How to get picked for AI gateways by coding agents
Portkey took 21% of 140 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 140 judged sessions with Claude Code, Codex and Cursor, spread across 8 realistic codebases, with every session read by a judge.
What coding agents choose for AI gateways
Across 140 judged sessions, Portkey was chosen most often, in 21% of runs. Cloudflare AI Gateway was second with 21%.
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Portkey | 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% |
| 9 | Envoy AI Gateway | 1 | 1% |
Full board, every run replayable: the AI gateways leaderboard.
What the shape of this category means
The leader takes only 21% of runs. This category is genuinely open and the ordering can be moved.
With the top product at 21%, 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 the three agents we ran put different products first.
| Agent | Runs | Picked most often |
|---|---|---|
| Claude Code | 45 | Portkey (14) |
| Codex | 48 | Cloudflare AI Gateway (20) |
| Cursor | 47 | LiteLLM (11) |
That split decides where a vendor spends. Codex ran a web search in 53% of decision runs and Claude Code in 1.6%, so the pages you publish are live in half of Codex's AI gateways sessions and almost none of Claude Code's. Taking Cloudflare AI Gateway's position with Codex is a content problem. Taking Portkey's with Claude Code is a repository problem.
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 | 16 | Vercel AI Gateway |
| Junior developer | 33 | Vercel AI Gateway |
| Senior engineer | 56 | Portkey |
| Enterprise team | 35 | LiteLLM |
That is 3 different products winning AI gateways for 4 kinds of buyer, out of the same 140 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 9% 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 29 sessions, chosen in none.
| Product | Raised in | Chosen in |
|---|---|---|
| Kong AI Gateway | 29 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 29 sessions is recorded in each transcript, one reason at a time.
What to do about it in AI gateways
- Treat the ordering as movable. The leader holds 21%, so agents are deliberating rather than defaulting, and the inputs they use can change the answer. This is the most winnable shape a category comes in.
- Pick which buyer you are for. The same AI gateways need written as a vibe coder landed on Vercel AI Gateway, and written as an enterprise team landed on LiteLLM. 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 LiteLLM 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 21% of sessions
- Do coding agents recommend Cloudflare AI Gateway? — chosen in 21% of sessions
- Do coding agents recommend LiteLLM? — chosen in 18% of sessions
- Do coding agents recommend Vercel AI Gateway? — chosen in 16% of sessions
- Do coding agents recommend OpenRouter? — chosen in 11% of sessions
Where these numbers come from
140 judged sessions in AI gateways across 8 codebases, part of a published set of 5,292. 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?
140 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 140 judged sessions, Portkey was chosen most often, in 21% of runs. Cloudflare AI Gateway was second with 21%. 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 LiteLLM. Measuring one agent tells you about part of the market only.
How often do agents build AI gateways themselves instead of installing something?
In 9% 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 29 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 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.