DecisionsApi
Coming soon: OpenAI Decisions APIExplore the playground

DecisionsApi · Many models. One decision workflow.

DecisionsApiText in. Decisions out.

Explore decision models in one place. Compare Jev, Laya, Kev, Solar, and Span in the playground, then use one API to classify, score, and route text.

Try the playgroundExplore the API
Structured answersMultiple questions at onceProbabilities included

Illustrative example

No credits used

Customer message

“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.

01 / Workbench

Decisions API playground

Choose a task, edit the input, define typed questions, and preview the request before you connect the same workflow to your backend.

New accounts receive 100 credits once.

1. State

Give the selected model the context shared by every question.

1/15

All questions share this context and are answered independently.

2. Questions

Define up to eight typed questions for the same state.

5 / 8

3. Run decision

Run the decision request.

Results

Click “Generate decisions” to see typed output with probabilities.

4. API request

Preview or copy the JSON shape to call the same endpoint from your app.

Results are returned in a structured format so you can connect them to your application logic.

02 / How it works

A decision is a useful interface for software.

Turn context and a bounded question into a result your code can inspect and use. The model provides the signal; your product controls the action.

01

Supply context

Provide a message, policy, record, or the application state the decision actually needs.

state = ticket.text
02

Define the question

Name the decision and its allowed answers, scale, or yes-and-no criteria.

questions = { intent, urgent }
03

Inspect the result

Read the typed answer, probability signals, model, usage, and request details together.

answer = result.answers.route
04

Choose the next step

Route, score, block, or request human review using the rules your application owns.

if result.urgent: escalate()

03 / Start from a real task

What you can build with Decisions API

Start with a decision your product already needs to make, then test clear and ambiguous examples before you automate the next step.

01

Route customer requests

Distinguish billing, technical, account, and other issues, then pass the selected label to your support system.

02

Choose an agent's next step

Classify whether a request needs a record lookup, a language model, a tool, or human review before anything executes.

03

Check claims against evidence

Place a claim beside a source passage and ask whether the supplied evidence supports, contradicts, or fails to establish it.

04 / Understand the output

How Decisions API turns context into an answer

Use a bounded question when your application needs a structured signal rather than another paragraph of generated text.

Choice

Select one label from a set you define. Use it for routing, categorization, filtering, and the next step in an agent workflow.

Score

Measure urgency, relevance, or completeness on an ordered scale whose boundaries are explicit and testable.

Noul / yes–no

Ask a focused yes-or-no question and use the returned probability with your own thresholds, rules, and review path.

Designed for developers

One Decisions API integration. Multiple models.

Move from the playground to your backend with the same state and question structure. Choose a supported model, send a server-side Bearer token, and receive structured answers with usage details.

Explore API docs
REST-ready
Structured responses
Manageable API keys

POST /v1/systemone

Server-side JavaScript · one request shape across models

POST /v1/systemone
const response = await fetch(
  "https://decisionapi.net/v1/systemone",
  {
    method: "POST",
    headers: {
      "Authorization": `Bearer ${DECISIONS_API_KEY}`,
      "Content-Type": "application/json"
    },
    body: JSON.stringify({
      model: "typesafe/jev-1.13",
      state: ticket,
      questions: { route: { type: "choice", criteria } }
    })
  }
);

05 / Understand the service

Start building with Decisions API

100 welcome credits

Create an account, load a recipe, review the budget, and run your first questions without buying a credit pack.

One wallet for every live call

Use the same credit balance across the playground, API, and evaluation workflows. Credits from purchased packs do not expire.

Usage you can inspect

Review request history and credit activity, and use request identifiers to connect API calls with their usage records.

Pricing

One credit balance for playground, API, and evaluation calls.

$1 = 10,000 credits on every pack. Credits do not expire. Pay once, with no subscription.

Starter

$10

Validate one real workflow, from the playground to your first API call

  • 100,000 credits, no expiry
  • Choice, score, and noul questions
  • Typed decision output
  • Probability and confidence results
  • Online playground
  • API key management
  • Usage and request history
Recommended

Pro

$100

Connect classification, routing, and safety decisions to a production product

  • 1,000,000 credits, no expiry
  • Choice, score, and noul questions
  • Typed decision output
  • Probability and confidence results
  • Online playground
  • API key management
  • Usage and request history

Volume

$1,000

For higher usage at the same unit rate

  • 10,000,000 credits, no expiry
  • Choice, score, and noul questions
  • Typed decision output
  • Probability and confidence results
  • Online playground
  • API key management
  • Usage and request history

Compare before you ship

Choose models with evidence from your own cases

Published benchmarks are useful background, but production choices should also reflect answer quality, uncertainty, latency, and cost on inputs that resemble your workflow.

Decision qualityResponse speedCost per decision
Explore model comparisons

Jev

Typed choices, scores, and yes–no decisions

01

Laya

English and multilingual decision workflows

02

Kev, Solar, and Span

Additional models for comparison and evaluation

03

Questions about Decisions API

Learn how multiple decision models, credits, structured outputs, and API integration work.