The first System One model. Reads a state, answers typed Choice, Score and Noul questions in one call with calibrated probabilities, and generates no text. Closed weights, served by TypeSafe AI.
A ModernBERT-large encoder with an option-marker head. Premise and options are packed into one sequence and each option's marker is scored in a single bidirectional pass; version 1.2 makes the scoring order-invariant.
Decides
choice, score, noul, classify, route
choice, score, noul, classify
Architecture
jev
von
Fine-tuned from
—
answerdotai/modernbert-large
License
proprietary
apache-2.0
Availability
Hosted API
Open weights
Hosted by
TypeSafe AI
—
Input price
$0.042/MTok
—
Decision accuracy
—
63.9%
Calibration error
—
0.045
Valid action rate
—
—
Median latency
—
18 ms
p95 latency
—
—
Evaluation suite
—
JevBench public standard tier
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 jev and von?
jev is from TypeSafe AI and von from wfzyx. jev is only available as a hosted API; von has open weights you can download and run. Both answer choice, score, noul and classify questions. Only jev answers route. jev reads up to 32K tokens of state, against 8K tokens for von. jev is licensed proprietary; von, apache-2.0.
Which is more accurate, jev or von?
Only von publishes an accuracy figure (63.9% on JevBench public standard tier); jev does not, so there is no comparison to make without your own test.
Which is cheaper, jev or von?
jev: $0.042 / $0 per 1M. von: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run jev or von locally?
von yes — systemone pull wfzyx/von downloads its weights. The other is only served as a hosted API.
