# Do coding agents recommend Portkey?

> Portkey is the most chosen AI gateway, taking 21% of 140 judged AI gateways sessions. Measured with Claude Code, Codex and Cursor.

Source: https://armature.tech/library/do-coding-agents-recommend-portkey
Published: 2026-09-03
Publisher: Armature, Inc. (https://armature.tech)

---

> Portkey is the most chosen AI gateway, taking 21% of 140 judged AI gateways sessions. It was also raised as a candidate in 98 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 Portkey. What an agent actually installed.

## The numbers

| | |
| --- | --- |
| Category | AI gateways |
| Sessions in the category | 140 |
| Sessions where Portkey was chosen | 30 |
| Install share | 21% |
| Rank in category | 1 of 8 |
| Codebases it won in | 6 |
| Raised as a candidate, not chosen | 98 |
| Chosen when considered | 23% |
| Site | portkey.ai |

## By agent

The three agents treat Portkey very differently. Claude Code chose it in 31% of its sessions in this category and Codex in 10%, a spread of 21 points.

| Agent | Sessions | Chose Portkey | Share |
| --- | --- | --- | --- |
| Claude Code | 45 | 14 | 31% |
| Codex | 48 | 5 | 10% |
| Cursor | 47 | 11 | 23% |

A single blended install share would report the midpoint and hide both ends. If most of your users run Codex, your real position here is 10%, not 21%.

## By who was asking

Portkey does much better with one kind of buyer than another. It won 34% of sessions asked as senior engineer and 0% of those asked as vibe coder.

| Who is asking | Sessions | Chose Portkey | Share |
| --- | --- | --- | --- |
| Vibe coder | 16 | 0 | 0% |
| Junior developer | 33 | 2 | 6% |
| Senior engineer | 56 | 19 | 34% |
| Enterprise team | 35 | 9 | 26% |

## What Portkey was up against

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

| # | Product | Runs won | Share |
| --- | --- | --- | --- |
| 1 | Portkey **(this page)** | 30 | 21% |
| 2 | Cloudflare AI Gateway | 30 | 21% |
| 3 | LiteLLM | 25 | 18% |
| 4 | Vercel AI Gateway | 22 | 16% |
| 5 | OpenRouter | 15 | 11% |
| 6 | Built in-house (no product adopted) | 12 | 9% |
| 7 | Amazon Bedrock | 3 | 2% |
| 8 | Helicone | 1 | 1% |

## What this means

Leading a category is a position to defend rather than a result to celebrate. In our data, leaders lose ground in exactly two situations: when the person asking is an enterprise buyer with procurement constraints, and when a competitor's documentation is easier for an agent to integrate correctly.

The defence is unglamorous. Keep the quickstart running. Keep the version current on the page. Keep the names aligned. Stay in the templates.

## 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](/library/how-we-measured-this).

Every AI gateways run can be replayed on [the board](/leaderboards/ai-gateway).

If you work on Portkey: 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 Portkey?

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

### Does Claude Code recommend Portkey?

In 14 of the 45 sessions in AI gateways run with Claude Code, which is 31%.

### Do different coding agents treat Portkey differently?

Yes, and by a wide margin. Claude Code chose it in 31% of its runs and Codex in 10%.

### 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 Portkey considered but not chosen?

It was raised as a candidate in 98 sessions without being chosen, and chosen in 30. That is a 23% conversion from considered to chosen.

## Read next

- [How to get picked for AI gateways by coding agents](https://armature.tech/library/ai-gateway-coding-agents-playbook) (Markdown: https://armature.tech/library/ai-gateway-coding-agents-playbook.md)
- [Do coding agents recommend Cloudflare AI Gateway?](https://armature.tech/library/do-coding-agents-recommend-cloudflare-ai-gateway) (Markdown: https://armature.tech/library/do-coding-agents-recommend-cloudflare-ai-gateway.md)
- [Do coding agents recommend LiteLLM?](https://armature.tech/library/do-coding-agents-recommend-litellm) (Markdown: https://armature.tech/library/do-coding-agents-recommend-litellm.md)
- [Do Claude Code, Codex and Cursor pick the same tools?](https://armature.tech/library/do-claude-code-and-codex-agree) (Markdown: https://armature.tech/library/do-claude-code-and-codex-agree.md)

---

Armature helps software products get discovered and used by coding agents.
Service: https://armature.tech/discoverability · Results: https://armature.tech/leaderboards/sectors · Contact: contact@armature.tech