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.
Unofficial NoulXP package of Convai Innovations' Laya (English) (Apache-2.0), fp32-o23: checked against the model's own answers, none changed. Not made by Convai Innovations.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
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
—
116 ms
p95 latency
—
859 ms
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-noulxp-cpu?
jev is from TypeSafe AI and laya-noulxp-cpu from Convai Innovations. jev is only available as a hosted API; laya-noulxp-cpu has open weights you can download and run. Both answer choice, score, noul, classify and route questions. jev reads up to 32K tokens of state, against 512 tokens for laya-noulxp-cpu. jev is licensed proprietary; laya-noulxp-cpu, apache-2.0.
Which is more accurate, jev or laya-noulxp-cpu?
Neither publishes an accuracy figure. Test both on your own labelled examples.
Which is cheaper, jev or laya-noulxp-cpu?
jev: $0.042 / $0 per 1M. laya-noulxp-cpu: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run jev or laya-noulxp-cpu locally?
laya-noulxp-cpu yes — systemone pull convai-innovations/laya-noulxp-cpu downloads its weights. The other is only served as a hosted API.
Measured by System One Models on 2026-10-05: one question per request, 4 threads of a Xeon Gold 6342
