Open AI Decisions API is coming soon.
LIQUID AI / VERCEL AI GATEWAY
Liquid AI's decision model for classification, routing and scoring. Send one shared state with typed questions and get structured answers with probabilities instead of generated prose.
Vercel AI Gateway currently lists Liquid d1 as free (checked September 30, 2026). This site charges its minimum 1 credit for each successful request.
Context window
32,000
tokens · Vercel listing
Vercel input price
$0 / 1M
per million input tokens · current public listing
Vercel output price
$0 / 1M
per million output tokens · no generated output
Site token rate
0
credits per million input tokens · 1-credit minimum per successful call
/typesafe/v1/systemone
Liquid d1 is available through Vercel AI Gateway's TypeSafe-compatible endpoint. It accepts the same state and typed questions as Jev and returns answers keyed by the same question IDs. The existing playground can switch between the two models without changing the input format.
STATE → DECISION
Ask a yes/no question (noul), choose from named options, or score against an ordered scale. Answers include probabilities for your application to interpret; d1 does not generate explanatory prose.
Vercel lists a 32,000-token context and no generated output tokens. This site's shared workbench accepts text or JSON state, up to 8 questions and 32 KiB per request. Check the live model page for current availability and price.
This page opens the existing Jev workbench with Liquid d1 selected. Keep the state and questions fixed, then switch the model to compare the returned choices, scores and probabilities. The browser draft is saved separately from the main playground.
What do you want to decide?
Choose a task to load its input and rules. Loading examples uses no credits.
We reserve this budget before the model runs, then charge actual usage and return the difference. Failed calls are refunded.
New account? Receive 100 credits once. Short requests typically use 1 credit; longer inputs can use more.
Draft saved in this browser · Your draft will be restored after sign-in.
ILLUSTRATIVE EXAMPLE · NO CREDITS USED
“I was charged twice this morning. Please refund the duplicate payment today.”
Choice
Billing
Route to the billing queue
Yes / no
96%
Probability of an urgent request
Score
2.8 / 3
Urgency on a 0–3 scale
Static illustration of the output format. Values are not a live model response or a measure of accuracy.
Capture A, change the model or questions in the workbench, then capture B. Both versions use identical states.
Capture A from the current workbench model and rules. Change the model or questions, then capture B. Import up to 25 labeled cases and compare both versions. The dataset state replaces each captured state.
This simulates a policy, not accuracy. Noul uses max(P(yes), P(no)); Choice and Score use your selected signal. Validate thresholds on labeled cases.
Total budget across both versions and all cases. Each request reserves its own allowance, then settles actual usage and refunds the remainder. Stopping preserves charges for completed requests.
New account? Receive 100 credits once. Short requests typically use 1 credit; longer inputs can use more.
Each successful comparison request uses credits. Review the total budget before starting. Requests run sequentially; stopping keeps charges for completed requests. Export includes rules, cases, results and errors. Closing this page stops the comparison.
Use a site API key with Jev AI Model's /v1/systemone endpoint. Select liquid/d1 as the model. The server forwards the request to Vercel AI Gateway using VERCEL_AI_GATEWAY_API_KEY; the Gateway key stays on the server.
The public Vercel listing currently shows $0 input and output cost. At a zero upstream price, a 50% gross-margin token rate has no nonzero cost base: the token rate is 0 credits per million and this site applies its 1-credit successful-request minimum. If Vercel changes the price, recalculate the rate from the paid upstream cost before updating billing.
// Server-side JavaScript (Node 20+ or Bun). Set JEV_API_KEY.
const response = await fetch("https://jevaimodel.net/v1/systemone", {
method: "POST",
headers: {
"Authorization": `Bearer ${process.env.JEV_API_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"model": "liquid/d1",
"state": "I was charged twice for order A-4471. Please refund the duplicate payment.",
"questions": {
"route": {
"type": "choice",
"instructions": "Which team should handle this ticket? Use other when no option fits.",
"criteria": {
"billing": "Payments, charges and refunds",
"technical": "Bugs and product errors",
"account": "Login and account access",
"other": "None of these teams"
}
}
}
}),
});
const body = await response.json();
if (!response.ok || body.code !== 0) throw new Error(body.message);
console.log(body.data.result.answers);
console.log(body.data.creditsUsed);Credits are worth $0.0001 each at the listed pack rate. For a nonzero upstream cost, a 50% gross margin requires a selling price equal to twice that cost: credits per million = upstream dollars per million × 20,000. For reference, Jev at $0.042 per million input tokens would require 840 credits per million for 50%; its current 600-credit rate corresponds to a 30% gross margin. Liquid d1's current $0 listing instead bills at the 1-credit request minimum.