The first System One model. Reads a state, answers typed Choice, Score and Noul questions in one call with calibrated probabilities, and generates no text. Closed weights, served by TypeSafe AI.
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.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
jev
simple-jev
Fine-tuned from
—
google/gemma-4-26b-a4b-it
License
proprietary
apache-2.0
Availability
Hosted API
Open weights + hosted API
Hosted by
TypeSafe AI
Featherless AI
Input price
$0.042/MTok
—
Decision accuracy
—
—
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 jev and simple-jev?
jev is from TypeSafe AI and simple-jev from Featherless AI. jev is only available as a hosted API; simple-jev has open weights and a hosted API. Both answer choice, score, noul, classify and route questions. jev is licensed proprietary; simple-jev, apache-2.0.
Which is more accurate, jev or simple-jev?
Neither publishes an accuracy figure. Test both on your own labelled examples.
Which is cheaper, jev or simple-jev?
jev: $0.042 / $0 per 1M. simple-jev: Hosted, price not published, or free to self-host. Open weights cost nothing per call beyond your own hardware.
Can I run jev or simple-jev locally?
simple-jev yes — systemone pull featherless-ai/simple-jev downloads its weights. The other is only served as a hosted API.
