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.
Qwen3.5-4B with a merged rank-16 LoRA distilled from 17,408 teacher questions and 30,000 public training rows, read out as a temperature-scaled softmax over answer-letter logits. Also in 9B, 2B and GGUF.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
jev
jevk5
Fine-tuned from
—
qwen/qwen3.5-4b
License
proprietary
apache-2.0
Availability
Hosted API
Open weights
Hosted by
TypeSafe AI
—
Input price
$0.042/MTok
—
Decision accuracy
—
78.4%
Calibration error
—
0.035
Valid action rate
—
—
Median latency
—
13.2 ms
p95 latency
—
—
Evaluation suite
—
JevBench public hard tier
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 jevk5?
jev is from TypeSafe AI and jevk5 from Alibi Serikbay. jev is only available as a hosted API; jevk5 has open weights you can download and run. Both answer choice, score, noul, classify and route questions. jev is licensed proprietary; jevk5, apache-2.0.
Which is more accurate, jev or jevk5?
Only jevk5 publishes an accuracy figure (78.4% on JevBench public hard tier); jev does not, so there is no comparison to make without your own test.
Which is cheaper, jev or jevk5?
jev: $0.042 / $0 per 1M. jevk5: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run jev or jevk5 locally?
jevk5 yes — systemone pull alibi-serikbay/jevk5 downloads its weights. The other is only served as a hosted API.
