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.
Small open typed-decision model with calibrated probabilities, first-class Nepali coverage.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
jev
mira
Fine-tuned from
—
jhu-clsp/mmbert-small
License
proprietary
apache-2.0
Availability
Hosted API
Open weights
Hosted by
TypeSafe AI
—
Input price
$0.042/MTok
—
Decision accuracy
—
61.3%
Calibration error
—
0.083
Valid action rate
—
100.0%
Median latency
—
30 ms
p95 latency
—
43 ms
Evaluation suite
—
s1-decision-bench
Latest version
1.13.0
0.1.5
Variants
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 mira?
jev is from TypeSafe AI and mira from SAGEA. jev is only available as a hosted API; mira has open weights you can download and run. Both answer choice, score, noul, classify and route questions. jev is licensed proprietary; mira, apache-2.0.
Which is more accurate, jev or mira?
Only mira publishes an accuracy figure (61.3% on s1-decision-bench); jev does not, so there is no comparison to make without your own test.
Which is cheaper, jev or mira?
jev: $0.042 / $0 per 1M. mira: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run jev or mira locally?
mira yes — systemone pull sagea/mira downloads its weights. The other is only served as a hosted API.
