Small open typed-decision model with calibrated probabilities, first-class Nepali coverage.
Superagent's 27B security decision model. It scores 2 to 16 supplied options in one forward pass and returns a probability for each, for triaging prompt injection, agent tool calls, code changes, logs and alerts. Apache-2.0 weights (gated, auto-approved) plus a hosted API.
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 security-one?
mira is from SAGEA and security-one from Superagent. mira has open weights you can download and run; security-one has open weights and a hosted API. Both answer choice, score, noul, classify and route questions.
Which is more accurate, mira or security-one?
They report on different suites — mira 61.3% on s1-decision-bench, security-one 99.8% on BIPIA binary prompt-injection detector adaptation (800 rows; Superagent's frozen evaluation, unsafe if P(unsafe) >= 0.70) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, mira or security-one?
mira: Free (open weights). security-one: Hosted, price not published, or free to self-host. Open weights cost nothing per call beyond your own hardware.
Can I run mira or security-one locally?
Yes, both: systemone pull sagea/mira and systemone pull superagent/security-one download the weights.
