> For the complete documentation index, see [llms.txt](https://docs.darcyiq.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.darcyiq.com/dispatch/manage/manage.md).

# Organization Settings

The Organization page, where a Dispatch Admin sets spend, content policy, models, data residency, tags and provider accounts for everyone at once

Personal keys only work for a whole organization if somebody decides the rules they all run under: what the organization may spend, what may be sent, which models may be called, where requests are processed, and who pays the provider. **The Organization page is where a Dispatch Admin makes those decisions once, for everybody.** Every key in the organization follows them, whoever created it.

{% hint style="info" %}
**Who can use it**: The Organization page is for Dispatch Admins only. It appears under **Manage** in the sidebar, next to [Users](/dispatch/manage/users.md). If a Dispatch User opens its address, Dispatch takes them to their API keys instead. See [Roles & Access](/dispatch/get-started/roles-and-access.md).
{% endhint %}

## When Changes Take Effect

The page describes itself as "Settings for everybody in the organization. Changes apply to new requests straight away." Requests that are already running aren't affected. Two details are worth knowing:

* **Models** and **Token Optimization** confirm a save by saying the change applies within a minute.
* Spend is measured every few minutes, so a budget or allowance that has just been reached can let a little more spend through before requests are refused.

## The Tabs, in Setup Order

The tabs run in the order you'd set up a new organization. The first four are limits on every request: what it may cost, what it may contain, which models it may reach, and where it may be processed. Tags come next, because they label the spend those requests create. Provider keys come last, because most organizations never need them: by default, every request runs on DarcyIQ's own provider accounts.

**Models** sits with the limits, not with the read-only [Models](/dispatch/use-dispatch/models.md) page, because it's the same kind of decision as a guardrail: an administrator choosing on behalf of everyone. The Models page in the main navigation is where people go to see what they're allowed to call.

| Tab                  | What you decide                                                                                                        | Documentation                                                     |
| -------------------- | ---------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------- |
| **Billing & Budget** | Prepaid credits, and the most the whole organization may spend in a day, week or month                                 | [Billing & Budget](/dispatch/manage/manage/billing-and-budget.md) |
| **Guardrails**       | Spend limits, content filters and model restrictions for groups of people, plus the defaults new key owners start with | [Guardrails](/dispatch/manage/manage/guardrails.md)               |
| **Models**           | Which model tiers anyone in the organization may call, and how new tiers arrive                                        | [Model Access](/dispatch/manage/manage/model-access.md)           |
| **Data residency**   | Whether requests may be processed anywhere, or only in the U.S.                                                        | [Data Residency](/dispatch/manage/manage/data-residency.md)       |
| **Tags**             | The labels spend is grouped by in Cost Reporting                                                                       | [Tags](/dispatch/manage/manage/tags.md)                           |
| **Provider keys**    | Whether to use your own model provider accounts instead of DarcyIQ's                                                   | [Provider Keys](/dispatch/manage/manage/provider-keys.md)         |

## A Suggested First Pass

{% stepper %}
{% step %}
**Fund the organization and set a ceiling** On **Billing & Budget**, add credits and set an organization budget so spend can't run past a number you chose. See [Billing & Budget](/dispatch/manage/manage/billing-and-budget.md).
{% endstep %}

{% step %}
**Set what new people start with** On **Guardrails**, create a guardrail if you need content filters, then fill in **Defaults for new key owners** so everyone's first key arrives with an allowance. See [Guardrails](/dispatch/manage/manage/guardrails.md).
{% endstep %}

{% step %}
**Choose the models and the region** On **Models**, switch off any tiers your organization shouldn't call. On **Data residency**, choose U.S. only if your data or contracts require it. See [Model Access](/dispatch/manage/manage/model-access.md) and [Data Residency](/dispatch/manage/manage/data-residency.md).
{% endstep %}

{% step %}
**Define tags, then invite your team** Create the tags you want to report on, then invite colleagues from [Users](/dispatch/manage/users.md).
{% endstep %}
{% endstepper %}

## Next Steps

| Goal                                           | Documentation                                                     |
| ---------------------------------------------- | ----------------------------------------------------------------- |
| Add credits and set the organization budget    | [Billing & Budget](/dispatch/manage/manage/billing-and-budget.md) |
| Limit what groups of people can spend and send | [Guardrails](/dispatch/manage/manage/guardrails.md)               |
| Invite people and set their allowances         | [Users](/dispatch/manage/users.md)                                |
| See what the settings cost and save            | [Cost Reporting](/dispatch/cost-and-insights/cost-reporting.md)   |


---

# 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.darcyiq.com/dispatch/manage/manage.md?ask=<question>&goal=<user_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.