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.
meraGPT's hosted decision model (state-decider-1). Answers yes/no, choice and rubric-score questions over one state as calibrated distributions in a single pass, on the System One schema, so the typesafe-sdk works by changing its base URL.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
neohorse
state-decider
Fine-tuned from
tokenrhythm/neohorse-1-4b
—
License
apache-2.0
proprietary
Availability
Open weights
Hosted API
Hosted by
—
meraGPT
Input price
—
$0.030/MTok
Decision accuracy
75.3%
76.8%
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 state-decider-1?
neohorse-jev is from TokenRhythm and state-decider-1 from meraGPT. neohorse-jev has open weights you can download and run; state-decider-1 is only available as a hosted API. Both answer choice, score, noul, classify and route questions. neohorse-jev is licensed apache-2.0; state-decider-1, proprietary.
Which is more accurate, neohorse-jev or state-decider-1?
They report on different suites — neohorse-jev 75.3% on JevBench public set (231 items), vLLM, maker's run, state-decider-1 76.8% on typed-decisions benchmark (400 cases, 2,000 decisions; teacher-ensemble references), single run — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, neohorse-jev or state-decider-1?
neohorse-jev: Free (open weights). state-decider-1: $0.03 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run neohorse-jev or state-decider-1 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
typed-decisions benchmark (400 cases, 2,000 decisions; teacher-ensemble references), single run
