OpenAI's decision endpoint, announced at DevDay 2026. It focuses GPT-6 Luna on developer-defined questions that have a finite set of predefined answers, with text or image context, for classification, routing and an agent's next action.
The first System One model. Reads a state, answers typed Choice, Score and Noul questions in one call with calibrated probabilities, and generates no text. Closed weights, served by TypeSafe AI.
Decides
choice, classify, route
choice, score, noul, classify, route
Architecture
gpt-6-luna
jev
Fine-tuned from
—
—
License
proprietary
proprietary
Availability
Hosted API
Hosted API
Hosted by
OpenAI
TypeSafe AI
Input price
—
$0.042/MTok
Decision accuracy
—
—
Calibration error
—
—
Valid action rate
—
—
Median latency
—
—
p95 latency
—
—
Figures are from each model’s manifest; accuracy and latency are what the publishers report, on their own suites and hardware. Add a third model.
Questions
What is the difference between decisions-api and jev?
decisions-api is from OpenAI and jev from TypeSafe AI. Both are only available as a hosted API. Both answer choice, classify and route questions. Only jev answers score and noul.
Which is more accurate, decisions-api or jev?
Neither publishes an accuracy figure. Test both on your own labelled examples.
Which is cheaper, decisions-api or jev?
decisions-api: Hosted, price not published. jev: $0.042 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
