Laya fine-tune that scans untrusted text (extracted files, knowledge-base documents, agent skills, tool descriptions) for prompt injection and data exfiltration in English and German, as a noul question answered in one forward pass. 322M parameters, PyTorch and ONNX.
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
noul, classify
choice, score, noul, classify, route
Architecture
laya
strom
Fine-tuned from
convaiinnovations/laya-multilingual
—
License
Unspecified; training data includes CC BY-NC-SA 4.0 material (non-commercial), not relicensed
proprietary
Availability
Open weights
Hosted API
Hosted by
—
Uprelic
Input price
—
$0.042/MTok
Decision accuracy
—
87.0%
Calibration error
—
0.033
Valid action rate
—
—
Median latency
95.4 ms
136 ms
p95 latency
149 ms
—
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 laya-cybersec and strom?
laya-cybersec is from TextCortex and strom from Uprelic. laya-cybersec has open weights you can download and run; strom is only available as a hosted API. Both answer noul and classify questions. Only strom answers choice, score and route. strom reads up to 32K tokens of state, against 1K tokens for laya-cybersec. laya-cybersec is licensed other; strom, proprietary.
Which is more accurate, laya-cybersec or strom?
Only strom publishes an accuracy figure (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)); laya-cybersec does not, so there is no comparison to make without your own test.
Which is cheaper, laya-cybersec or strom?
laya-cybersec: Free (open weights). strom: $0.042 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Which is faster, laya-cybersec or strom?
By their publishers’ figures, laya-cybersec answers in about 95.4 ms at the median and strom in about 136 ms — measured on different hardware, so treat it as a rough guide.
Can I run laya-cybersec or strom locally?
laya-cybersec yes — systemone pull textcortex/laya-cybersec downloads its weights. The other is only served as a hosted API.
Evaluation suite
TextCortex saved run: 279 single-window inputs, PyTorch batch one
JevBench public set (231 items), the maker's production run of Strom 1.0.7 on 1 Oct 2026 (Open-Jev harness format)
