Now available: GPT-6 Luna Decisions

Try the model

UPSTAGE / OPENROUTER

Solar Decide Flash

Upstage’s low-latency Solar Decide variant is built on Solar Mini 4. Classify, route and score shared text or JSON with structured answers and probabilities through the same playground and API as Jev.

upstage/solar-decide-flash
TextJSON

New accounts get 100 credits. The playground and API share one balance.

Context window

524,288

tokens · provider-listed maximum

OpenRouter input price

$0.05 / 1M

per million input tokens

OpenRouter output price

$0 / 1M

output tokens are free upstream

This site's input rate

720

credits per million input tokens · minimum 1 per successful request

JEV / SYSTEM ONE

Uses the Jev decision playground

Send model, state and a keyed questions object to /v1/systemone, then read data.result.answers. Text, JSON objects and arrays use the existing Choice, Score and Noul contract through OpenRouter.

SPAN / NOUL

How it differs from Span

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.

Three structured answer types

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.

choicescorenoul

OpenRouter lists a 524,288-token provider context. This platform accepts up to 8 questions and 32 KiB for text plus questions. Choice accepts 2–26 options, Score accepts 2–10 ordered levels, and Noul accepts optional true/false criteria. Image input is not supported.

Uses OpenRouter’s decisions endpoint with model upstage/solar-decide-flash. Upstage serves this model through its System One API. The published context is the provider maximum; platform request limits still apply.

Input and output credits

OpenRouter currently lists $0.05 per million input tokens and $0 for output. The playground, API and evaluation charge 720 credits per million actual input tokens, rounded up with a minimum of 1 credit per successful request. Provider input usage includes questions. Output is free; failed requests release the reservation.

max(1, ceil(input_tokens × 720 / 1,000,000))

A successful request with 1,000 input tokens costs 1 credit; 5,000 input tokens cost 4 credits. Output tokens add no charge. Failed calls release the credit reservation.

Verified October 8, 2026: provider metadata and synthetic calls with text, object and array state, all three answer types, 8 questions, 26 Choice options, 10 Score levels, and Noul without criteria. These are interface compatibility checks, not an accuracy benchmark or latency guarantee.

Try Solar Decide Flash with your own state

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.

Solar Decide Flash ↗Span · behavior evaluation ↗

OpenRouter provider context: 524,288 tokens. This platform: 8 questions, 2–26 Choice options and 32 KiB text plus questions. Text and JSON only; image input is not supported.

Text or JSON shared by all questions; attach images below on vision models.

Images 0/4

Text / JSON only

Embedded images stay in this page until you leave or refresh. Saved configurations and history keep image metadata; API URL references are retained and may expire.

Advanced question settings

Questions 1/8

Which team should handle this ticket? Use other when no option fits.Choice

Options

Maximum credit budget: 1 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.

100 welcome credits · one balance for web & API

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.”

One input → structured decisions

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.

Web runs and saved configurations are private to your account. API history stores usage only. Embedded image pixels are omitted from drafts, configurations and history; metadata and missing-image counts remain. Add the images again before replaying. API URL references may expire. API setup exports local-file code without storing pixels.Usage ↗

Your draft will be restored after sign-in.

Use the same decision API

Send model, state, and questions to Decisions API's /v1/systemone endpoint with an API key created here. Set model to upstage/solar-decide-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": "upstage/solar-decide-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);