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.
A Gemma 4 12B fine-tune for typed decisions that also chats and reads images. Ships as GGUF for llama.cpp, holds a 64K context on a 16 GB GPU, and serves /v1/systemone next to /v1/chat/completions.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
jev
winnow
Fine-tuned from
—
google/gemma-4-12b-it
License
proprietary
apache-2.0
Availability
Hosted API
Open weights
Hosted by
TypeSafe AI
—
Input price
$0.042/MTok
—
Decision accuracy
—
85.7%
Calibration error
—
—
Valid action rate
—
—
Median latency
—
143 ms
p95 latency
—
—
Evaluation suite
—
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 winnow?
jev is from TypeSafe AI and winnow from EldanRing. jev is only available as a hosted API; winnow has open weights you can download and run. Both answer choice, score, noul, classify and route questions. winnow reads up to 64K tokens of state, against 32K tokens for jev. jev is licensed proprietary; winnow, apache-2.0.
Which is more accurate, jev or winnow?
Only winnow publishes an accuracy figure (85.7% on JevBench public subset (231 items), Q8_0); jev does not, so there is no comparison to make without your own test.
Which is cheaper, jev or winnow?
jev: $0.042 / $0 per 1M. winnow: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run jev or winnow locally?
winnow yes — systemone pull eldanring/winnow downloads its weights. The other is only served as a hosted API.
