A 144M-parameter System One model on the multilingual mmBERT-small encoder. Takes a state, a question and 2 to 20 options and returns one decision with probabilities for choice, score and yes/no questions, on a CPU.
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
julia
span
Fine-tuned from
jhu-clsp/mmbert-small
—
License
apache-2.0
proprietary
Availability
Open weights
Hosted API
Hosted by
—
Respan
Input price
—
$0.020/MTok
Decision accuracy
73.2%
—
Calibration error
—
—
Valid action rate
—
—
Median latency
—
—
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 julia-1 and span-01?
julia-1 is from Supersonic Labs and span-01 from Respan. julia-1 has open weights you can download and run; span-01 is only available as a hosted API. Both answer noul and classify questions. Only julia-1 answers choice, score and route. julia-1 is licensed apache-2.0; span-01, proprietary.
Which is more accurate, julia-1 or span-01?
Only julia-1 publishes an accuracy figure (73.2% on typed-decisions test set (400 cases, 2,000 questions)); span-01 does not, so there is no comparison to make without your own test.
Which is cheaper, julia-1 or span-01?
julia-1: Free (open weights). span-01: $0.02 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run julia-1 or span-01 locally?
julia-1 yes — systemone pull supersonic-labs/julia-1 downloads its weights. The other is only served as a hosted API.
Evaluation suite
typed-decisions test set (400 cases, 2,000 questions)
