The right model(s) for every request.
six real decisions from the measured frontier — not a simulation · click a row for its receipt
No. A gateway answers how do I call any model? Potion answers which model does this request deserve? Those are different layers, and the second one is where the money is.
Access stopped being scarce the day gateways shipped. Judgment — measured per kind of work, stated with its error bars, enforced as a floor — is the scarce layer. That layer is Potion, and it works the same over any gateway or provider underneath.
Five models writing code to specification — scored by running their code, not by opinion. The quality difference across this table is two points in a hundred. The price difference is two hundred and seventy fold.
This is why routing pays: most requests deserve the bottom row, a few genuinely need the top one, and only a measurement can tell them apart.
measured 2026-08-20 · retrieval-hostile suite · scored by execution · error bars on the full table in the docs
↑ the routed pick — 99% of the top row's quality at 1/270th the price. The name? That's the product.
bars show cost per 1,000 requests · teal = what a 0.95 quality floor actually buys
the price range across five models doing the same measured work — quality within two points in a hundred
of the most expensive model's quality, from the pick our measurements route to, at 1/270th the price
the measured saving across a typical traffic mix, with a quality floor enforced on every request
per 1,000 requests — the routed pick, name withheld
per 1,000 requests — the model most teams would have picked
Both rows did the same held-out work and were scored the same way — by running what they wrote. The gap between them is not quality. It is the cost of choosing without measuring.
There are hundreds of AI models. They differ enormously in price and only sometimes in quality — and which one is best changes every few weeks as new ones ship.
Almost nobody re-checks. A team picks a model once, wires it in, and keeps paying that price on every request forever — including the thousands of easy ones a model costing a fraction as much would answer just as well.
Every bar does the job. The dearest costs 172× more than the cheapest and measures 1.8 points better out of 100. Most companies are on a bar near the bottom of this chart for every request they send, because they picked one model and moved on.
This is not a marketing calculator. It runs Potion's real selection rule over Potion's real measurements, live, as you drag. Raise the quality bar and watch categories drop out — including the ones we would refuse to take money for.
$50k a month is $600k a year.
Measured quality, 0 to 1 — the floor Potion is never allowed to go below.
Some rows sit at or near zero and that is the model working. On multi-step reasoning the cheap options measure 0.46 against 0.98 for the expensive one — so Potion pays for the expensive one and saves you nothing there. Half the categories carry most of the saving; being told which half is the product.
Computed live from Potion's own measurements, against a baseline of running the highest-quality model on everything. It weights every kind of work equally — a real bill depends on your traffic mix, which is the first thing Potion measures once you connect.
The router is a week of engineering. The evidence it routes on is not — and it is the half that compounds.
Every model, on every kind of work, graded against known answers — and re-graded when a new one ships. That corpus is the product, and it is worth more every week than it was the week before.
Public leaderboards rank models on average, across work you do not do. Potion measures each model on each kind of job, and keeps the error bars — the only comparison that can tell you what to send where.
You start on measurements of your kind of work. As your own traffic accumulates, the routing retunes to it specifically — so the saving grows without you changing a line or paying more attention.
Before anything is chosen, the request is sorted into a kind of work — writing code, summarising, pulling data out of a document, and so on. Each kind has its own answer about which model is best.
cluster = code-genYou say what matters: never go below this quality, or never spend above this much, or never take longer than this. Potion holds a measured map of every option — single models and combinations of them — and picks the best one that obeys your rule.
policy = min_cost · qualityFloor 0.80The response carries what it chose, why, and which measurements it relied on. If Potion had nothing measured for your request, the receipt says that too rather than quietly guessing.
x-frontier-trace: cluster=code-gen;strategy=6efe8a56;frontier=v2;policy=min_cost;fallback=0A cheap model answers and reports how sure it is. Only when that confidence falls below a measured threshold does the request go on to a stronger one. Most traffic never reaches the expensive model at all — so the combination can land at the top of the measured quality range while costing a fraction of sending everything to the strong model.
Potion measures those combinations exactly the way it measures single models: the same held-out items, the same known answers, the same error bars. A mixture earns a place on the map or it does not appear on it.
There is nothing for you to assemble. You set the same rule you would set anyway — stay above this quality, stay under this cost — and if a combination is the best way to honour it, that is what serves your request. The receipt names whatever answered.
There are far more useful combinations than there are models, and almost none of them have been measured by anyone. That is the dimension this company is named for.
Every quality score Potion reports comes with a margin of error, the way a poll does. When two models are close enough that the measurement cannot separate them, Potion says they are tied instead of inventing a winner — and then picks the cheaper one.
Too close to call. Those two bars overlap almost completely, so the quality difference is not real evidence — while the cheaper one costs 46% less and answers 1.9× faster. A leaderboard would rank them and let you overpay for the gap.
Measured options for one kind of work, spanning a hundredfold price range. Pick a rule, drag the slider, and you are running the same selection the router runs in production — including its refusal to answer when nothing measured qualifies.
or-deepseek-v4-flash-0731 — quality 0.98 ±0.04, $0.0304 per 1k requests, p95 9,702 ms.
Real measured points, quoted from the committed frontier — hover any dot for its name and numbers. The cheapest row costs under a cent per 1k and measures 0.50, a coin flip, which is exactly why the router will not send reasoning work there: cheap only wins where the measurement clears your floor. Try latency_bound at 2,500 ms — the answer changes.
Usage-based today. The direction of travel is to charge against measured savings — the only pricing that stays honest when the whole point of the product is spending less, and the only one that makes the bill fall when we do our job badly.
Customers bring no accounts and no keys. Potion buys from every provider at once, which is also what lets it reach the whole market rather than the one account a customer happened to open.
Point your client at Potion. Nothing else about your app changes.
Each request goes where the evidence says it should, not where habit does.
A line their traffic is never allowed to fall below, enforced per request.
What was chosen, why, and which measurements it relied on.
The request is refused before the money is spent, never after.
Spend is attributable to decisions you can audit, line by line.
Point a client at Potion and watch the routing decisions arrive with the answers.