GPT-6 Luna Decisions via the Tokenator API
What the model is for
GPT-6 Luna Decisions is GPT-6 Luna served through OpenAI's Decisions API. Instead of generating text, it reads the content passed as state (text, JSON, or images) and returns typed, probabilistic answers to named questions in a single request: the probability of yes for a yes/no question (noul), a probability for every option plus the most likely one (choice), or a probability for every level of an ordered rubric plus the expected score (score). It is built for classification, routing, moderation, and rubric grading where application code thresholds the returned numbers rather than parsing a chat reply. A request can carry up to 200 questions about the same content.
Specification
| Full name | GPT-6 Luna Decisions |
| API ID | gpt-6-luna-decisions |
| Model vendor | OpenAI |
| Type | Decisions (probabilities for typed questions) |
| Context window | 1.05M tokens |
| Tokenator usage multiplier | 1.1× |
| Badge | NEW |
| Input modalities | text, image |
| Supported API formats | /v1/decisions |
| Upstream providers | 1 |
| Current status | available |
| Data updated | 2026-10-08 |
Upstream providers
| Provider | Multiplier |
|---|---|
| Unified LLM API | 1.1× |
A request goes to the first available provider by priority; if it fails, Tokenator switches to the next one.
Example request
curl https://api.tokenator.top/v1/decisions \ -H "Authorization: Bearer sk-your-tokenator-key" \ -H "Content-Type: application/json" \ -d '{ "model": "gpt-6-luna-decisions", "state": "My checkout page shows a blank screen after I click Pay. I have tried two browsers.", "questions": { "is_bug": { "type": "noul", "instructions": "Is the customer reporting a software defect?", "criteria": { "true": "The customer describes broken or unexpected product behavior.", "false": "The customer is asking a question or requesting a feature." } }, "team": { "type": "choice", "instructions": "Which team should own this ticket?", "criteria": { "account": "Login, permissions, or profile issues.", "frontend": "Rendering, layout, or browser compatibility issues.", "payments": "Checkout, billing, or payment processing issues." } }, "urgency": { "type": "score", "instructions": "How urgent is this ticket?", "criteria": [ "Can wait for the next release", "Should be fixed this week", "Blocking revenue right now" ] } } }'
See also
FAQ about GPT-6 Luna Decisions
What is the API ID of GPT-6 Luna Decisions?
gpt-6-luna-decisions — put this into the model field of your request.
What context window does GPT-6 Luna Decisions have?
1.05M tokens.
How many tokens will a request cost?
input × 1.1× — the answer with its probabilities is not billed, you pay for the input only: the state and the questions. See the documentation for details.
How do I call this model?
Through /v1/decisions only: the chat endpoints refuse such a model. Question types, the answer shape and examples are in the decisions documentation.