Compare GPT-6 Luna and other decision models in one playgroundExplore the playground

DecisionsApi · Focused questions. Predefined answers.

OpenAI Decisions APIGPT-6 Luna Decisions

Use GPT-6 Luna Decisions through this independent platform to classify, route, moderate, and score your inputs. Select predefined answers and receive typed probabilities through the same API used by our other decision models.

View the GPT-6 Luna Decisions model on OpenRouter
Define the expected answerCompare the same examplesInspect uncertain cases

This platform's output example

Static illustration

Customer message

“I was charged twice this morning. Please refund the duplicate payment today.”

One message → three useful decisions

Choice

Billing

Choose the support queue

Yes / no

96%

Signal for an urgent request

Score

2.8 / 3

Urgency on a defined 0–3 scale

Static illustration of this platform's decision format. These values are not a Luna response, a live result, or an accuracy benchmark.

01 / Try the workflow

Try GPT-6 Luna Decisions

This workbench starts with openai/gpt-6-luna-decisions selected. Enter text or JSON state, add Choice, Score, or Noul questions, then inspect the request and response or switch models to compare.

Check the selected model and the workbench's current usage terms before running a request.

Workbench

What do you want to decide?

Choose a scenario to load editable input and rules. Loading an example uses no credits.

Examples load into the current draft only; no configurations or run history are saved.

State

Give the selected model the context shared by every question.

Text

All questions share this context and are answered independently.

Questions

Define up to eight typed questions for the same state.

3 / 8

3. Run decision

Run the decision request.

Result preview

Subject: Charged twice again!! Hi — this is the SECOND month in a row I've been billed twice for the Pro plan. I already emailed last month and nobody replied. I run my whole business on this. If it's not refunded today I'm cancelling and disputing the charge with my bank.

↓One input → multiple structured decisions

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

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

02 / Plan the evaluation

Turn model research into a repeatable test.

A useful comparison starts with a fixed task, clear labels, and representative inputs. Use the same criteria when assessing any model your account can access.

01

Collect realistic inputs

Choose messages and records from the workflow, including short requests, missing context, and ambiguous examples.

state = ticket.text
02

Define a good answer

Write the allowed labels, scoring criteria, or yes-and-no rules before comparing model responses.

questions = { intent, urgent }
03

Review each result

Compare outputs against reviewed answers. Record errors, response time, and actual usage for each tested model.

answer = result.answers.route
04

Set the action boundary

Decide which results can trigger an action and which require more context or human review before deployment.

if result.urgent: escalate()

03 / Choose a useful task

Evaluate decisions your product already makes

OpenAI's announcement highlights classification, request routing, and an agent's next action. Use these related scenarios to prepare a practical test set for your OpenAI Decisions API Luna model evaluation.

01

Route customer requests

Define billing, technical, account, and other queues. Test messages that mention several issues and measure how often the intended queue is selected.

02

Choose an agent's next step

Compare record lookup, tool use, text generation, and human review. Include cases where a requested action lacks sufficient information or permission.

03

Check a claim against evidence

Pair a claim with a source passage and label it supported, contradicted, or undetermined. Keep missing evidence separate from a false claim.

04 / Choose the output

Three decision formats to test on this platform

GPT-6 Luna Decisions supports Choice, Score, and Noul. Define the options, rubric levels, or yes–no condition, then use the returned probabilities in your application.

Choice: one defined label

Set a small list of distinct options and describe where their boundaries fall. Include an other or review option when a case may not fit.

Score: an explicit scale

Describe each level of urgency, relevance, or completeness. Compare disagreements by level so a small difference is distinguishable from a serious error.

Noul: a focused yes–no check

Define what yes and no mean, then inspect the returned probability on held-out examples before choosing an automation threshold.

From evaluation to implementation

Call GPT-6 Luna Decisions through one API

Send openai/gpt-6-luna-decisions to this platform’s /v1/systemone endpoint using your platform API key. Keep the same state and questions format used by other decision models. This platform accepts up to 8 questions and a 32 KiB request body.

Read this platform's API docs
Server-side REST request
Typed decision answers
This platform's API key

POST /v1/systemone · this platform

JavaScript example · openai/gpt-6-luna-decisions

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: "openai/gpt-6-luna-decisions",
      state: ticket,
      questions: {
        route: {
          type: "choice",
          instructions: "Choose the support queue for this ticket.",
          criteria
        }
      }
    })
  }
);

05 / Understand the service

How do I start testing and estimate usage?

Testing credits included

Create an account, check your available testing credits, and try real classification and scoring cases before choosing 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.

Plans for this independent platform

These plans cover this platform's services and supported models. Choose a plan for your testing and integration needs; the amounts shown are not OpenAI Luna pricing.

API calls use this platform’s credits. Luna is served through OpenRouter, subject to provider availability. Plans here do not grant a separate OpenAI API account or direct OpenAI access.

Model access and billing

OpenAI’s Decisions API is in public beta. This platform provides model access through its unified API; check the current directory and your account access for available models and question types. Credit packs fund this service and do not add credit to an OpenAI account.

Starter

$10

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

  • 100,000 credits, no expiry
  • 1 workspace
  • 3 concurrent requests
  • Standard speed
  • Choice, score, and noul questions
  • Typed decision output
  • Probability and confidence results
  • Online playground
  • API key management
  • Email support
Recommended

Pro

$100

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

  • 1,000,000 credits, no expiry
  • Unlimited workspaces
  • 10 concurrent requests
  • Fast lane
  • Choice, score, and noul questions
  • Typed decision output
  • Parallel questions per request
  • API access
  • Usage and request history
  • Priority support

Enterprise

$1,000

For multiple workspaces, team collaboration, and custom production integrations, with 10% extra credits

  • 11,000,000 credits (10% extra included)
  • Everything in Pro
  • Unlimited concurrency
  • Dedicated fast lane
  • Team workspaces and collaboration
  • Custom integration support
  • Security and permission guidance
  • Dedicated support
  • Priority production processing
  • Product roadmap feedback

Compare on your own data

Build an evidence-based model shortlist

Start with the models available here, then apply the same reviewed test set to other models you can access. Track decision quality, response time, and actual cost without treating different providers' probability values as interchangeable.

Quality on reviewed examplesMeasured response timeActual cost per decision
Explore available model comparisons

Jev

Establish a baseline for choice, score, and yes–no tasks

01

Laya

Compare results using the same inputs and decision criteria

02

Kev, Solar, and Span

Add available models and inspect their supported question types

03

OpenAI Decisions API

Compare GPT-6 Luna using the same inputs and decision criteria

04

OpenAI Decisions API Luna model questions

Understand the announced capabilities, prepare a useful evaluation, and check which integration fits your workflow.

What is the OpenAI Decisions API Luna model connection?

GPT-6 Luna Decisions is GPT-6 Luna served through OpenAI’s Decisions API. OpenRouter lists it as openai/gpt-6-luna-decisions, with text and image inputs and Choice, Score, and Noul outputs. This platform calls it through /v1/systemone.

Can I call Luna with this platform’s plan?

Yes. Use your platform API key and openai/gpt-6-luna-decisions at /v1/systemone. API calls consume platform credits and depend on provider availability. This does not create an OpenAI account or grant direct access to OpenAI’s API.

Which models can I actually test in this workbench?

This page selects GPT-6 Luna Decisions by default. You can switch to Jev, Clef, PPLX Decider, Liquid d1, Kev, Solar, Span, and other available decision models. Span supports Noul only; check the selected model’s supported question types.

How should I compare a Luna model with another model?

First verify that you have access to the intended model and its documented API. Prepare a fixed set of representative inputs with reviewed answers, then test each model against the same decision criteria. Record errors by category, response time, usage cost, and cases needing human review. Keep a separate test set for final evaluation.

Can I compare probability or confidence numbers directly?

Do not assume that equal numbers from different models mean equal reliability. Check what each provider returns, measure how often decisions are correct at different thresholds, and account for the cost of mistakes. A confidence signal is not a measured accuracy rate.

Does the code example call Luna?

Yes. It calls openai/gpt-6-luna-decisions through this platform’s /v1/systemone endpoint with a platform API key. Use 1–8 questions in a request body no larger than 32 KiB. Answers are returned in data.result.answers. Direct OpenAI integrations use OpenAI’s own endpoint and authentication.