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.
Upstage's structured decision model, a System One endpoint on Solar Mini 4. Returns a choice, a score or a yes/no answer with a probability read from the model, in one forward pass, on the same /v1/systemone schema as Jev.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
neohorse
solar
Fine-tuned from
tokenrhythm/neohorse-1-4b
—
License
apache-2.0
proprietary
Availability
Open weights
Hosted API
Hosted by
—
Upstage
Input price
—
$0.10/MTok
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 neohorse-jev and solar-decide?
neohorse-jev is from TokenRhythm and solar-decide from Upstage. neohorse-jev has open weights you can download and run; solar-decide is only available as a hosted API. Both answer choice, score, noul, classify and route questions. neohorse-jev is licensed apache-2.0; solar-decide, proprietary.
Which is more accurate, neohorse-jev or solar-decide?
Only neohorse-jev publishes an accuracy figure (75.3% on JevBench public set (231 items), vLLM, maker's run); solar-decide does not, so there is no comparison to make without your own test.
Which is cheaper, neohorse-jev or solar-decide?
neohorse-jev: Free (open weights). solar-decide: $0.1 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run neohorse-jev or solar-decide 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
