Coming soon: OpenAI Decisions API
Explore the comparisonCONVAI INNOVATIONS / VERCEL AI GATEWAY
Convai Innovations’ System One evaluation model makes structured decisions in a single forward pass. Classify shared state, route requests, score a rubric, or check a yes/no condition through Vercel AI Gateway, without generating free-form text.
convaiinnovations/layaNew accounts get 100 credits. The playground and API share one balance.
Context window
8,192
tokens · provider-listed maximum
Vercel input price
$0 / 1M
promotional price through October 31, 2026
Vercel output price
$0 / 1M
promotional price through October 31, 2026
Platform price
1 credit
$0.0001 per successful request · output adds no charge
JEV / SYSTEM ONE
Laya uses the shared model, state and questions interface. This service maps Noul to the Gateway’s boolean question, converts the returned probability to noul, and normalizes token usage. Choice and Score retain their structured answers, so the same recipes, evaluation datasets and API code work here.
SPAN / NOUL
Span accepts only Noul behavior questions and requires text or a specific input/output conversation object. This model also accepts Choice and Score questions, with text, generic JSON objects, or arrays as state. Use the Jev playground for this broader decision contract.
Choice returns a named option and its probability distribution. Score returns a value on an ordered scale with probabilities. Noul returns the probability of a yes/no condition. Multiple questions share the same state.
Vercel lists an 8,192-token context window. This service accepts text, JSON objects or arrays as state, up to 8 questions and 32 KiB per request. Laya Choice accepts 2–100 named options: live requests accept 100 and reject 101. Score uses 2–10 ordered levels. State and questions must also fit the provider’s context budget.
Vercel currently routes the hosted convaiinnovations/laya model to Boundless. The context and pricing shown here describe this hosted API entry; checkpoint-specific local benchmark results should be evaluated separately.
Laya uses the platform’s minimum charge: 1 credit ($0.0001) per successful request on web, API and evaluation. Input has a 0-credit per-token rate and output adds no charge. Failed calls release the reservation. Vercel currently lists input and output as free promotional pricing ending October 31, 2026; this platform price is a separate service charge.
max(1, ceil(input_tokens × 0 / 1,000,000))
A successful request with 1,000 input tokens costs 1 credit; 5,000 input tokens cost 1 credits. Output tokens add no charge. Failed calls release the credit reservation.
Checked October 2, 2026 against the official Vercel listing and live requests for Choice, Score and Noul. This checks API compatibility, not model accuracy. Recheck upstream pricing when the promotion ends.
The Jev workbench below starts with this model selected. Try a recipe, edit the state and questions, or export API code. This page stores its browser draft separately from other model pages and the main playground.
What do you want to decide?
Choose a task to load its input and rules. Loading examples uses no credits.
Laya supports Choice, Score and Noul through Vercel AI Gateway. Context: 8,192 tokens. Choice: 2–100 options. Every successful web, API or evaluation request costs 1 credit; output adds no charge.
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.
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.
Send model, state, and questions to Decisions API's /v1/systemone endpoint with an API key created here. Set model to convaiinnovations/laya; answers are in data.result.answers and token usage is in data.result.usage.
// Server-side JavaScript (Node 20+ or Bun). Set DECISIONS_API_KEY.
const response = await fetch("https://decisions-api.dev/v1/systemone", {
method: "POST",
headers: {
"Authorization": `Bearer ${process.env.DECISIONS_API_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"model": "convaiinnovations/laya",
"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);