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.
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
choice, score, noul, classify, route
Architecture
startlux-decision
state-decider
Fine-tuned from
—
—
License
cc-by-nc-4.0
proprietary
Availability
Open weights
Hosted API
Hosted by
—
meraGPT
Input price
—
$0.030/MTok
Decision accuracy
88.3%
76.8%
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 startlux-decision and state-decider-1?
startlux-decision is from StartLux and state-decider-1 from meraGPT. startlux-decision has open weights you can download and run; state-decider-1 is only available as a hosted API. Both answer choice, score and noul questions. Only state-decider-1 answers classify and route. startlux-decision is licensed cc-by-nc-4.0; state-decider-1, proprietary.
Which is more accurate, startlux-decision or state-decider-1?
They report on different suites — startlux-decision 88.3% on JevBench public set (231 items; 204 correct), maker's run, state-decider-1 76.8% on typed-decisions benchmark (400 cases, 2,000 decisions; teacher-ensemble references), single run — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, startlux-decision or state-decider-1?
startlux-decision: Free (open weights). state-decider-1: $0.03 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run startlux-decision or state-decider-1 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
typed-decisions benchmark (400 cases, 2,000 decisions; teacher-ensemble references), single run
