An open Jev-style decision model by Andy Zhang: a LoRA adapter on Gemma 4 26B-A4B (also on Gemma 4 12B) that reads a state and returns a temperature-calibrated probability for every option of a yes/no, choice or score question in one forward pass.
Uprelic's hosted decision API, run on GPUs in Paris. Answers noul, choice and score questions about text, JSON and up to 8 images, with a probability for every option and no generated text, on the same request shape as Jev. No weights; base model and size not disclosed.
Decides
choice, score, noul
choice, score, noul, classify, route
Architecture
ajev
strom
Fine-tuned from
google/gemma-4-26b-a4b-it
—
License
apache-2.0
proprietary
Availability
Open weights
Hosted API
Hosted by
—
Uprelic
Input price
—
$0.042/MTok
Decision accuracy
—
87.0%
Calibration error
—
0.033
Valid action rate
—
—
Median latency
49 ms
136 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 ajev and strom?
ajev is from Andy Zhang and strom from Uprelic. ajev has open weights you can download and run; strom is only available as a hosted API. Both answer choice, score and noul questions. Only strom answers classify and route. ajev is licensed apache-2.0; strom, proprietary.
Which is more accurate, ajev or strom?
Only strom publishes an accuracy figure (87.0% on JevBench public set (231 items), the maker's production run of Strom 1.0.7 on 1 Oct 2026 (Open-Jev harness format)); ajev does not, so there is no comparison to make without your own test.
Which is cheaper, ajev or strom?
ajev: Free (open weights). strom: $0.042 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Which is faster, ajev or strom?
By their publishers’ figures, ajev answers in about 49 ms at the median and strom in about 136 ms — measured on different hardware, so treat it as a rough guide.
Can I run ajev or strom locally?
ajev yes — systemone pull andy-zhang/ajev downloads its weights. The other is only served as a hosted API.
Sequential requests, the maker's own measurement
JevBench public set (231 items), the maker's production run of Strom 1.0.7 on 1 Oct 2026 (Open-Jev harness format)
