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.
Native MLX FP16 conversion of Laya for Apple silicon. The same ModernBERT-large encoder, decision transformer and heads, running in MLX with no PyTorch; the checkpoint Laya Studio fine-tunes from.
Decides
choice, score, noul, classify, route
choice, score, noul
Architecture
jev
laya
Fine-tuned from
—
convai-innovations/laya
License
proprietary
apache-2.0
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
—
—
Evaluation suite
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 laya-mlx?
jev is from TypeSafe AI and laya-mlx from aac6fef. jev is only available as a hosted API; laya-mlx has open weights you can download and run. Both answer choice, score and noul questions. Only jev answers classify and route. jev reads up to 32K tokens of state, against 512 tokens for laya-mlx. jev is licensed proprietary; laya-mlx, apache-2.0.
Which is more accurate, jev or laya-mlx?
Neither publishes an accuracy figure. Test both on your own labelled examples.
Which is cheaper, jev or laya-mlx?
jev: $0.042 / $0 per 1M. laya-mlx: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run jev or laya-mlx locally?
laya-mlx yes — systemone pull aac6fef/laya-mlx downloads its weights. The other is only served as a hosted API.
