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 System One model from Interfaze AI. A rank-32 LoRA on Qwen3.5-4B reads yes/no, choice and score answers from the logits of one forward pass, returns calibrated probabilities and serves the /v1/systemone API.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
jev
lev
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
—
68.9%
Calibration error
—
0.115
Valid action rate
—
—
Median latency
—
69 ms
p95 latency
—
—
Evaluation suite
—
S1Bench (13 public subsets, macro)
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 lev?
jev is from TypeSafe AI and lev from Interfaze AI. jev is only available as a hosted API; lev has open weights you can download and run. Both answer choice, score, noul, classify and route questions. jev is licensed proprietary; lev, apache-2.0.
Which is more accurate, jev or lev?
Only lev publishes an accuracy figure (68.9% on S1Bench (13 public subsets, macro)); jev does not, so there is no comparison to make without your own test.
Which is cheaper, jev or lev?
jev: $0.042 / $0 per 1M. lev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run jev or lev locally?
lev yes — systemone pull interfaze-ai/lev downloads its weights. The other is only served as a hosted API.
