From the experiment

Do coding agents recommend Cloudflare AI Gateway?

Cloudflare AI Gateway was chosen in 21% of 140 judged AI gateways sessions, ranking second. Measured with Claude Code, Codex and Cursor.

Published September 3, 2026 Read as Markdown

Cloudflare AI Gateway was chosen in 21% of 140 judged AI gateways sessions, ranking second. It was also raised as a candidate in 85 further sessions without being chosen.

This page reports what happened when Claude Code, Codex and Cursor had to solve a problem in AI gateways inside a realistic codebase. Not what a chat assistant says about Cloudflare AI Gateway. What an agent actually installed.

The numbers

CategoryAI gateways
Sessions in the category140
Sessions where Cloudflare AI Gateway was chosen30
Install share21%
Rank in category2 of 8
Codebases it won in8
Raised as a candidate, not chosen85
Chosen when considered26%
Sitecloudflare.com

By agent

The three agents treat Cloudflare AI Gateway very differently. Codex chose it in 42% of its sessions in this category and Cursor in 0%, a spread of 42 points.

AgentSessionsChose Cloudflare AI GatewayShare
Claude Code451022%
Codex482042%
Cursor4700%

A single blended install share would report the midpoint and hide both ends. If most of your users run Cursor, your real position here is 0%, not 21%.

By who was asking

Cloudflare AI Gateway does much better with one kind of buyer than another. It won 31% of sessions asked as vibe coder and 16% of those asked as senior engineer.

Who is askingSessionsChose Cloudflare AI GatewayShare
Vibe coder16531%
Junior developer331030%
Senior engineer56916%
Enterprise team35617%

What Cloudflare AI Gateway was up against

The full ranking in AI gateways, from the same sessions:

#ProductRuns wonShare
1Portkey3021%
2Cloudflare AI Gateway (this page)3021%
3LiteLLM2518%
4Vercel AI Gateway2216%
5OpenRouter1511%
6Built in-house (no product adopted)129%
7Amazon Bedrock32%
8Helicone11%

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 140 sessions in AI gateways are part of a published set of 5,292, 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 Cloudflare 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 Cloudflare AI Gateway?

Yes. Cloudflare AI Gateway was chosen in 30 of the 140 judged sessions in AI gateways, a 21% install share, ranking second in its category.

Does Claude Code recommend Cloudflare AI Gateway?

In 10 of the 45 sessions in AI gateways run with Claude Code, which is 22%.

Do different coding agents treat Cloudflare AI Gateway differently?

Yes, and by a wide margin. Codex chose it in 42% of its runs and Cursor in 0%.

How was this measured?

Real coding agents at pinned versions were run in sandboxes inside 51 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 Cloudflare AI Gateway considered but not chosen?

It was raised as a candidate in 85 sessions without being chosen, and chosen in 30. That is a 26% conversion from considered to chosen.

Where this comes from

Armature ran 5,292 judged sessions with Claude Code, Codex and Cursor inside 51 realistic codebases, and published every run. The numbers on this page come from that work.

Read next

All library pages