Now available: GPT-6 Luna Decisions
Try the modelCLOUDFLARE / OPENROUTER
Cloudflare’s mixture-of-experts decision model is based on Qwen3-Omni-30B-A3B, with 30B total and 3B active parameters. Classify, route and score text, JSON or images with typed answers.
cloudflare/clef-omniNew accounts get 100 credits. The playground and API share one balance.
Context window
65,536
tokens · provider-listed maximum
OpenRouter input price
$0.15 / 1M
per million input tokens
OpenRouter output price
$0 / 1M
output tokens are free upstream
This site's input rate
2200
credits per million input tokens · minimum 1 per successful request
JEV / SYSTEM ONE
Send model, state and keyed Choice, Score or Noul questions to /v1/systemone. This service calls OpenRouter’s Decisions endpoint, validates answers and settles the shared web, API and evaluation credit balance.
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.
Provider context: 65,536 tokens. This service accepts up to 8 questions, 2–255 Choice options and 2–10 ordered Score levels. Text plus questions must fit 32 KiB. Add up to 4 PNG, JPEG or WebP images: 4 MiB and 16 MP each, 8 MiB total, 13 MiB for the complete request.
Uses OpenRouter’s Decisions endpoint. Published context is the provider maximum; platform request limits still apply.
Upstream input is $0.15 per million tokens; output is free. Web, API and evaluation charge 2200 credits per million actual input tokens, including questions and processed images, rounded up per successful request with a minimum of 1 credit ($0.0001). Failed calls release the reservation.
max(1, ceil(input_tokens × 2200 / 1,000,000))
A successful request with 1,000 input tokens costs 3 credit; 5,000 input tokens cost 11 credits. Output tokens add no charge. Failed calls release the credit reservation.
Verified October 10, 2026 through OpenRouter: text, object and array state, all three answer types, 8 mixed questions, 255 Choice options, 10 Score levels, Noul without criteria and a long-state tail marker. Contrasting red/blue images and four-image requests also passed. Reported usage fits the reserved credit budget. These checks verify the API contract, not accuracy or a latency SLA.
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.
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 cloudflare/clef-omni; 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": "cloudflare/clef-omni",
"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);