A 2.8 MB byte-level transformer for GUI form filling. For each form element it returns one probability per typed option (fill an entity, check, click or skip), using jevlike's option-attention head.
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.
Decides
choice
choice, score, noul, classify, route
Architecture
cua-s1
jev
Fine-tuned from
—
—
License
mit
proprietary
Availability
Open weights
Hosted API
Hosted by
—
TypeSafe AI
Input price
—
$0.042/MTok
Decision accuracy
100.0%
—
Calibration error
—
—
Valid action rate
—
—
Median latency
—
—
p95 latency
—
—
Evaluation suite
196-decision evaluation on real forms
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 cua-s1-forms and jev?
cua-s1-forms is from Cua and jev from TypeSafe AI. cua-s1-forms has open weights you can download and run; jev is only available as a hosted API. Both answer choice questions. Only jev answers score, noul, classify and route. cua-s1-forms is licensed mit; jev, proprietary.
Which is more accurate, cua-s1-forms or jev?
Only cua-s1-forms publishes an accuracy figure (100.0% on 196-decision evaluation on real forms); jev does not, so there is no comparison to make without your own test.
Which is cheaper, cua-s1-forms or jev?
cua-s1-forms: Free (open weights). jev: $0.042 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run cua-s1-forms or jev locally?
cua-s1-forms yes — systemone pull cua/cua-s1-forms downloads its weights. The other is only served as a hosted API.
