A local, Jev-compatible decision model from Rizzo AI Academy. XHToken's Spark-X2.5-4B with a merged typed-decisions LoRA, run on llama.cpp; yes/no, choice and score questions share one prefill of the state and are read from the answer-letter logits. No text is generated.
Upstage's structured decision model, a System One endpoint on Solar Mini 4. Returns a choice, a score or a yes/no answer with a probability read from the model, in one forward pass, on the same /v1/systemone schema as Jev.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
rizzo-flow
solar
Fine-tuned from
xhtoken/spark-x2.5-4b
—
License
apache-2.0
proprietary
Availability
Open weights
Hosted API
Hosted by
—
Upstage
Input price
—
$0.10/MTok
Decision accuracy
64.8%
—
Calibration error
0.112
—
Valid action rate
—
—
Median latency
195 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 rizzo-flow and solar-decide?
rizzo-flow is from Rizzo AI Academy and solar-decide from Upstage. rizzo-flow has open weights you can download and run; solar-decide is only available as a hosted API. Both answer choice, score, noul, classify and route questions. rizzo-flow is licensed apache-2.0; solar-decide, proprietary.
Which is more accurate, rizzo-flow or solar-decide?
Only rizzo-flow publishes an accuracy figure (64.8% on LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions), Q8_0); solar-decide does not, so there is no comparison to make without your own test.
Which is cheaper, rizzo-flow or solar-decide?
rizzo-flow: Free (open weights). solar-decide: $0.1 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run rizzo-flow or solar-decide locally?
rizzo-flow yes — systemone pull rizzo-ai-academy/rizzo-flow downloads its weights. The other is only served as a hosted API.
Evaluation suite
LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions), Q8_0
