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.
AutoTrust's student of TypeSafe Jev 1.13. A frozen Qwen3.8-27B plus a 108.9M-parameter decision block trained on Jev's own output distributions; one set of weights answers typed questions in one pass (System 1) or generates text with the untouched base (System 2).
Decides
choice, classify, route
choice, score, noul
Architecture
gpt-6-luna
blocks-of-experts
Fine-tuned from
—
qwen/qwen3.8-27b
License
proprietary
apache-2.0
Availability
Hosted API
Open weights
Hosted by
OpenAI
—
Input price
—
—
Decision accuracy
—
88.7%
Calibration error
—
—
Valid action rate
—
—
Median latency
—
137 ms
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-27b?
decisions-api is from OpenAI and jev-27b from AutoTrust AI Lab. decisions-api is only available as a hosted API; jev-27b has open weights you can download and run. Both answer choice questions. Only decisions-api answers classify and route. Only jev-27b answers score and noul. decisions-api is licensed proprietary; jev-27b, apache-2.0.
Which is more accurate, decisions-api or jev-27b?
Only jev-27b publishes an accuracy figure (88.7% on JevBench public set (231 items), family-macro score, maker's run); decisions-api does not, so there is no comparison to make without your own test.
Which is cheaper, decisions-api or jev-27b?
decisions-api: Hosted, price not published. jev-27b: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run decisions-api or jev-27b locally?
jev-27b yes — systemone pull autotrust-ai/jev-27b downloads its weights. The other is only served as a hosted API.
Evaluation suite
—
JevBench public set (231 items), family-macro score, maker's run
