Featherless AI's open server that turns a stock Hugging Face language model into a typed-decision endpoint. It reads the next-token logits for each question and builds the Choice, Score or Noul answer itself; no classifier head is trained and no JSON is generated.
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
choice, score, noul, classify, route
choice, score, noul
Architecture
simple-jev
startlux-decision
Fine-tuned from
google/gemma-4-26b-a4b-it
—
License
apache-2.0
cc-by-nc-4.0
Availability
Open weights + hosted API
Open weights
Hosted by
Featherless AI
—
Input price
—
—
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 simple-jev and startlux-decision?
simple-jev is from Featherless AI and startlux-decision from StartLux. simple-jev has open weights and a hosted API; startlux-decision has open weights you can download and run. Both answer choice, score and noul questions. Only simple-jev answers classify and route. simple-jev is licensed apache-2.0; startlux-decision, cc-by-nc-4.0.
Which is more accurate, simple-jev or startlux-decision?
Only startlux-decision publishes an accuracy figure (88.3% on JevBench public set (231 items; 204 correct), maker's run); simple-jev does not, so there is no comparison to make without your own test.
Which is cheaper, simple-jev or startlux-decision?
simple-jev: Hosted, price not published, or free to self-host. startlux-decision: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run simple-jev or startlux-decision locally?
Yes, both: systemone pull featherless-ai/simple-jev and systemone pull startlux/startlux-decision download the weights.
—
Evaluation suite
—
JevBench public set (231 items; 204 correct), maker's run
