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 0.6B replica of the System One idea trained on game environments. A Qwen3-0.6B backbone with an attention-based Choice head that scores a dynamic candidate set for Maze, Snake, ViZDoom and position prediction, shipped with its full training pipeline.
Decides
choice, score, noul, classify, route
choice, noul, score
Architecture
jev
nanojev
Fine-tuned from
—
qwen/qwen3-0.6b
License
proprietary
mit
Availability
Hosted API
Open weights
Hosted by
TypeSafe AI
—
Input price
$0.042/MTok
—
Decision accuracy
—
—
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 jev and nanojev?
jev is from TypeSafe AI and nanojev from TianyuCodings. jev is only available as a hosted API; nanojev has open weights you can download and run. Both answer choice, score and noul questions. Only jev answers classify and route. jev is licensed proprietary; nanojev, mit.
Which is more accurate, jev or nanojev?
Neither publishes an accuracy figure. Test both on your own labelled examples.
Which is cheaper, jev or nanojev?
jev: $0.042 / $0 per 1M. nanojev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run jev or nanojev locally?
nanojev yes — systemone pull tianyu-codings/nanojev downloads its weights. The other is only served as a hosted API.
