StartLux's decision family in five sizes, 0.8B to 27B. All questions in a request are answered in one forward pass, with a probability for every option, through a TypeSafe /v1/systemone-compatible server that records CUDA graphs for short requests.
A Situated World Model for fast judgment in agent loops.
Decides
choice, score, noul
choice, route, classify
Architecture
startlux-decision
trio-spark
Fine-tuned from
—
—
License
cc-by-nc-4.0
proprietary
Availability
Open weights
Hosted API
Hosted by
—
MachineFi
Input price
—
$0.042/MTok
Decision accuracy
88.3%
—
Calibration error
—
—
Valid action rate
—
—
Median latency
26 ms
—
p95 latency
—
—
Evaluation suite
JevBench public set (231 items; 204 correct), maker's run
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 startlux-decision and trio-spark-v1?
startlux-decision is from StartLux and trio-spark-v1 from MachineFi. startlux-decision has open weights you can download and run; trio-spark-v1 is only available as a hosted API. Both answer choice questions. Only startlux-decision answers score and noul. Only trio-spark-v1 answers route and classify. startlux-decision is licensed cc-by-nc-4.0; trio-spark-v1, proprietary.
Which is more accurate, startlux-decision or trio-spark-v1?
Only startlux-decision publishes an accuracy figure (88.3% on JevBench public set (231 items; 204 correct), maker's run); trio-spark-v1 does not, so there is no comparison to make without your own test.
Which is cheaper, startlux-decision or trio-spark-v1?
startlux-decision: Free (open weights). trio-spark-v1: $0.042 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run startlux-decision or trio-spark-v1 locally?
startlux-decision yes — systemone pull startlux/startlux-decision downloads its weights. The other is only served as a hosted API.
