Do coding agents recommend OpenMeter?
OpenMeter was chosen in 2% of 515 judged usage-based billing sessions, ranking sixth. Measured with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code.
OpenMeter was chosen in 2% of 515 judged usage-based billing sessions, ranking sixth. It was also raised as a candidate in 209 further sessions without being chosen.
This page reports what happened when Claude Code, Codex, Cursor, Grok Build CLI and Muse Code had to solve a problem in usage-based billing inside a realistic codebase. Not what a chat assistant says about OpenMeter. What an agent actually installed.
The numbers
| Category | Usage-based billing |
| Sessions in the category | 515 |
| Sessions where OpenMeter was chosen | 9 |
| Install share | 2% |
| Rank in category | 6 of 15 |
| Codebases it won in | 3 |
| Raised as a candidate, not chosen | 209 |
| Chosen when considered | 4% |
| Site | openmeter.io |
By agent
With 9 wins spread across 5 agents, the rates below are small numbers and a difference between them is not yet a finding. They are here because the direction is worth knowing, not because the gap is established.
| Agent | Sessions | Chose OpenMeter | Share |
|---|---|---|---|
| Claude Code | 127 | 0 | 0% |
| Codex | 131 | 4 | 3% |
| Cursor | 132 | 3 | 2% |
| Grok Build CLI | 26 | 0 | 0% |
| Muse Code | 99 | 2 | 2% |
By who was asking
OpenMeter performs similarly across the four kinds of buyer, from 0% to 4%. That is unusual: the category leader changed with the persona in 22 of the 29 categories we measured.
| Who is asking | Sessions | Chose OpenMeter | Share |
|---|---|---|---|
| Junior developer | 94 | 0 | 0% |
| Senior engineer | 190 | 8 | 4% |
| Enterprise team | 231 | 1 | 0% |
What OpenMeter was up against
The full ranking in usage-based billing, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Metronome | 211 | 41% |
| 2 | Built in-house (no product adopted) | 107 | 21% |
| 3 | Orb | 80 | 16% |
| 4 | Lago | 59 | 11% |
| 5 | Stripe Billing | 13 | 3% |
| 6 | CGRateS | 13 | 3% |
| 7 | OpenMeter (this page) | 9 | 2% |
| 8 | Solvimon | 6 | 1% |
What this means
This is an integration problem, not a presence problem. Agents raised OpenMeter in 209 sessions and chose it in 9, so it reaches the shortlist and then loses. Something at the last step is costing the session, and in our data that is usually a quickstart that does not run when pasted, documentation describing an interface that changed, or a package name that does not match the product name.
That is the cheaper of the two problems to have. The reason is written down in each losing transcript.
Where these numbers come from
The 515 sessions in usage-based billing are part of a published set of 13,497, run with real coding agents inside realistic codebases and judged blind. The full method is on one page: how we measured this.
Every usage-based billing run can be replayed on the board.
If you work on OpenMeter: the judge recorded a reason for every session where it was raised and passed over. Those reasons are in the transcripts.
<!-- generated by scripts/write-data-pages.mjs -->
Common questions
Do coding agents recommend OpenMeter?
Yes. OpenMeter was chosen in 9 of the 515 judged sessions in usage-based billing, a 2% install share, ranking sixth in its category.
Does Claude Code recommend OpenMeter?
In 0 of the 127 sessions in usage-based billing run with Claude Code, which is 0%.
Do different coding agents treat OpenMeter differently?
Not much. Claude Code, Codex, Cursor and Muse Code chose it at similar rates, between 0% and 3% of their runs.
How was this measured?
Real coding agents at pinned versions were run in sandboxes inside 91 realistic codebases and asked to solve real tasks. A simulated project owner approved or questioned each recommendation before any code was written, and a judge from a model family that builds none of the agents read every session blind.
How often is OpenMeter considered but not chosen?
It was raised as a candidate in 209 sessions without being chosen, and chosen in 9. That is a 4% conversion from considered to chosen.
Where this comes from
Armature ran 13,497 judged sessions with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code inside 91 realistic codebases, and published every run. The numbers on this page come from that work.