Decisions APIText in. Decisions out.
Decisions API · MANY MODELS. ONE DECISION WORKFLOW.
Decisions APIText in. Decisions out.
Explore decision models in one place with Decisions API. Compare Jev, Liquid d1, Kev, Solar, Tev1, and Span in the playground, then use the API to classify, score, and route text. New accounts receive 100 credits.
Browse all 7 modelsTry the playground
- Structured answers
- Multiple questions at once
- Probabilities included
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.
TypeSafe
Choice · score · noul
Jev 1.13
Support triage and agent routing
Jev's structured decision model. Ask typed questions about shared state and get answers with probabilities.
Capability notes: Choice, Score and Noul outputs
Platform price
600 credits / 1M input tokens
MODEL ID
`typesafe/jev-1.13`
API alias: `jev-latest`
Jared Palmer
Choice · score · noul
Kev 4B
Compact-model classification and scoring
A compact 4B decision model for typed answers and probability estimates.
Capability notes: 8,192-token context
Platform price
600 credits / 1M input tokens
MODEL ID
`jaredpalmer/kev-4b`
Respan
Noul behavior
Span-01 Lite
Lightweight behavior checks
A lightweight Span behavior model for Noul yes-or-no judgments.
Capability notes: Noul only; conversation input
Platform price
1 credit / successful request
MODEL ID
`respan/span-01-lite`
Minimum 1 credit per successful request. Output tokens are not charged.
01 / WORKBENCH
Decisions API playground
Preview a task in Decisions API, choose a model, and edit the input. Sign in to run it with your credits. New accounts receive 100 credits once.
Workbench
Examples24Decision workbench
What do you want to decide?
Support routingAgent routingCitation verificationContent moderationLead scoringLLM guardrail
Choose a task to load its input and rules. Loading examples uses no credits.
ModelJev 1.13 ↗Span · behavior evaluation ↗
Shared state
Text or JSON evaluated independently by every question.
Advanced question settings
Questions 1/8
Add question
Which team should handle this ticket? Use other when no option fits.Choice
Question IDAnswer type
What should the model decide?
Options
\+ Add option
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.
Sign in to run100 welcome credits · one balance for web & API
Draft saved in this browser · Your draft will be restored after sign-in.
Use this configuration via API →
Your current configuration stays in this browser tab for the setup flow.
ResultsRequestResponseCode
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.
##
Your draft will be restored after sign-in.
Sign in to run
Designed for developers
One Decisions API integration. Multiple models.
Move from the Decisions API playground to your backend with the same state and question structure. Choose a supported model, create an API key, and use the generated cURL, JavaScript, or Python example. The shared endpoint keeps your integration familiar as you explore different decision models.
Send requests to Decisions API with a server-side Bearer token. Successful responses contain structured answers and usage information. Check the response status, keep the request identifier for troubleshooting, and handle errors explicitly. Your application decides whether the result should route a ticket, request a review, or trigger the next operation.
Decisions API uses one balance for playground, API, and evaluation calls at the same per-model rates. A budget is reserved before each call; successful calls settle actual input usage, and failed calls are refunded. Review the request and model rate before integrating.
1. 1. Choose a model 2. 2. Create an API key 3. 3. Run from your server
Start integration →API reference ↗
POST /v1/systemone typesafe/jev-1.13 · liquid/d1 · upstage/solar-decide · togethercomputer/tev1-4b-experimental · jaredpalmer/kev-4b
Copy
// 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": "typesafe/jev-1.13",
"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);Pricing
One credit balance for web, API and evaluation. New accounts receive 100 credits.
$1 = 10,000 credits on every pack. Credits do not expire. Pay once, with no subscription. Successful calls start at 1 credit; actual input usage determines the charge. Site input rates per million tokens: Jev / Kev $0.06, Solar Decide $0.072, and Span-01 $0.03. Output tokens are not charged.
Starter
$10
For your first workflows and integration.
Buy now
Recommended
Pro
$100
For regular use and repeated evaluations.
Buy now
Volume
$1,000
For higher usage at the same unit rate.
Buy now
Estimate your credit use
Estimate with your average input tokens, including state and questions. Each request is rounded up separately.
ModelNumber of requestsAverage input tokens / requestCredit pack
Credits per request
1
Estimated total credits
10,000
Credit value at selected pack rate
$1.00
max(1, ceil(input\_tokens × 600 / 1,000,000))
All live calls use credits, including web and evaluation. Minimum 1 credit per successful request; output tokens are not charged. Jev, Kev and Tev1: 600 credits/million input tokens; Solar Decide: 720; Span-01: 300. Liquid d1 and Span-01 Lite: 1 credit per successful request. $1 buys 10,000 credits. Failed calls are refunded. Estimates exclude taxes.
Questions about Decisions API
Learn how Decisions API brings multiple decision models together, how credits work, and how to move from the playground to an API integration.
Is Decisions API a chat assistant?
Which models can I use with Decisions API?
Can I try Decisions API before buying credits?
What should I put in the input state?
Can I treat confidence as measured accuracy?
How do I integrate Decisions API into my app?
Guides & model resources
Explore model guides and comparisons after choosing your first model.
Model guides
Jev 1.13Liquid d1Solar DecideTev1 4B ExperimentalKev 4BSpan-01Span-01 Lite
Comparisons
BenchmarksJev vs djevJev vs LayaJev vs Liquid d1OpenAI Decisions API vs JevJev vs OpenJevJev vs SemIf