Now available: GPT-6 Luna Decisions
Try the modelCLOUDFLARE / OPENROUTER
Cloudflare’s compact decision model checks short text, JSON and images. Use it for screenshot classification, rules and yes/no checks.
cloudflare/clef-flashNew accounts get 100 credits. The playground and API share one balance.
Effective text-state limit
~2,000
first text-state tokens read upstream · platform cap: 2,000 UTF-8 bytes
OpenRouter input price
$0.038 / 1M
per million input tokens
OpenRouter output price
$0 / 1M
output tokens are free upstream
This site's input rate
600
credits per million input tokens · minimum 1 per successful request
JEV / SYSTEM ONE
Uses the same decision endpoint and typed answers as Jev. Send text or JSON in state and optional image attachments in images; alternatively use text/image_url content parts in state. All questions share the supplied images.
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.
Text state: 2,000 UTF-8 bytes after JSON serialization. Upstream currently reads about the first 2K text-state tokens. Text, JSON and image inputs are supported. Add up to 4 PNG, JPEG or WebP images (4 MiB each, 8 MiB total, 16 MP each); complete image requests may use 13 MiB, while text and questions stay within 32 KiB. The text-state cap does not include image bytes. Up to 8 questions; Choice: 2–255 options; Score: 2–10 ordered levels.
Image input verified through OpenRouter on October 6, 2026 with red/blue fixtures, four images and Choice, Score and Noul answers. This service embeds downloaded images because upstream rejects remote image URLs.
OpenRouter charges $0.038 per million input tokens and $0 for output. This service charges 600 credits per million input tokens on web, API and evaluation, rounded up per successful request with a minimum of 1 credit. Billing uses the provider’s total input usage, including questions. Output tokens add no charge; failed calls release the reservation. Actual input usage includes processed images; image bytes are not billed as text tokens.
max(1, ceil(input_tokens × 600 / 1,000,000))
A successful request with 1,000 input tokens costs 1 credit; 5,000 input tokens cost 3 credits. Output tokens add no charge. Failed calls release the credit reservation.
Verified October 4, 2026 against official OpenRouter prices and live requests: text, object and array state; 8 questions; 255 Choice options; 10 Score levels; Noul without criteria; and long-state marker probes. These checks verify the API contract and input limits, not model accuracy. Image input verified October 6, 2026 with contrasting red/blue fixtures, four-image requests and all three answer types through OpenRouter. Remote upstream URLs are rejected; this service embeds downloaded images.
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.
Clef reads only about the first 2K text-state tokens; this service caps serialized text state at 2,000 UTF-8 bytes. Images are validated separately.
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-flash; 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-flash",
"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);