> For the complete documentation index, see [llms.txt](https://docs.uptiq.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.uptiq.ai/ai-workbench-qore/control-center/cost-control/usage-limits.md).
# Usage Limits
Set credit spending caps and receive threshold alerts.
Set hard caps for credit consumption and alerts for administrators. Open **Cost Control → Usage Limits**.
{% hint style="info" %}
**Credit limits exist at three levels**, and the strictest applicable one wins: an organization-wide cap, the per-account limits and alerts this page configures, and a per-agent credit guardrail set in Agent Builder. Every account also starts with a default weekly hard limit, until you replace it with your own.
{% endhint %}
Usage Limits, with configured limits and alerts.
### Create usage limits
Usage limits are hard caps. Requests that would exceed a limit are rejected.
Each limit shows its period, cap, and type. For example, a **Monthly** limit of `80,000 Credits` can be a **Hard Limit**. It resets on the first day of each month.
Select **+ Add Limit** to create a limit. Use a row's menu to edit or remove it.
### Add an alert
Usage alerts email every **Account Admin** role holder on the account once per period after usage crosses a threshold — not every administrator on the platform. Select **+ Add Alerts** to create one.
**+ Add Alerts** opens the **Add Alert** dialog:
* **Duration**—required. The alert period, such as **Daily**
* **Metric Type**—required. **Absolute Credits** uses a credit count. **Percentage of Limit** uses a share of a configured limit
* **Credit Limit** or threshold—required. Enter a credit count for **Absolute Credits**. Enter a percentage for **Percentage of Limit**
The Add Alert dialog.
Choose **Absolute Credits** or **Percentage of Limit** as the alert metric.
{% hint style="info" %}
**How it works:** The platform evaluates every usage limit before consumption. If a request exceeds any limit, the platform rejects it.
{% endhint %}
### Related
Review consumption and credit history in [Credit Usage](/ai-workbench-qore/control-center/cost-control/credit-usage.md).
{% content-ref url="/pages/807cab861e090edd0ce825909db3db1b28f73799" %}
[Control Center](/ai-workbench-qore/start-here/control-center.md)
{% endcontent-ref %}
***
{% columns %}
{% column width="83.33333333333334%" %}
Maintained by Abhishek Paul AI-assisted, human-approved
{% endcolumn %}
{% endcolumns %}
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.
Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:
```
GET https://docs.uptiq.ai/ai-workbench-qore/control-center/cost-control/usage-limits.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
