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.
A Thai-and-English System One model. Qwen3.5-0.8B continued-pretrained on about 5B Thai tokens, its language-model head replaced by a 256-way slot head (slot 255 abstains), trained on 2–3M decision examples and temperature-calibrated per question type.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
jev
openthai
Fine-tuned from
—
qwen/qwen3.5-0.8b-base
License
proprietary
apache-2.0
Availability
Hosted API
Open weights
Hosted by
TypeSafe AI
—
Input price
$0.042/MTok
—
Decision accuracy
—
74.3%
Calibration error
—
—
Valid action rate
—
—
Median latency
—
40 ms
p95 latency
—
—
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 openthai-systemone?
jev is from TypeSafe AI and openthai-systemone from iApp Technology. jev is only available as a hosted API; openthai-systemone has open weights you can download and run. Both answer choice, score, noul, classify and route questions. jev is licensed proprietary; openthai-systemone, apache-2.0.
Which is more accurate, jev or openthai-systemone?
Only openthai-systemone publishes an accuracy figure (74.3% on Bespoke public subsets (13, macro average)); jev does not, so there is no comparison to make without your own test.
Which is cheaper, jev or openthai-systemone?
jev: $0.042 / $0 per 1M. openthai-systemone: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run jev or openthai-systemone locally?
openthai-systemone yes — systemone pull iapp-technology/openthai-systemone downloads its weights. The other is only served as a hosted API.
