HEAD TO HEAD

djev vs neohorse-jev

Q: Can I run djev or neohorse-jev locally?

Yes, both: systemone pull maisa/djev and systemone pull tokenrhythm/neohorse-jev download the weights.

Maisa: djev and TokenRhythm: neohorse-jev, compared on what they decide, where they run, what they cost and what their publishers report.

The short version

djev has open weights and a hosted API; neohorse-jev has open weights you can download and run.
Both answer choice, score and noul questions.
Only neohorse-jev answers classify and route.
neohorse-jev is the smaller model, at 4.0B parameters to 26B.

Property	maisa/djev	tokenrhythm/neohorse-jev
Summary	A typed-decision layer for Google's DiffusionGemma, from David Villalón at Maisa AI. It compiles a request into a small answer canvas, runs one denoising read on patched vLLM and reads the probabilities of the allowed labels, for text, images and images offered as options.	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, score, noul	choice, score, noul, classify, route
Architecture	djev	neohorse
Fine-tuned from	google/diffusiongemma-26b-a4b-it	tokenrhythm/neohorse-1-4b
License	apache-2.0	apache-2.0
Availability	Open weights + hosted API	Open weights
Hosted by	Maisa	—
Input price	$0.035/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 djev and neohorse-jev?

djev is from Maisa and neohorse-jev from TokenRhythm. djev has open weights and a hosted API; neohorse-jev has open weights you can download and run. Both answer choice, score and noul questions. Only neohorse-jev answers classify and route. neohorse-jev is the smaller model, at 4.0B parameters to 26B.

Which is more accurate, djev or neohorse-jev?

Only neohorse-jev publishes an accuracy figure (75.3% on JevBench public set (231 items), vLLM, maker's run); djev does not, so there is no comparison to make without your own test.

Which is cheaper, djev or neohorse-jev?

djev: $0.035 / $0 per 1M, or free to self-host. neohorse-jev: Free (open weights). Open weights cost nothing per call beyond your own hardware.

Can I run djev or neohorse-jev locally?

Yes, both: systemone pull maisa/djev and systemone pull tokenrhythm/neohorse-jev download the weights.