When an AI agent builds software for you, someone pays for the model that does the thinking. There are two common setups: the vendor bundles model usage into its price, or you bring your own subscription or API key. This guide explains the second setup and when it fits.
What bring your own means
You hold an account with the model provider, such as a Claude Code, Codex, OpenCode or Oh My Pi subscription, or an API key. The delivery tool uses that account to run the agents. Your provider bill shows exactly what the agents used.
Why teams choose it
- Cost you can see: usage appears on your own provider account, so there is no hidden markup on model use.
- Control: you decide which model runs, and you can change it when a better one ships.
- Existing agreements: if your company already has terms with a provider, those terms keep applying.
- Predictable planning: a flat subscription is easier to budget than usage you cannot see.
What you still pay the delivery tool for
The delivery tool covers the work around the model: reading the backlog, planning, running agents in parallel, review, and keeping the ticket up to date. Model usage is separate and stays on your account. Delivery Autopilot works this way: its packs cover the agents and the workflow, and model usage runs on your own subscription or key.
How to size a subscription
Start with a small number of tickets and watch usage for a couple of weeks. Look at how much one typical ticket uses, then multiply by the tickets you expect each month. Leave headroom for tickets that need a second try.
Questions to ask before you start
- Which provider and plan does my company already use?
- Who owns the account, and who can see the usage?
- Is the code used to train models under our plan?
- What happens when the plan's limit is reached mid-ticket?
Write the answers down once. They are the same for every ticket that follows.