# OpenAI’s Decisions API turns GPT-6 Luna into a bounded decision layer for software OpenAI has introduced a Decisions API that takes text or image context plus finite, developer-defined answer choices and returns decisions for classification, routing and agent control, bringing the emerging decision-model pattern into its own API platform. Jev, CLM and GLiNER2.5-Decide made bounded software decisions look like a distinct model category. OpenAI is now validating the same architectural split with a Luna-powered API designed to answer finite questions rather than generate open-ended prose. - Status: Active - Published: 2026-09-30T16:48:32+13:00 - Updated: 2026-09-30T16:48:32+13:00 - Categories: Artificial Intelligence, AI Models, AI Agents, Inference & APIs - Tags: agent routing, decision models, Decisions API, GPT-6 Luna, OpenAI, structured outputs - Canonical HTML: https://beyondthe.news/dossiers/openai-decisions-api-gpt-6-luna-bounded-software-decisions ## What changed At DevDay on September 29, 2026, OpenAI introduced Decisions API in limited preview. Developers define questions with finite pre-defined answers, provide context as text or images, and receive answers intended for direct software use. OpenAI names content classification, request routing and selecting an agent's next action as example workloads. The API uses GPT-6 Luna and OpenAI says a broad release is planned in the coming days. ## Why it matters This is not merely another structured-output option. OpenAI is exposing a separate API surface around the idea that many production AI calls are bounded decisions rather than conversations. That is the same software layer recently targeted by Jev, CLM-8B and GLiNER2.5-Decide. A frontier API provider adopting the pattern makes it easier for builders to compare decision-specific calls against general LLM generation on latency, cost, calibration and operational simplicity. ## The contract is finite answers, not generated prose Developers supply context and a known answer set instead of asking a model to generate and then parse free-form text. OpenAI explicitly positions the interface for classification, routing and agent-action selection, where the application already knows the legal outcomes. ## Luna becomes more than a cheap chat model The first Decisions API implementation focuses GPT-6 Luna on bounded questions. That gives OpenAI a way to reuse its inexpensive model tier behind a task-specific interface while applications consume decisions rather than conversational output. ## The category is getting crowded quickly BTN has already tracked Jev's typed probabilistic API and external Vercel adoption, open CLM-8B, and the much smaller GLiNER2.5-Decide. OpenAI's entry does not make those systems equivalent, but it strengthens the case that decision-specific inference is becoming a distinct production layer rather than a single startup's API design. ## The important evidence is still missing OpenAI has not yet published enough detail in the DevDay recap to compare calibration, latency, per-decision economics or exact response semantics against Jev and other decision models. Limited-preview behavior may also change before broad release. ## Key details - Announced September 29, 2026 at OpenAI DevDay 2026. - Available in limited preview with broad release planned in the coming days. - Uses GPT-6 Luna for bounded decision workloads. - Developers define questions with finite pre-defined answers. - Context can include text or images. - OpenAI names classification, request routing and agent next-action selection as example uses. ## Builder takeaways - Benchmark the Decisions API against your existing classifier or structured-output LLM path, not against chat quality. - Measure calibration, latency, cost per accepted decision and escalation rate on labelled production-like data. - Keep deterministic business rules outside the model where the decision does not need probabilistic judgement. - Treat limited-preview schemas and behavior as changeable until OpenAI documents the broad release. ## What to watch - Broad-release API documentation, schemas and pricing. - Whether OpenAI returns probabilities or calibration information alongside answers. - Independent comparisons with Jev, CLM-8B and GLiNER2.5-Decide. - SDK and gateway support for a first-class decision primitive. - Production case studies replacing repeated general-LLM calls with bounded decisions. ## Uncertainties - The DevDay recap does not yet provide full API schema, pricing or latency details. - OpenAI has not published independent calibration or decision-quality evidence. - Limited-preview behavior may change before broad release. - It is not yet clear how much of the behavior comes from Luna itself versus a task-specific serving or prompting layer. ## Sources - [DevDay 2026 Recap](https://openai.com/index/devday-2026-recap/) — OpenAI · primary · 2026-09-29T00:00:00+13:00. Primary announcement for Decisions API, Luna basis, finite-answer contract, supported context and limited-preview availability.