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.
Respan's behaviour-scoring model for evals, guardrails and monitoring. For each plain-language behaviour you define, it reads a conversation or agent trace and returns the probability the behaviour is present, absent or not observable, in one forward pass.
Decides
choice, score, noul, classify, route
noul, classify
Architecture
laya
span
Fine-tuned from
convai-innovations/laya
—
License
apache-2.0
proprietary
Availability
Open weights
Hosted API
Hosted by
—
Respan
Input price
—
$0.020/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 laya-noulxp-cpu and span-01?
laya-noulxp-cpu is from Convai Innovations and span-01 from Respan. laya-noulxp-cpu has open weights you can download and run; span-01 is only available as a hosted API. Both answer noul and classify questions. Only laya-noulxp-cpu answers choice, score and route. laya-noulxp-cpu is licensed apache-2.0; span-01, proprietary.
Which is more accurate, laya-noulxp-cpu or span-01?
Neither publishes an accuracy figure. Test both on your own labelled examples.
Which is cheaper, laya-noulxp-cpu or span-01?
laya-noulxp-cpu: Free (open weights). span-01: $0.02 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run laya-noulxp-cpu or span-01 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
