Playbooks

How to get picked for usage-based billing by coding agents

Metronome took 45% of 293 judged usage-based billing sessions. What the numbers say a vendor in this category should do.

Published September 14, 2026 Read as Markdown

If you sell usage-based billing platforms, this page is the part of the market no dashboard shows you: what a coding agent does when a developer asks for usage-based billing and never compares vendors.

The numbers come from 293 judged sessions with Claude Code, Codex and Cursor, spread across 11 realistic codebases, with every session read by a judge.

What coding agents choose for usage-based billing

Across 293 judged sessions, Metronome was chosen most often, in 45% of runs. Orb was second with 18%.

#ProductRuns wonShare
1Metronome13145%
2Orb5318%
3Built in-house (no product adopted)4014%
4Lago3913%
5CGRateS103%
6Stripe Billing52%
7OpenMeter52%
8PortaBilling31%
9Solvimon21%
10m3ter21%

Full board, every run replayable: the usage-based billing leaderboard.

What the shape of this category means

The leader takes 45% of runs and there is a real second place. The category has a default but it is not settled.

Metronome at 45% with Orb at 18% is a default with a real challenger behind it. The agent is choosing rather than reaching, which means the inputs it uses can move the answer.

The work is to be the easiest correct answer: a quickstart that runs when pasted, documentation that states the current version, and pages that answer the exact configuration questions agents search for.

The agents do not agree with each other

In this category all three agents put Metronome first, which is less common than it sounds: across the eighteen categories we measured, Claude Code and Codex disagreed on the leader in nine of them.

AgentRunsPicked most often
Claude Code95Metronome (30)
Codex99Metronome (54)
Cursor99Metronome (47)

Even where they agree, they get there differently. Codex ran a web search in 53% of decision runs and Claude Code in 1.6%, so what you publish reaches one of them in half its usage-based billing sessions and the other in almost none.

Who is asking changes the answer

Every request was written as a specific kind of person. In this category Metronome led for every persona, which is a sign of a strong default.

Who is askingRunsPicked most often
Junior developer54Metronome
Senior engineer107Metronome
Enterprise team132Metronome

What you are really competing against

In 14% of runs the agent wrote the code itself rather than adopting a product. That is low enough that your competition is other vendors, but high enough to be worth watching.

Considered, and never chosen

Because the judge records every product an agent raised and not only the one it picked, this board also shows who kept reaching the shortlist and losing. In usage-based billing the clearest case is Chargebee: on the table in 125 sessions, chosen in none.

ProductRaised inChosen in
Chargebee125 sessions0
Zuora113 sessions0
Recurly70 sessions0
Kill Bill63 sessions0
Togai29 sessions0

Being rejected is a better position than being unknown, and a cheaper one to fix. The product is already in the agent's head and on the list. Whatever ended those 400 sessions is recorded in each transcript, one reason at a time.

What to do about it in usage-based billing

  1. Aim at second place first. Metronome holds 45% and Orb holds 18%. The gap between the default and the field is where the reachable sessions are.

The work that applies to every category rather than to this one is written up separately: audit your documentation, write a quickstart an agent can follow, and how to measure install share.

Every usage-based billing platform on this board

One page per product, with its install share, the per-agent split, and how often it was raised without being chosen.

Where these numbers come from

293 judged sessions in usage-based billing across 11 codebases, part of a published set of 6,748. Real coding agents at pinned versions, in sandboxes, inside realistic codebases, with a simulated project owner in the loop and a blind judge on every session. The full method is on one page: how we measured this.

Every usage-based billing run can be replayed on the board.

<!-- generated by scripts/write-data-pages.mjs -->

Common questions

How many codebases is this based on?

293 judged sessions across 11 realistic codebases. A category only runs on repositories where its seam is open, so coverage differs: some categories ran on more than ten codebases and some on two.

What usage-based billing platform do coding agents choose?

Across 293 judged sessions, Metronome was chosen most often, in 45% of runs. Orb was second with 18%. The result changes by agent and by who is asking.

Do Claude Code and Codex pick the same usage-based billing platform?

Yes. All three agents we tested put Metronome first in this category, which is unusual: they disagree in half of the categories we measured.

How often do agents build usage-based billing themselves instead of installing something?

In 14% of runs the agent wrote the code itself rather than adopting a product.

How can a vendor improve its position here?

Make the quickstart run when pasted, state the current version on the documentation page, use one name across product, package and import, write pages for the symptoms users describe rather than only the category name, and get into the repository through templates and framework integrations.

Which usage-based billing platforms do agents consider but never choose?

Chargebee (raised in 125 sessions, chosen in none), Zuora (raised in 113 sessions, chosen in none), Recurly (raised in 70 sessions, chosen in none), Kill Bill (raised in 63 sessions, chosen in none), Togai (raised in 29 sessions, chosen in none). Being considered and not chosen is a different problem from being unknown, and it is usually fixable.

Where this comes from

Armature ran 6,748 judged sessions with Claude Code, Codex and Cursor inside 74 realistic codebases, and published every run. The numbers on this page come from that work.

Read next

All library pages