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.
Respan's behaviour-scoring model for evals, guardrails and monitoring. For each plain-language behaviour you define, it reads a conversation or agent trace and returns the probability the behaviour is present, absent or not observable, in one forward pass.
Decides
choice, score, noul, classify, route
noul, classify
Architecture
jev
span
Fine-tuned from
—
—
License
proprietary
proprietary
Availability
Hosted API
Hosted API
Hosted by
TypeSafe AI
Respan
Input price
$0.042/MTok
$0.020/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 span-01?
jev is from TypeSafe AI and span-01 from Respan. Both are only available as a hosted API. Both answer noul and classify questions. Only jev answers choice, score and route.
Which is more accurate, jev or span-01?
Neither publishes an accuracy figure. Test both on your own labelled examples.
Which is cheaper, jev or span-01?
jev: $0.042 / $0 per 1M. span-01: $0.02 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
