Input price
Jev
$0.042 / 1M tokens
Liquid d1
$0.02 / 1M input tokens; output free
Jev uses the OpenRouter rate configured by this app. Vercel currently lists Liquid d1 input at $0.02 per million tokens and free output.
Provider price pagesJetzt verfügbar: GPT-6 Luna Decisions
Modell testenModel comparison · pricing checked Oct 19, 2026
Jev and Liquid d1 both evaluate shared state against typed questions. Their request and response semantics are compatible, while their gateway formats and current prices differ.
This app currently calls Jev through OpenRouter and Liquid d1 through Vercel AI Gateway. The shared playground can run the same state and questions against either model after a small server-side adapter maps Noul to boolean and normalizes usage.
Compare the operating details
Use the same examples to compare behavior. This page keeps the price snapshot separate from model-quality claims, which still need a labeled evaluation set.
Input price
Jev
$0.042 / 1M tokens
Liquid d1
$0.02 / 1M input tokens; output free
Jev uses the OpenRouter rate configured by this app. Vercel currently lists Liquid d1 input at $0.02 per million tokens and free output.
Provider price pages50% gross-margin credit rate
Jev
840 / 1M input tokens
Liquid d1
400 / 1M input tokens; platform charges 600
At $0.0001 per credit, a hypothetical 50% margin gives 400 credits/M for d1. The actual platform rate remains 600 credits/M, with a 1-credit minimum per successful request.
Decision output
Jev
Typed answers with probabilities
Liquid d1
Typed answers with probabilities
Both return boolean, choice, and score decisions. The adapter translates field names and token-usage casing; the Gateway response does not add a separate confidence field for Choice or Score.
Vercel evaluation APIPick a model with a shared test set
01
The site routes d1 to Vercel’s evaluation endpoint using the configured VERCEL_AI_GATEWAY_API_KEY.
02
The current Jev integration remains available; choose either model in the shared workbench without changing the question editor.
03
Run labeled examples through both models and compare false positives, false negatives, and calibration before you set production thresholds.
What changes when the provider changes?
Jev · OpenRouter Decisions API
The current integration sends the shared state and Jev’s typed questions to OpenRouter, then bills input tokens at the configured app rate.
Liquid d1 · Vercel AI Gateway
The gateway evaluation API accepts the same shared state and typed-decision workflow. This app maps its Noul question to boolean and converts the returned probability into the Jev playground answer shape.
Request and response compatibility
Sources and calculation
Liquid d1 pricing was checked on October 19, 2026: $0.02/M input and free output on Vercel AI Gateway. The hypothetical 50% gross-margin calculation gives 400 credits/M for d1 and 840 credits/M for Jev at $0.042/M upstream. Actual platform rates remain 600 credits/M for both, rounded up to at least 1 credit per successful request. At $0.0001 per credit, d1 has about a 66.7% inference margin before Gateway, payment and serving costs.
Führe d1 im gemeinsamen Entscheidungs-Workbench aus und wechsle dann zu Jev, um denselben Zustand und dieselben Fragen zu vergleichen.
Was möchtest du entscheiden?
Wähle eine Aufgabe, um Eingabe und Regeln zu laden. Beispiele zu laden kostet kein Guthaben.
Wir reservieren dieses Budget, bevor das Modell ausgeführt wird, rechnen anschließend den tatsächlichen Verbrauch ab und erstatten die Differenz. Fehlgeschlagene Aufrufe werden erstattet.
Neues Konto? Erhalte einmalig 100 Guthabenpunkte. Kurze Anfragen verbrauchen meist 1 Guthabenpunkt; längere Eingaben können mehr kosten.
Entwurf in diesem Browser gespeichert · Dein Entwurf wird nach der Anmeldung wiederhergestellt.
Die Konfiguration bleibt während der Einrichtung in diesem Browser-Tab.
BEISPIEL · KEIN GUTHABEN VERBRAUCHT
„Mir wurde heute Morgen zweimal Geld abgebucht. Bitte erstatte die doppelte Zahlung noch heute.“
Choice
Abrechnung
An das Abrechnungsteam weiterleiten
Ja / Nein
96%
Wahrscheinlichkeit einer dringenden Anfrage
Score
2.8 / 3
Dringlichkeit auf einer Skala von 0 bis 3
Statische Darstellung des Ausgabeformats. Die Werte sind weder eine Live-Modellantwort noch ein Maß für die Genauigkeit.