A training-free layer that turns an open LLM into a decision model. It reads typed choice, yes/no and score answers from one prefill, removes option-order bias with no labels and, from a few hundred labels, calibrates or fits a closed-form head. Weights stay untouched.
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
anyjev
span
Fine-tuned from
qwen/qwen3-8b
—
License
apache-2.0
proprietary
Availability
Open weights
Hosted API
Hosted by
—
Respan
Input price
—
$0.020/MTok
Decision accuracy
77.1%
—
Calibration error
0.034
—
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 anyjev and span-01?
anyjev is from Nokia and span-01 from Respan. anyjev has open weights you can download and run; span-01 is only available as a hosted API. Both answer noul and classify questions. Only anyjev answers choice, score and route. anyjev is licensed apache-2.0; span-01, proprietary.
Which is more accurate, anyjev or span-01?
Only anyjev publishes an accuracy figure (77.1% on LocalLLaMA/typed-decisions (2,000 held-out decisions), L2 with 300 labels per question); span-01 does not, so there is no comparison to make without your own test.
Which is cheaper, anyjev or span-01?
anyjev: Free (open weights). span-01: $0.02 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run anyjev or span-01 locally?
anyjev yes — systemone pull nokia/anyjev downloads its weights. The other is only served as a hosted API.
Evaluation suite
LocalLLaMA/typed-decisions (2,000 held-out decisions), L2 with 300 labels per question
