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.
TokenRhythm's prefill-only decision model for agent workflows. Built on its NeoHorse-1-4B (a Qwen3.5-4B derivative), it predicts Choice, Noul and Score answers over application-defined options without generating text, with optional single-image input.
Decides
choice, classify, route
choice, score, noul, classify, route
Architecture
gpt-6-luna
neohorse
Fine-tuned from
—
tokenrhythm/neohorse-1-4b
License
proprietary
apache-2.0
Availability
Hosted API
Open weights
Hosted by
OpenAI
—
Input price
—
—
Decision accuracy
—
75.3%
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 neohorse-jev?
decisions-api is from OpenAI and neohorse-jev from TokenRhythm. decisions-api is only available as a hosted API; neohorse-jev has open weights you can download and run. Both answer choice, classify and route questions. Only neohorse-jev answers score and noul. decisions-api is licensed proprietary; neohorse-jev, apache-2.0.
Which is more accurate, decisions-api or neohorse-jev?
Only neohorse-jev publishes an accuracy figure (75.3% on JevBench public set (231 items), vLLM, maker's run); decisions-api does not, so there is no comparison to make without your own test.
Which is cheaper, decisions-api or neohorse-jev?
decisions-api: Hosted, price not published. neohorse-jev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run decisions-api or neohorse-jev locally?
neohorse-jev yes — systemone pull tokenrhythm/neohorse-jev downloads its weights. The other is only served as a hosted API.
—
Evaluation suite
—
JevBench public set (231 items), vLLM, maker's run
