Typed decisions from Google's frozen Gemma-4-12B-it, with no fine-tuning. A small shim over unmodified vLLM letters the options, reads the model's own probability for each letter at one answer position and applies one calibration temperature; one output token per decision.
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.
Decides
choice, score, noul
choice, score, noul, classify, route
Architecture
cygnet
jev
Fine-tuned from
google/gemma-4-12b-it
—
License
mit
proprietary
Availability
Open weights
Hosted API
Hosted by
—
TypeSafe AI
Input price
—
$0.042/MTok
Decision accuracy
87.9%
—
Calibration error
—
—
Valid action rate
—
—
Median latency
50 ms
—
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 cygnet and jev?
cygnet is from Blockbrain Labs and jev from TypeSafe AI. cygnet has open weights you can download and run; jev is only available as a hosted API. Both answer choice, score and noul questions. Only jev answers classify and route. jev reads up to 32K tokens of state, against 16K tokens for cygnet. cygnet is licensed mit; jev, proprietary.
Which is more accurate, cygnet or jev?
Only cygnet publishes an accuracy figure (87.9% on JevBench public set (231 items), JevBench CLI); jev does not, so there is no comparison to make without your own test.
Which is cheaper, cygnet or jev?
cygnet: Free (open weights). jev: $0.042 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run cygnet or jev locally?
cygnet yes — systemone pull blockbrain-labs/cygnet downloads its weights. The other is only served as a hosted API.
