Unofficial NoulXP package of Convai Innovations' Laya (English) (Apache-2.0), fp16: checked against the model's own answers, none changed. Not made by Convai Innovations.
meraGPT's hosted decision model (state-decider-1). Answers yes/no, choice and rubric-score questions over one state as calibrated distributions in a single pass, on the System One schema, so the typesafe-sdk works by changing its base URL.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
laya
state-decider
Fine-tuned from
convai-innovations/laya
—
License
apache-2.0
proprietary
Availability
Open weights
Hosted API
Hosted by
—
meraGPT
Input price
—
$0.030/MTok
Decision accuracy
—
76.8%
Calibration error
—
—
Valid action rate
—
—
Median latency
—
—
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-noulxp-gpu and state-decider-1?
laya-noulxp-gpu is from Convai Innovations and state-decider-1 from meraGPT. laya-noulxp-gpu has open weights you can download and run; state-decider-1 is only available as a hosted API. Both answer choice, score, noul, classify and route questions. state-decider-1 reads up to 4K tokens of state, against 512 tokens for laya-noulxp-gpu. laya-noulxp-gpu is licensed apache-2.0; state-decider-1, proprietary.
Which is more accurate, laya-noulxp-gpu or state-decider-1?
Only state-decider-1 publishes an accuracy figure (76.8% on typed-decisions benchmark (400 cases, 2,000 decisions; teacher-ensemble references), single run); laya-noulxp-gpu does not, so there is no comparison to make without your own test.
Which is cheaper, laya-noulxp-gpu or state-decider-1?
laya-noulxp-gpu: Free (open weights). state-decider-1: $0.03 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run laya-noulxp-gpu or state-decider-1 locally?
laya-noulxp-gpu yes — systemone pull convai-innovations/laya-noulxp-gpu downloads its weights. The other is only served as a hosted API.
Evaluation suite
—
typed-decisions benchmark (400 cases, 2,000 decisions; teacher-ensemble references), single run
