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 Situated World Model for fast judgment in agent loops.
Decides
choice, score, noul, classify, route
choice, route, classify
Architecture
jev
trio-spark
Fine-tuned from
—
—
License
proprietary
proprietary
Availability
Hosted API
Hosted API
Hosted by
TypeSafe AI
MachineFi
Input price
$0.042/MTok
$0.042/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 trio-spark-v1?
jev is from TypeSafe AI and trio-spark-v1 from MachineFi. Both are only available as a hosted API. Both answer choice, classify and route questions. Only jev answers score and noul. jev reads up to 32K tokens of state, against 1K tokens for trio-spark-v1.
Which is more accurate, jev or trio-spark-v1?
Neither publishes an accuracy figure. Test both on your own labelled examples.
Which is cheaper, jev or trio-spark-v1?
jev: $0.042 / $0 per 1M. trio-spark-v1: $0.042 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
