For the complete documentation index, see llms.txt. This page is also available as Markdown.

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.

Who can use it: The Organization page is for Dispatch Admins only. It appears under Manage in the sidebar, next to Users. If a Dispatch User opens its address, Dispatch takes them to their API keys instead. See Roles & Access.

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 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

Guardrails

Spend limits, content filters and model restrictions for groups of people, plus the defaults new key owners start with

Models

Which model tiers anyone in the organization may call, and how new tiers arrive

Data residency

Whether requests may be processed anywhere, or only in the U.S.

Tags

The labels spend is grouped by in Cost Reporting

Provider keys

Whether to use your own model provider accounts instead of DarcyIQ's

A Suggested First Pass

1

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.

2

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.

3

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 and Data Residency.

4

Define tags, then invite your team Create the tags you want to report on, then invite colleagues from Users.

Next Steps

Goal
Documentation

Add credits and set the organization budget

Limit what groups of people can spend and send

Invite people and set their allowances

See what the settings cost and save

Last updated

Was this helpful?