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.
OpenAI's decision endpoint, announced at DevDay 2026. It focuses GPT-6 Luna on developer-defined questions that have a finite set of predefined answers, with text or image context, for classification, routing and an agent's next action.
Decides
choice
choice, classify, route
Architecture
cua-s1
gpt-6-luna
Fine-tuned from
—
—
License
mit
proprietary
Availability
Open weights
Hosted API
Hosted by
—
OpenAI
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 decisions-api?
cua-s1-forms is from Cua and decisions-api from OpenAI. cua-s1-forms has open weights you can download and run; decisions-api is only available as a hosted API. Both answer choice questions. Only decisions-api answers classify and route. cua-s1-forms is licensed mit; decisions-api, proprietary.
Which is more accurate, cua-s1-forms or decisions-api?
Only cua-s1-forms publishes an accuracy figure (100.0% on 196-decision evaluation on real forms); decisions-api does not, so there is no comparison to make without your own test.
Which is cheaper, cua-s1-forms or decisions-api?
cua-s1-forms: Free (open weights). decisions-api: Hosted, price not published. Open weights cost nothing per call beyond your own hardware.
Can I run cua-s1-forms or decisions-api locally?
cua-s1-forms yes — systemone pull cua/cua-s1-forms downloads its weights. The other is only served as a hosted API.
