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.
meraGPT's hosted decision model (state-decider-1). Answers yes/no, choice and rubric-score questions over one state as calibrated distributions in a single pass, on the System One schema, so the typesafe-sdk works by changing its base URL.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
jev
state-decider
Fine-tuned from
—
—
License
proprietary
proprietary
Availability
Hosted API
Hosted API
Hosted by
TypeSafe AI
meraGPT
Input price
$0.042/MTok
$0.030/MTok
Decision accuracy
—
76.8%
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 state-decider-1?
jev is from TypeSafe AI and state-decider-1 from meraGPT. Both are only available as a hosted API. Both answer choice, score, noul, classify and route questions. jev reads up to 32K tokens of state, against 4K tokens for state-decider-1.
Which is more accurate, jev or state-decider-1?
Only state-decider-1 publishes an accuracy figure (76.8% on typed-decisions benchmark (400 cases, 2,000 decisions; teacher-ensemble references), single run); jev does not, so there is no comparison to make without your own test.
Which is cheaper, jev or state-decider-1?
jev: $0.042 / $0 per 1M. state-decider-1: $0.03 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run jev or state-decider-1 locally?
Neither: both are only served as hosted APIs.
—
typed-decisions benchmark (400 cases, 2,000 decisions; teacher-ensemble references), single run
