How to get picked for AI gateways by coding agents
Portkey took 26% of 329 judged AI gateways sessions. What the numbers say a vendor in this category should do.
If you sell AI gateways, this page is the part of the market no dashboard shows you: what a coding agent does when a developer asks for AI gateways and never compares vendors.
The numbers come from 329 judged sessions with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code, spread across 8 realistic codebases, with every session read by a judge.
What coding agents choose for AI gateways
Across 329 judged sessions, Portkey was chosen most often, in 26% of runs. Cloudflare AI Gateway was second with 23%.
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Portkey | 86 | 26% |
| 2 | Cloudflare AI Gateway | 76 | 23% |
| 3 | Vercel AI Gateway | 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% |
| 9 | Envoy AI Gateway | 1 | 0% |
| 10 | Opper | 1 | 0% |
Full board, every run replayable: the AI gateways leaderboard.
What the shape of this category means
The leader takes only 26% of runs. This category is genuinely open and the ordering can be moved.
With the top product at 26%, AI gateways is decided in the moment, from what the agent reads and what it finds in the repository. Nothing is locked in, which is the best situation a vendor can be in and the one where the work pays fastest.
The order here is set by the quality of what an agent can read and by whether your product is already present in the codebase. Both are things you can change.
The agents do not agree with each other
In this category Claude Code, Codex and Cursor did not put the same product first.
Grok Build CLI (24 sessions) and Muse Code (69 sessions) join this table with fewer runs, so read their rows as indicative.
| Agent | Runs | Picked most often |
|---|---|---|
| Claude Code | 69 | Portkey (21) |
| Codex | 96 | Cloudflare AI Gateway (36) |
| Cursor | 71 | Portkey (17) |
| Grok Build CLI | 24 | Portkey (6) |
| Muse Code | 69 | Portkey (22) |
That split decides where a vendor spends. In this category Codex ran a web search in 100% of its sessions and Claude Code in 23%, so what you publish reaches nearly all of Codex's AI gateways sessions and about a quarter of Claude Code's. Taking Cloudflare AI Gateway's position with Codex is mostly a content problem. Taking Portkey's with Claude Code leans more on the repository.
Who is asking changes the answer
Every request in this experiment was written as a specific kind of person. In this category the leader changes with the person.
| Who is asking | Runs | Picked most often |
|---|---|---|
| Vibe coder | 40 | OpenRouter |
| Junior developer | 81 | Vercel AI Gateway |
| Senior engineer | 126 | Portkey |
| Enterprise team | 82 | Portkey |
That is 3 different products winning AI gateways for 4 kinds of buyer, out of the same 329 sessions. Nobody here is winning AI gateways. They are each winning one kind of buyer.
If you sell to more than one of them, you need pages for each. See how to win the enterprise persona.
What you are really competing against
In 5% 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 AI gateways the clearest case is Kong AI Gateway: on the table in 34 sessions, chosen in none.
| Product | Raised in | Chosen in |
|---|---|---|
| Kong AI Gateway | 34 sessions | 0 |
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 34 sessions is recorded in each transcript, one reason at a time.
What to do about it in AI gateways
- Aim at second place first. Portkey holds 26% and Cloudflare AI Gateway holds 23%. The gap between the default and the field is where the reachable sessions are.
- Pick which buyer you are for. The same AI gateways need written as a vibe coder landed on OpenRouter, and written as an enterprise team landed on Portkey. Those are two markets, and the enterprise one needs pages containing the constraint words: audit log, data residency, retention, single sign-on. See how to win the enterprise persona.
- Measure per agent. Claude Code put Portkey first, Codex put Cloudflare AI Gateway first, Cursor put Portkey first, Grok Build CLI put Portkey first, Muse Code put Portkey first. A blended number for AI gateways describes a market that does not exist.
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 AI gateway on this board
One page per product, with its install share, the per-agent split, and how often it was raised without being chosen.
- Do coding agents recommend Portkey? — chosen in 26% of sessions
- Do coding agents recommend Cloudflare AI Gateway? — chosen in 23% of sessions
- Do coding agents recommend Vercel AI Gateway? — chosen in 16% of sessions
- Do coding agents recommend OpenRouter? — chosen in 15% of sessions
- Do coding agents recommend LiteLLM? — chosen in 8% of sessions
- Do coding agents recommend Helicone? — chosen in 0% of sessions
Where these numbers come from
329 judged sessions in AI gateways across 8 codebases, part of a published set of 15,287. 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 AI gateways run can be replayed on the board.
<!-- generated by scripts/write-data-pages.mjs -->
Common questions
How many codebases is this based on?
329 judged sessions across 8 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 AI gateway do coding agents choose?
Across 329 judged sessions, Portkey was chosen most often, in 26% of runs. Cloudflare AI Gateway was second with 23%. The result changes by agent and by who is asking.
Do Claude Code and Codex pick the same AI gateway?
No. Claude Code picked Portkey, Codex picked Cloudflare AI Gateway, Cursor picked Portkey. Measuring one agent tells you about part of the market only.
How often do agents build AI gateways themselves instead of installing something?
In 5% 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 AI gateways do agents consider but never choose?
Kong AI Gateway (raised in 34 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 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.