A training-free layer that turns an open LLM into a decision model. It reads typed choice, yes/no and score answers from one prefill, removes option-order bias with no labels and, from a few hundred labels, calibrates or fits a closed-form head. Weights stay untouched.
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.
Decides
choice, score, noul, classify, route
choice, classify, route
Architecture
anyjev
gpt-6-luna
Fine-tuned from
qwen/qwen3-8b
—
License
apache-2.0
proprietary
Availability
Open weights
Hosted API
Hosted by
—
OpenAI
Input price
—
—
Decision accuracy
77.1%
—
Calibration error
0.034
—
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 anyjev and decisions-api?
anyjev is from Nokia and decisions-api from OpenAI. anyjev has open weights you can download and run; decisions-api is only available as a hosted API. Both answer choice, classify and route questions. Only anyjev answers score and noul. anyjev is licensed apache-2.0; decisions-api, proprietary.
Which is more accurate, anyjev or decisions-api?
Only anyjev publishes an accuracy figure (77.1% on LocalLLaMA/typed-decisions (2,000 held-out decisions), L2 with 300 labels per question); decisions-api does not, so there is no comparison to make without your own test.
Which is cheaper, anyjev or decisions-api?
anyjev: Free (open weights). decisions-api: Hosted, price not published. Open weights cost nothing per call beyond your own hardware.
Can I run anyjev or decisions-api locally?
anyjev yes — systemone pull nokia/anyjev downloads its weights. The other is only served as a hosted API.
Evaluation suite
LocalLLaMA/typed-decisions (2,000 held-out decisions), L2 with 300 labels per question
