We use cookies. Cookies and browser storage keep you signed in and remember your preferences. With your permission we also measure how the site is used. You can any time. See our cookie policy.
OpenAI: GPT-6 Luna Decisions
openai/gpt-6-luna-decisionsTry OpenAI: GPT-6 Luna Decisions now
Runs on your balance at the prices above. New accounts start with free usage.
Results will appear here.
Settings
OpenAI: GPT-6 Luna Decisions at a glance
- Input price is 138% higher than the median of 25 Decisions models.
- Context window of 1,050,000 tokens, enough for long documents and multi-turn conversations.
- A typical request (1,000 input / 500 output tokens) costs about $0.000350.
About OpenAI: GPT-6 Luna Decisions
GPT-6 Luna Decisions is a model from OpenAI, served through OpenAI's Decisions API. It belongs to the decisions category, which sets it apart from the text generation models most developers are used to working with. Rather than producing prose or code, it is built to evaluate a situation and return a decision. The model was released by the provider on 2026-10-06 and is identified on api14 as openai/gpt-6-luna-decisions.
The model accepts text and images as input. Instead of generating text, it reads the content passed as state, which can be text, JSON, or images, and returns typed, probabilistic output. The context window is 1,050,000 tokens, and the maximum output is 945,000, so both the material it can consider and the decision payload it can return are large. Because the output modality is decisions rather than text, you should expect structured results rather than a conversational reply.
The practical uses follow directly from that shape. Any workflow where you need a judgement rather than a paragraph is a candidate: triaging incoming requests, classifying or routing items based on text or JSON state, and assessing images alongside written context in a single call. The large context window means you can pass substantial background material, long documents, or accumulated state without trimming it down first. Because the output is typed and probabilistic, it suits pipelines where a downstream system consumes the result and needs to handle confidence rather than parse free-form language.
You call the model through api14's OpenAI-compatible API using the model id openai/gpt-6-luna-decisions. Because the interface is OpenAI-compatible, existing SDKs and clients work with a change of base URL and model id. The model lists no supported request parameters, so plan on sending the state content and the model id rather than relying on tuning knobs such as temperature or top_p. Check the live price table on the page for current rates before you commit to a high-volume integration.
One thing to weigh is the output modality. If your application needs generated text, this is not the model for that job; a text generation model such as GPT-6 Luna is the more natural fit. GPT-6 Luna Decisions is the right choice when the deliverable is a decision, especially when the input includes images or a large body of state that must be considered together.
How to call the OpenAI: GPT-6 Luna Decisions API
- Create an API key in your dashboard.
- Install the official openai SDK for your language.
- Set baseURL to https://api14.com/api/v1 and model to "openai/gpt-6-luna-decisions".
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api14.com/api/v1",
apiKey: process.env.API14_API_KEY,
});
const result = await client.post("/decisions", { body: {
"model": "openai/gpt-6-luna-decisions",
"state": "Customer: I was charged twice for my order and want my money back.",
"questions": {
"team": {
"type": "choice",
"instructions": "Which team should handle this message?",
"criteria": {
"billing": "Payments, refunds, invoices",
"support": "Product questions and bugs",
"sales": "Pricing and new purchases"
}
},
"urgent": {
"type": "noul",
"instructions": "Does this need a reply today?",
"criteria": {
"true": "Money, outage or legal risk",
"false": "Can wait"
}
}
}
} });
console.log(result.answers);
Specifications
- Context length
- 1,050,000
- Max output
- 945,000
- Input
- text, image
- Output
- decisions
Requests on api14 · last 7 days
OpenAI: GPT-6 Luna Decisions: frequently asked questions
- How much does the OpenAI: GPT-6 Luna Decisions API cost?
- OpenAI: GPT-6 Luna Decisions costs Input $0.35 / 1M tokens. It is charged from your USD balance only for successful requests; failed requests are free.
- What is the context window of OpenAI: GPT-6 Luna Decisions?
- OpenAI: GPT-6 Luna Decisions reads up to 1,050,000 tokens per request: prompt, history and documents together. It writes up to 945,000 output tokens per response.
- What can OpenAI: GPT-6 Luna Decisions do?
- OpenAI: GPT-6 Luna Decisions accepts text, image and returns decisions.
- How do I call OpenAI: GPT-6 Luna Decisions from my code?
- Point any OpenAI SDK at https://api14.com/api/v1 and set the model to "openai/gpt-6-luna-decisions". No other code changes. Copy a ready example from the code panel on this page.
- What are alternatives to OpenAI: GPT-6 Luna Decisions?
- Comparable Decisions models at a similar price: Upstage: Solar Decide Flash, Upstage: Solar Decide, LiquidAI: d1-ultra. Each runs through the same API key, so switching is one string.
OpenAI: GPT-6 Luna Decisions community
New topicThis community has no topics yet. Open the first one about OpenAI: GPT-6 Luna Decisions.