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.
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.
Decides
noul, classify
choice, score, noul
Architecture
span
startlux-decision
Fine-tuned from
—
—
License
proprietary
cc-by-nc-4.0
Availability
Hosted API
Open weights
Hosted by
Respan
—
Input price
$0.020/MTok
—
Decision accuracy
—
88.3%
Calibration error
—
—
Valid action rate
—
—
Median latency
—
26 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 span-01 and startlux-decision?
span-01 is from Respan and startlux-decision from StartLux. span-01 is only available as a hosted API; startlux-decision has open weights you can download and run. Both answer noul questions. Only span-01 answers classify. Only startlux-decision answers choice and score. span-01 is licensed proprietary; startlux-decision, cc-by-nc-4.0.
Which is more accurate, span-01 or startlux-decision?
Only startlux-decision publishes an accuracy figure (88.3% on JevBench public set (231 items; 204 correct), maker's run); span-01 does not, so there is no comparison to make without your own test.
Which is cheaper, span-01 or startlux-decision?
span-01: $0.02 / $0 per 1M. startlux-decision: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run span-01 or startlux-decision locally?
startlux-decision yes — systemone pull startlux/startlux-decision downloads its weights. The other is only served as a hosted API.
Evaluation suite
—
JevBench public set (231 items; 204 correct), maker's run
