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.
Liquid AI's first decision model, served only through the Liquid API. Returns Choice, Score and Noul answers with probability distributions and zero output tokens, on the /v1/systemone request shape used by TypeSafe's SDK.
Decides
choice
choice, score, noul, classify, route
Architecture
cua-s1
d1
Fine-tuned from
—
—
License
mit
proprietary
Availability
Open weights
Hosted API
Hosted by
—
Liquid AI
Input price
—
—
Decision accuracy
100.0%
—
Calibration error
—
—
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 cua-s1-forms and d1?
cua-s1-forms is from Cua and d1 from Liquid AI. cua-s1-forms has open weights you can download and run; d1 is only available as a hosted API. Both answer choice questions. Only d1 answers score, noul, classify and route. cua-s1-forms is licensed mit; d1, proprietary.
Which is more accurate, cua-s1-forms or d1?
Only cua-s1-forms publishes an accuracy figure (100.0% on 196-decision evaluation on real forms); d1 does not, so there is no comparison to make without your own test.
Which is cheaper, cua-s1-forms or d1?
cua-s1-forms: Free (open weights). d1: Hosted, price not published. Open weights cost nothing per call beyond your own hardware.
Can I run cua-s1-forms or d1 locally?
cua-s1-forms yes — systemone pull cua/cua-s1-forms downloads its weights. The other is only served as a hosted API.
