> For the complete documentation index, see [llms.txt](https://docs.otari.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.otari.ai/learn/budgets.md).
# Budgets
A budget caps how much can be spent in a period and blocks requests when the limit is reached. You can set budgets at the organization or workspace level, and narrow them to specific members or providers when you need finer control.
***
### Scope: where the budget applies
Every budget has two scope dimensions.
**Level:**
* Organization caps spend across the whole organization.
* Workspace caps spend within a single workspace.
**Applies to:**
* Overall is one total cap for everything at that level.
* Members caps all members, or one specific member.
* Providers caps all providers, or one specific provider.
**Combine the two to get a specific scope.**
* **Organization > Overall**: total organization spend cap.
* **Organization > A specific member**: cap one person's spend across all workspaces.
* **Workspace > All providers**: cap spend on every provider used by that workspace.
* **Workspace > A specific member**: cap one contributor's spend within one workspace.
{% hint style="info" %}
Each budget is enforced independently. If a workspace has a $500/month overall cap and one member has a $100/month cap inside that workspace, both limits are checked on every request. The first budget to run out blocks the request.
{% endhint %}
***
### Period: how often it resets
| **Daily** | Resets every day at UTC midnight. |
| ----------- | ------------------------------------------------- |
| **Weekly** | Resets every Monday at UTC midnight. |
| **Monthly** | Resets on the first of the month at UTC midnight. |
All resets are automatic. No cleanup is required.
***
### Enforcement
When a budget is exhausted, Otari blocks matching requests until the next period starts.
{% hint style="info" %}
Existing in-flight requests complete normally. New requests at or above the cap fail until the next reset.
{% endhint %}
***
### Status indicators
| 🟢 **Green (0-80%)** | Healthy. |
| ----------------------- | ----------------------------------------------------- |
| 🟡 **Yellow (80-100%)** | Approaching the limit. |
| 🔴 **Red (100%+)** | Exhausted. Matching requests are blocked until reset. |
***
### Limit types
Spend limits are defined in USD. Budgets can also cap tokens and request count.
Ready to set up a budget?
{% content-ref url="/pages/AhgAITMaTc8ggokxoe3I" %}
[Set a budget & ceiling](/how-to-guides/set-a-budget-and-ceiling.md)
{% endcontent-ref %}
---
# 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.otari.ai/learn/budgets.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.