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.
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
answerdotai/modernbert-large
—
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
39.5 ms
—
p95 latency
—
—
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 and trio-spark-v1?
laya is from Convai Innovations and trio-spark-v1 from MachineFi. laya 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 answers score and noul. trio-spark-v1 reads up to 1K tokens of state, against 512 tokens for laya. laya is licensed apache-2.0; trio-spark-v1, proprietary.
Which is more accurate, laya or trio-spark-v1?
Neither publishes an accuracy figure. Test both on your own labelled examples.
Which is cheaper, laya or trio-spark-v1?
laya: 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 or trio-spark-v1 locally?
laya yes — systemone pull convai-innovations/laya downloads its weights. The other is only served as a hosted API.
