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.
Upstage's structured decision model, a System One endpoint on Solar Mini 4. Returns a choice, a score or a yes/no answer with a probability read from the model, in one forward pass, on the same /v1/systemone schema as Jev.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
jev
solar
Fine-tuned from
—
—
License
proprietary
proprietary
Availability
Hosted API
Hosted API
Hosted by
TypeSafe AI
Upstage
Input price
$0.042/MTok
$0.10/MTok
Decision accuracy
—
—
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 jev and solar-decide?
jev is from TypeSafe AI and solar-decide from Upstage. Both are only available as a hosted API. Both answer choice, score, noul, classify and route questions. solar-decide reads up to 512K tokens of state, against 32K tokens for jev.
Which is more accurate, jev or solar-decide?
Neither publishes an accuracy figure. Test both on your own labelled examples.
Which is cheaper, jev or solar-decide?
jev: $0.042 / $0 per 1M. solar-decide: $0.1 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
