Coming soon: OpenAI Decisions API
Explore the comparisonLiquid AI · hosted decision model
Liquid d1 evaluates shared state against typed yes/no, choice, and score questions, then returns structured probabilities for classification, routing, and scoring.
A decision interface the Jev playground can use
Both models work with one shared state and typed questions. This site maps Jev's Noul question to Vercel's boolean type and normalizes the response and token usage on the server, so the existing playground can run d1 with the same examples and controls.
Credit charge at a 50% gross margin target
At a $0 model-token cost, the 50% gross-margin formula (cost ÷ 0.5) gives $0 per million tokens, or 0 credits per million at $0.0001 per credit. The shared billing rule has a one-credit minimum per request, so a successful d1 call currently uses at least 1 credit. That floor means the actual model-token margin is above the 50% target at today's $0 listed rate; gateway, payment, and serving costs are not included.
Pricing checked September 30, 2026. Vercel currently lists d1 input and output at $0 per million tokens.
Use the shared decision workbench with d1 selected, then switch to Jev to compare the same state and questions.
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.
