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.
Uprelic's hosted decision API, run on GPUs in Paris. Answers noul, choice and score questions about text, JSON and up to 8 images, with a probability for every option and no generated text, on the same request shape as Jev. No weights; base model and size not disclosed.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
security-one
strom
Fine-tuned from
denis-pplx/autojev-27b
—
License
apache-2.0
proprietary
Availability
Open weights + hosted API
Hosted API
Hosted by
Superagent
Uprelic
Input price
—
$0.042/MTok
Decision accuracy
99.8%
87.0%
Calibration error
—
0.033
Valid action rate
—
—
Median latency
—
136 ms
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 security-one and strom?
security-one is from Superagent and strom from Uprelic. security-one has open weights and a hosted API; strom is only available as a hosted API. Both answer choice, score, noul, classify and route questions. security-one reads up to 256K tokens of state, against 32K tokens for strom. security-one is licensed apache-2.0; strom, proprietary.
Which is more accurate, security-one or strom?
They report on different suites — security-one 99.8% on BIPIA binary prompt-injection detector adaptation (800 rows; Superagent's frozen evaluation, unsafe if P(unsafe) >= 0.70), strom 87.0% on JevBench public set (231 items), the maker's production run of Strom 1.0.7 on 1 Oct 2026 (Open-Jev harness format) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, security-one or strom?
security-one: Hosted, price not published, or free to self-host. strom: $0.042 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run security-one or strom locally?
security-one yes — systemone pull superagent/security-one downloads its weights. The other is only served as a hosted API.
