Small open typed-decision model with calibrated probabilities, first-class Nepali coverage.
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
mira
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
74.5%
—
Calibration error
0.025
—
Valid action rate
100.0%
—
Median latency
30 ms
—
p95 latency
43 ms
—
Evaluation suite
s1-decision-bench
—
Latest version
0.1.4
2026.09
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 mira and span-01?
mira is from SAGEA and span-01 from Respan. mira has open weights you can download and run; span-01 is only available as a hosted API. Both answer noul and classify questions. Only mira answers choice, score and route. mira is licensed apache-2.0; span-01, proprietary.
Which is more accurate, mira or span-01?
Only mira publishes an accuracy figure (74.5% on s1-decision-bench); span-01 does not, so there is no comparison to make without your own test.
Which is cheaper, mira or span-01?
mira: Free (open weights). span-01: $0.02 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run mira or span-01 locally?
mira yes — systemone pull sagea/mira downloads its weights. The other is only served as a hosted API.