Unofficial NoulXP package of Convai Innovations' Laya multilingual (Apache-2.0), fp32-o23: checked against the model's own answers, none changed. Not made by Convai Innovations.
A Situated World Model for fast judgment in agent loops.
Decides
choice, score, noul, classify, route
choice, route, classify
Architecture
laya
trio-spark
Fine-tuned from
convai-innovations/laya
—
License
apache-2.0
proprietary
Availability
Open weights
Hosted API
Hosted by
—
MachineFi
Input price
—
$0.042/MTok
Decision accuracy
—
—
Calibration error
—
—
Valid action rate
—
—
Median latency
44.9 ms
—
p95 latency
742 ms
—
Evaluation suite
Measured by System One Models on 2026-10-05: one question per request, 4 threads of a Xeon Gold 6342
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-multilingual-noulxp and trio-spark-v1?
laya-multilingual-noulxp is from Convai Innovations and trio-spark-v1 from MachineFi. laya-multilingual-noulxp has open weights you can download and run; trio-spark-v1 is only available as a hosted API. Both answer choice, classify and route questions. Only laya-multilingual-noulxp answers score and noul. laya-multilingual-noulxp is licensed apache-2.0; trio-spark-v1, proprietary.
Which is more accurate, laya-multilingual-noulxp or trio-spark-v1?
Neither publishes an accuracy figure. Test both on your own labelled examples.
Which is cheaper, laya-multilingual-noulxp or trio-spark-v1?
laya-multilingual-noulxp: Free (open weights). trio-spark-v1: $0.042 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run laya-multilingual-noulxp or trio-spark-v1 locally?
laya-multilingual-noulxp yes — systemone pull convai-innovations/laya-multilingual-noulxp downloads its weights. The other is only served as a hosted API.
