Unofficial NoulXP package of Convai Innovations' Laya typed-decisions (Apache-2.0), fp32-o23: checked against the model's own answers, none changed. Not made by Convai Innovations.
Upstage's structured decision model, a System One endpoint on Solar Mini 4. Returns a choice, a score or a yes/no answer with a probability read from the model, in one forward pass, on the same /v1/systemone schema as Jev.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
laya
solar
Fine-tuned from
convai-innovations/laya
—
License
apache-2.0
proprietary
Availability
Open weights
Hosted API
Hosted by
—
Upstage
Input price
—
$0.10/MTok
Decision accuracy
—
—
Calibration error
—
—
Valid action rate
—
—
Median latency
126 ms
—
p95 latency
2185 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-typed-decisions-noulxp and solar-decide?
laya-typed-decisions-noulxp is from Convai Innovations and solar-decide from Upstage. laya-typed-decisions-noulxp has open weights you can download and run; solar-decide is only available as a hosted API. Both answer choice, score, noul, classify and route questions. solar-decide reads up to 512K tokens of state, against 1K tokens for laya-typed-decisions-noulxp. laya-typed-decisions-noulxp is licensed apache-2.0; solar-decide, proprietary.
Which is more accurate, laya-typed-decisions-noulxp or solar-decide?
Neither publishes an accuracy figure. Test both on your own labelled examples.
Which is cheaper, laya-typed-decisions-noulxp or solar-decide?
laya-typed-decisions-noulxp: Free (open weights). solar-decide: $0.1 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run laya-typed-decisions-noulxp or solar-decide locally?
laya-typed-decisions-noulxp yes — systemone pull convai-innovations/laya-typed-decisions-noulxp 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