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.
Respan's behaviour-scoring model for evals, guardrails and monitoring. For each plain-language behaviour you define, it reads a conversation or agent trace and returns the probability the behaviour is present, absent or not observable, in one forward pass.
Decides
choice, score, noul, classify, route
noul, classify
Architecture
rizzo-flow
span
Fine-tuned from
xhtoken/spark-x2.5-4b
—
License
apache-2.0
proprietary
Availability
Open weights
Hosted API
Hosted by
—
Respan
Input price
—
$0.020/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 span-01?
rizzo-flow is from Rizzo AI Academy and span-01 from Respan. rizzo-flow has open weights you can download and run; span-01 is only available as a hosted API. Both answer noul and classify questions. Only rizzo-flow answers choice, score and route. rizzo-flow is licensed apache-2.0; span-01, proprietary.
Which is more accurate, rizzo-flow or span-01?
Only rizzo-flow publishes an accuracy figure (64.8% on LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions), Q8_0); span-01 does not, so there is no comparison to make without your own test.
Which is cheaper, rizzo-flow or span-01?
rizzo-flow: Free (open weights). span-01: $0.02 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run rizzo-flow or span-01 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
