DecisionTune's 395M decision model: ModernBERT-large fine-tuned with a 4 KB scoring head that scores a marker per option, answering a choice or yes/no question in one encoder pass with a probability for every option. Runs locally on CPU or GPU via PyTorch, MLX or ONNX.
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, noul, route, classify
choice, score, noul, classify, route
Architecture
decisiontune
strom
Fine-tuned from
answerdotai/modernbert-large
—
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
—
136 ms
p95 latency
—
—
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 decisiontune and strom?
decisiontune is from DecisionTune and strom from Uprelic. decisiontune has open weights you can download and run; strom is only available as a hosted API. Both answer choice, noul, route and classify questions. Only strom answers score. strom reads up to 32K tokens of state, against 8K tokens for decisiontune. decisiontune is licensed apache-2.0; strom, proprietary.
Which is more accurate, decisiontune 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)); decisiontune does not, so there is no comparison to make without your own test.
Which is cheaper, decisiontune or strom?
decisiontune: Free (open weights). strom: $0.042 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run decisiontune or strom locally?
decisiontune yes — systemone pull decision-tune/decisiontune downloads its weights. The other is only served as a hosted API.
Evaluation suite
—
JevBench public set (231 items), the maker's production run of Strom 1.0.7 on 1 Oct 2026 (Open-Jev harness format)
