back off rather than retrying immediately. Rate limits and credits are separate: you can be well inside your monthly credits and still hit a per minute limit during a burst.Designing agents around this
A few habits that keep agents inside the caps:- Use
limitandpagerather than pulling full result sets you will not read. - Cache results your workflow reuses within a single task, instead of re-fetching per step.
- Ask only for the optional sections you will read. Each one costs a credit.

