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.
An open family of System One models. A LoRA adapter plus a pointer head on a frozen Qwen base returns a distribution per typed question in one forward pass, serves TypeSafe's /v1/systemone contract, and ships a fitted temperature with every checkpoint.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
jev
kev
Fine-tuned from
—
qwen/qwen3.5-4b-base
License
proprietary
apache-2.0
Availability
Hosted API
Open weights
Hosted by
TypeSafe AI
—
Input price
$0.042/MTok
—
Decision accuracy
—
83.8%
Calibration error
—
0.042
Valid action rate
—
—
Median latency
—
—
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 kev?
jev is from TypeSafe AI and kev from Jared Palmer. jev is only available as a hosted API; kev has open weights you can download and run. Both answer choice, score, noul, classify and route questions. jev reads up to 32K tokens of state, against 8K tokens for kev. jev is licensed proprietary; kev, apache-2.0.
Which is more accurate, jev or kev?
Only kev publishes an accuracy figure (83.8% on transfer-v4 (locked, out of domain)); jev does not, so there is no comparison to make without your own test.
Which is cheaper, jev or kev?
jev: $0.042 / $0 per 1M. kev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run jev or kev locally?
kev yes — systemone pull jared-palmer/kev downloads its weights. The other is only served as a hosted API.
