Skip to main content

Blog / Engineering analytics

How much does AI-assisted development cost per shipped feature?

Monthly model bills tell you almost nothing. Attributing spend through sessions to landed features turns an opaque total into a unit economic you can manage.

The Tempo team · 11 July 2026

Divide attributed spend by landed features, not total spend by the calendar. Teams that trace model costs through coding sessions to the features that actually shipped typically discover unit costs in the hundreds of dollars per feature, along with a long tail of spend that produced nothing and is nobody’s fault until it is visible.

The problem with the monthly total

Most engineering leaders can quote their monthly AI bill. Very few can say what it bought. A five-figure model spend that produced a quarter's worth of shipped product is excellent. The same spend producing three features and a pile of abandoned branches is a problem. The total cannot tell you which one you have.

Building cost per feature

The attribution chain has three links. Sessions carry token usage and model pricing, so each session has a cost. Sessions touch files and produce commits, so they connect to pull requests. Pull requests land in features. Follow the chain and spend stops being a monthly blob and becomes a per-feature figure you can watch over time.

Three practical notes from doing this on real data:

What this changes in practice

Once cost follows the work, ordinary management questions get answers. Which project is burning premium-model tokens on work a cheaper model handles? Which engineer's two-thousand-dollar month of agents replaced what would have been a fortnight of work, and which one's produced nothing mergeable? Where does a budget flag need to fire before the invoice becomes a surprise? None of these are answerable from a monthly total. All of them are answerable from attributed spend.

Frequently asked questions

What is a good cost per shipped feature?

There is no universal number; complexity varies too much. What matters is establishing your own baseline and trend. Teams commonly land in the hundreds of dollars per feature once attribution is in place.

How accurate is cost estimation for subscription seats?

It is an equivalent-value estimate: session token counts priced at public per-model rates. It is not an invoice, and honest tooling labels it as such, but it is consistent and comparable across the team.

Does cost attribution require developers to tag their work?

No. The chain from session to commit to pull request to feature can be built from data that already exists. Declared priorities improve the importance weighting, but attribution itself is automatic.

See this on your own team's data

Tempo reads real coding-agent sessions and git history to show who ships what, what it costs and whether AI is paying off. No screenshots, ever.

Book a demo

Related reading: How do you measure developer productivity when AI writes most of the code? · What can Anthropic's admin tools actually show you about Claude Code usage?