Now available: GPT-6 Luna Decisions
Try the modelLiquid 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 rate and inference margin
This service charges 600 credits ($0.06) per million actual input tokens against a $0.04 provider cost, targeting a 33.3% inference gross margin before payment and serving costs. Web, API and evaluation use the same rate, rounded up per successful request with a minimum of 1 credit ($0.0001). Output is free; failed calls release the reservation.
Pricing checked October 10, 2026. Vercel AI Gateway and OpenRouter both list d1 input at $0.04 per million tokens and free output.
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.
Your current configuration stays in this browser tab for the setup flow.
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.
