OpenAI · 2026-09-29 · major
OpenAI Decisions API — GPT-6 Luna picks from your answers in 150 ms
OpenAI's Decisions API, launched at DevDay 2026, runs GPT-6 Luna to pick one of a developer's predefined answers about 10x faster than the Responses API. It is now in public beta at $0.10 per 1M input tokens.
OpenAI's answer to Jev: an endpoint that returns a choice, not text, about ten times faster than a normal Luna call.
Quick facts
| Maker | OpenAI |
|---|---|
| Model | gpt-6-luna (only model so far) |
| Latency | About 150 ms (vs 1.6 s for a standard Luna call) |
| Input | Text or image context + a closed list of answers |
| Price | $0.10 / 1M input tokens; no output or cache charges |
| Availability | Public beta; GA expected in the coming weeks |
What is it?
The Decisions API is a new OpenAI endpoint, announced at DevDay on September 29, 2026, that does not write free text. The developer sets a question and a fixed list of possible answers, and the API returns which answer fits best. The New Stack and The Decoder frame it as OpenAI's response to Jev, the typed decision model TypeSafe AI released in mid-September.
How does it work?
A specialized version of GPT-6 Luna reads the context — text or an image — and scores only the allowed options, then returns the most likely one with a confidence score. Because the output space is closed, the model cannot answer outside the list. Skipping text generation cuts the response time to about 150 milliseconds, against 1.6 seconds for a standard GPT-6 Luna call.
Why does it matter?
Classification, routing and "what should the agent do next" steps are often the slowest and least reliable part of an LLM app, because the model writes text that then has to be parsed. A fast endpoint that can only return a valid option makes these steps usable in real time. Billing only input tokens also makes high-volume routing cheap, though OpenAI has published no accuracy figure yet.
Who is it for?
developers building classifiers, routers and agent control loops
Frequently asked questions
- How much does the OpenAI Decisions API cost?
- OpenAI's docs price the Decisions API with gpt-6-luna at $0.10 per 1M input tokens. Developers pay only for input tokens: there are no output-token, cache-read or cache-write charges, because the API returns a choice instead of generated text.
- Can I use the OpenAI Decisions API today?
- Yes. The OpenAI Decisions API launched in limited preview at DevDay on September 29, 2026 and is now in public beta, according to OpenAI's developer docs. OpenAI says it expects general availability in the coming weeks. gpt-6-luna is the only model available for it so far.
- How does the OpenAI Decisions API compare to Jev?
- Both the OpenAI Decisions API and TypeSafe AI's Jev answer a question by choosing from predefined options instead of generating text. The New Stack describes the Decisions API as OpenAI's answer to Jev. OpenAI's version runs as a hosted API on a specialized GPT-6 Luna and has no published accuracy figure yet, so a direct comparison needs your own tests.
- What can the OpenAI Decisions API be used for?
- OpenAI says developers supply context as text or images and get back answers they can use to classify content, route requests, or choose an agent's next action. A typical case is a support app deciding whether a message goes to technical support, sales, or complaints — the Decisions API returns the category directly, with a confidence score.