Do coding agents recommend Vercel AI Gateway?
Vercel AI Gateway was chosen in 16% of 329 judged AI gateways sessions, ranking third. Measured with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code.
Vercel AI Gateway was chosen in 16% of 329 judged AI gateways sessions, ranking third. It was also raised as a candidate in 110 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 AI gateways inside a realistic codebase. Not what a chat assistant says about Vercel AI Gateway. What an agent actually installed.
The numbers
| Category | AI gateways |
| Sessions in the category | 329 |
| Sessions where Vercel AI Gateway was chosen | 52 |
| Install share | 16% |
| Rank in category | 3 of 9 |
| Codebases it won in | 5 |
| Raised as a candidate, not chosen | 110 |
| Chosen when considered | 32% |
| Site | vercel.com |
By agent
Claude Code, Codex, Cursor and Muse Code land within 6 points of each other on Vercel AI Gateway, which is closer than most products in this experiment manage. Grok Build CLI ran fewer than 30 sessions here, too few to compare.
| Agent | Sessions | Chose Vercel AI Gateway | Share |
|---|---|---|---|
| Claude Code | 69 | 8 | 12% |
| Codex | 96 | 17 | 18% |
| Cursor | 71 | 13 | 18% |
| Grok Build CLI | 24 | 4 | 17% |
| Muse Code | 69 | 10 | 14% |
By who was asking
Vercel AI Gateway does much better with one kind of buyer than another. It won 46% of sessions asked as junior developer and 1% of those asked as enterprise team.
| Who is asking | Sessions | Chose Vercel AI Gateway | Share |
|---|---|---|---|
| Vibe coder | 40 | 9 | 23% |
| Junior developer | 81 | 37 | 46% |
| Senior engineer | 126 | 5 | 4% |
| Enterprise team | 82 | 1 | 1% |
What Vercel AI Gateway was up against
The full ranking in AI gateways, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Portkey | 86 | 26% |
| 2 | Cloudflare AI Gateway | 76 | 23% |
| 3 | Vercel AI Gateway (this page) | 52 | 16% |
| 4 | OpenRouter | 49 | 15% |
| 5 | LiteLLM | 25 | 8% |
| 6 | Built in-house (no product adopted) | 15 | 5% |
| 7 | Amazon Bedrock | 14 | 4% |
| 8 | Helicone | 1 | 0% |
What this means
A solid second or third position in a category means the agent is genuinely choosing rather than reaching automatically. That is a winnable position, because the inputs it uses can be changed.
The fastest gains are usually in the sessions that were nearly won: read them, find the step where the agent moved on, and fix that step.
Where these numbers come from
The 329 sessions in AI gateways are part of a published set of 15,287, run with real coding agents inside realistic codebases and judged blind. The full method is on one page: how we measured this.
Every AI gateways run can be replayed on the board.
If you work on Vercel AI Gateway: 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 Vercel AI Gateway?
Yes. Vercel AI Gateway was chosen in 52 of the 329 judged sessions in AI gateways, a 16% install share, ranking third in its category.
Does Claude Code recommend Vercel AI Gateway?
In 8 of the 69 sessions in AI gateways run with Claude Code, which is 12%.
Do different coding agents treat Vercel AI Gateway differently?
Not much. Claude Code, Codex, Cursor and Muse Code chose it at similar rates, between 12% and 18% of their runs.
How was this measured?
Real coding agents at pinned versions were run in sandboxes inside 110 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 Vercel AI Gateway considered but not chosen?
It was raised as a candidate in 110 sessions without being chosen, and chosen in 52. That is a 32% conversion from considered to chosen.
Where this comes from
Armature ran 15,287 judged sessions with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code inside 110 realistic codebases, and published every run. The numbers on this page come from that work.