An open-weights System One model from Convai Innovations. A fully fine-tuned ModernBERT-large encoder with a from-scratch decision head that scores one marker per option and answers every question in a single 33–39 ms pass. Runs on your own CPU or GPU.
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
answerdotai/modernbert-large
—
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
39.5 ms
—
p95 latency
—
—
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 and span-01?
laya is from Convai Innovations and span-01 from Respan. laya 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 answers choice, score and route. laya is licensed apache-2.0; span-01, proprietary.
Which is more accurate, laya or span-01?
Neither publishes an accuracy figure. Test both on your own labelled examples.
Which is cheaper, laya or span-01?
laya: Free (open weights). span-01: $0.02 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run laya or span-01 locally?
laya yes — systemone pull convai-innovations/laya downloads its weights. The other is only served as a hosted API.
