Featherless AI's open server that turns a stock Hugging Face language model into a typed-decision endpoint. It reads the next-token logits for each question and builds the Choice, Score or Noul answer itself; no classifier head is trained and no JSON is generated.
A Situated World Model for fast judgment in agent loops.
Decides
choice, score, noul, classify, route
choice, route, classify
Architecture
simple-jev
trio-spark
Fine-tuned from
google/gemma-4-26b-a4b-it
—
License
apache-2.0
proprietary
Availability
Open weights + hosted API
Hosted API
Hosted by
Featherless AI
MachineFi
Input price
—
$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 simple-jev and trio-spark-v1?
simple-jev is from Featherless AI and trio-spark-v1 from MachineFi. simple-jev has open weights and a hosted API; trio-spark-v1 is only available as a hosted API. Both answer choice, classify and route questions. Only simple-jev answers score and noul. simple-jev is licensed apache-2.0; trio-spark-v1, proprietary.
Which is more accurate, simple-jev or trio-spark-v1?
Neither publishes an accuracy figure. Test both on your own labelled examples.
Which is cheaper, simple-jev or trio-spark-v1?
simple-jev: Hosted, price not published, or free to self-host. trio-spark-v1: $0.042 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run simple-jev or trio-spark-v1 locally?
simple-jev yes — systemone pull featherless-ai/simple-jev downloads its weights. The other is only served as a hosted API.
