An open family of System One models. A LoRA adapter plus a pointer head on a frozen Qwen base returns a distribution per typed question in one forward pass, serves TypeSafe's /v1/systemone contract, and ships a fitted temperature with every checkpoint.
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
kev
span
Fine-tuned from
qwen/qwen3.5-4b-base
—
License
apache-2.0
proprietary
Availability
Open weights
Hosted API
Hosted by
—
Respan
Input price
—
$0.020/MTok
Decision accuracy
83.8%
—
Calibration error
0.042
—
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 kev and span-01?
kev is from Jared Palmer and span-01 from Respan. kev has open weights you can download and run; span-01 is only available as a hosted API. Both answer noul and classify questions. Only kev answers choice, score and route. kev is licensed apache-2.0; span-01, proprietary.
Which is more accurate, kev or span-01?
Only kev publishes an accuracy figure (83.8% on transfer-v4 (locked, out of domain)); span-01 does not, so there is no comparison to make without your own test.
Which is cheaper, kev or span-01?
kev: Free (open weights). span-01: $0.02 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run kev or span-01 locally?
kev yes — systemone pull jared-palmer/kev downloads its weights. The other is only served as a hosted API.
