Routers pick from a menu. A compiler builds the plan: every model measured on your work, every request compiled to the lowest price your quality bar allows.
“Is this review positive, negative, or neutral? ‘Crashed twice, support never replied…’”
Less than it used to be — gateways now ship auto-routers, and that is exactly the point. Prediction is becoming free. A router picks a road; a compiler designs the route. Others predict which model should work. Potion measures what actually clears your bar — and signs the receipt.
Access stopped being scarce the day gateways shipped. Judgment did not. That is the layer Potion sells — measured per kind of work, enforced as a floor — and it works the same over any gateway or provider underneath.
Potion compiles it from three things: your traffic’s actual kinds of work, your quality bar, and the measured frontiers. It ships as a model id — potion/your-org — and as a document you can read: every kind of work, how it is executed, the measured quality and price behind the choice.
The compiler emits the simplest plan that clears your bar. Today that is usually one model per kind of work: we measured the clever shapes — referee juries, run-and-test, escalate-when-unsure — on the same requests, and every one of them lost. The gain is across requests, not inside one. When that changes, the plan changes and you do not.
It is versioned. When a new model ships or a measurement moves, Potion recompiles, mints the next version, and writes what changed on it — and every receipt names the version that served it. Roll it back, audit it, set boundaries on it.
You never hand-assign a model. You change what you want — the floor, the ceiling, a ban — and Potion recompiles. The intelligence stays on our side of the API.
| kind of work | compiles to | quality | $/1K |
|---|---|---|---|
| extraction | ·small | 0.977 | $0.05 |
| code-gen | ·mid | 0.917 | $0.55 |
| summarization | ·small | 0.850 | $0.01 |
| rag-answer | ·mid | 0.941 | $0.12 |
v3 → v4 · a new model cleared the bar on extraction — estimated at your mix: saves another 11%
Five models writing code to specification — scored by running their code, not by opinion. The quality difference across this table is 2.1 points in a hundred. The price difference is 271-fold.
This is why the compiler pays: most kinds of work are served from the bottom row, a few genuinely need the top one, and only a measurement can tell them apart.
measured 2026-08-21 · frontier v4 · retrieval-hostile suite · scored by execution · error bars on the full table in the docs
↑ the compiled pick — 97.8% of the top row's quality at 1/271st the price. The name? That's the product.
Figure 3. The code-gen-hard frontier, measured 2026-08-21, 30 items scored by execution (90 graded runs per point). Bars show cost per 1,000 requests · teal = what a 0.95 quality floor actually buys · 2 further frontier points measured below that floor and are not drawn
Every model the compiler is allowed to emit must first earn its place through measurement — the same private exams, per kind of work, with confidence intervals and dates on every point. New models are auditioned the week they ship. Only what dominates on quality, cost and speed at once is published to the frontiers your plans are compiled from.
The engine also tests the clever ideas, so you never pay for one that does not work. It spent two weeks trying to beat the single-model plan with multi-model combinations — pre-registered, budget-capped — and every attempt lost to the best single model. We published all five losses. If the model market ever changes shape so a combination pays, the same machinery will find it, measure it, and only then serve it.
Why this is hard to copy: the measured corpus, the live receipts, and the replay engine live in one place, and the corpus compounds every week — including the negatives. A compiler that only reports wins is indistinguishable from one that does not measure.
Measured options for one kind of work, error bars included. Pick a rule, drag the slider, and you are running the same selection the compiler makes in production — including its refusal to answer when nothing measured qualifies.
Real measured points, quoted from the committed frontier; hover any point for its name and numbers. The cheapest row costs under a cent per 1k and measures 0.50, a coin flip, which is why the compiler 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.
A compiler that spends your money has to be trustworthy before it is clever. So the serving path is written to fail closed: the server will not start if a frontier names a model it cannot serve; a frontier cannot be republished if it regresses; a request is refused before a budget is crossed, not after; and nothing is ever served from a number that was not measured.
Priced so we only win when you do: model costs pass through at cost, and Potion earns a share of the savings your own receipts verify. If it saves you nothing, it earns nothing above cost. No minimum. You bring no provider accounts and no keys — Potion buys from every provider at once, which is what lets it compile from the whole market rather than the one account you happened to open.
Kind of work, strategy, policy, provenance: what answered and why, on the response itself.
Boot refuses a frontier that names an unservable model. A regression cannot be published. No measurement, no plan.
A hard cap is enforced before the money is spent, within seconds of being crossed, never after.
Each frontier point carries its sample size, its 95% interval, and the day it was measured.
Every pick the compiler emits is re-measured on fresh tasks; a model that drifts is caught before it costs you.
OpenAI chat completions, including streaming and tool calls. Point your client at Potion; keep everything else.
One click opens a chat with the question already written: what Potion does, and what you should check before believing any of it.
The question is copied to your clipboard too, since Gemini will not take it from a link.
Point a client at Potion and watch every decision arrive with the answer.