Welcome to Dispatch

Managed model access for your organization — one key per person, one bill, and the controls to keep both in check

Every team now wants to use AI models from their own tools — coding agents, editors, scripts, internal apps. Left alone, that turns into a pile of personal provider accounts, keys pasted into chat, and a bill nobody can explain until it arrives.

Dispatch gives your organization one managed front door to the models. Each person gets their own API key that works in the tools they already use. Administrators decide what everyone may spend, which models they may call, what content is allowed, and where requests are processed — and everyone can see what it all costs, as it happens.

From key to cost report in minutes: An admin sets a monthly budget and a per-person allowance. A developer creates a key, follows the Claude Code cookbook, and is coding against Dispatch two minutes later. At the end of the week the admin opens Cost Reporting, groups spend by team tag, and sees exactly which project drove the increase.

Who Is This For?

• Developers and power users — one key that works in Claude Code, Cursor, Codex, OpenCode and anything else that accepts an OpenAI-compatible base URL

• Engineering and IT leaders — give a whole team model access without handing out provider accounts

• Finance and operations — a single bill, budgets that are enforced rather than advisory, and reports you can share

• Security and compliance — guardrails on what may be sent, control over which models are reachable, and data residency for where requests are processed

Key Benefits

Benefit	Description
Works With Your Tools	Speaks the OpenAI and Anthropic APIs, with step-by-step cookbooks for popular agents and editors
Personal Keys, Shared Controls	Everyone manages their own keys; limits and policy belong to the person, not the key
Enforced Budgets	Organization budgets and per-person allowances are hard limits, not warnings
Guardrails	Named policies that block sensitive content, cap spend and narrow which models people can call
Model Access	Choose which model tiers your organization may call
Data Residency	Restrict where requests may be processed
Cost Reporting	Group, filter and share spend by person, tier or tag
Insights	Checks that flag what's worth fixing, and where Token Optimization is saving money

How Dispatch Works

1. Connect — Point a tool at Dispatch with your personal API key.

2. Govern — Requests are held to your allowance, the organization's budget, your guardrail, the models the organization allows and where it may be processed.

3. Report — Usage and cost are recorded as requests happen, ready to report on by person, tier or tag.

Getting Started

1

Open Dispatch Launch Dispatch from the DarcyIQ Platform launcher. See Opening Dispatch.

2

Create a key Create your personal API key on the API keys page. See API Keys.

3

Connect a tool Follow the cookbook for your agent or editor. See Quickstart and Cookbooks.

4

Set the guardrails (admins) Set a budget, choose which models are allowed, and invite your team. See Organization Settings.

Next Steps

Goal	Documentation
Understand what each role can do	Roles & Access
Make your first request	Quickstart
See what models you can call	Models
Report on spend	Cost Reporting
Set budgets and policy for everyone	Organization Settings
Looking for DarcyIQ itself?	DarcyIQ documentation