Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.yourhq.ai/llms.txt

Use this file to discover all available pages before exploring further.

HQ records every LLM call an agent makes and lets you set monthly budgets to control spend.

What gets tracked

Token usage

Input, output, cache-read, and cache-write tokens per call.

Estimated cost

Calculated from known model pricing. Unknown models are counted as unmetered — never silently invented.

Setting a budget

1

Open the agent detail page

Navigate to Agents → select an agent → scroll to the Usage & Budget section.
2

Configure limits

Set a monthly limit in USD, a soft warning threshold (percentage), and whether to hard-stop the agent when the limit is exceeded.
3

Monitor spend

Current-period usage rolls up automatically. Budget warnings and exceedances create notifications.

What happens at the limit

SettingBehavior
Soft thresholdA notification is created when the agent crosses the warning percentage
Hard cutoff enabledThe runtime blocks further replies and the dispatcher stops waking the agent for background work
Hard cutoff disabledThe agent keeps working — you get the notification but no enforcement
Start without a hard cutoff to see how much an agent actually uses, then set limits based on real data.