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 multimodal decision classifier over text, image, audio and video on Gemma 4 12B, fine-tuned on 30,000 questions. Returns a probability per option and generates nothing.
Decides
choice, score, noul, classify, route
choice, noul, score, classify
Architecture
jev
jev-omni
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
—
87.6%
Calibration error
—
0.040
Valid action rate
—
—
Median latency
—
83 ms
p95 latency
—
—
Evaluation suite
—
DecisionBench Medium (author's set)
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 jev-omni?
jev is from TypeSafe AI and jev-omni from akhilaaa3. jev is only available as a hosted API; jev-omni has open weights you can download and run. Both answer choice, score, noul and classify questions. Only jev answers route. jev is licensed proprietary; jev-omni, apache-2.0.
Which is more accurate, jev or jev-omni?
Only jev-omni publishes an accuracy figure (87.6% on DecisionBench Medium (author's set)); jev does not, so there is no comparison to make without your own test.
Which is cheaper, jev or jev-omni?
jev: $0.042 / $0 per 1M. jev-omni: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run jev or jev-omni locally?
jev-omni yes — systemone pull akhilaaa3/jev-omni downloads its weights. The other is only served as a hosted API.
