Fastino's open-weight decision model. A DeBERTa-v3-large encoder that scores label sets supplied at runtime, answers single-label, multi-label, yes/no and ordinal questions in one pass, and extracts spans and relations.
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.
Decides
choice, score, noul, classify, extract, route
noul, classify
Architecture
gliner2
laya
Fine-tuned from
fastino/gliner2-large-v1
convaiinnovations/laya-multilingual
License
apache-2.0
Unspecified; training data includes CC BY-NC-SA 4.0 material (non-commercial), not relicensed
Availability
Open weights + hosted API
Open weights
Hosted by
Fastino
—
Input price
—
—
Decision accuracy
60.2%
—
Calibration error
—
—
Valid action rate
—
—
Median latency
38.3 ms
95.4 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 gliner2-5-decide and laya-cybersec?
gliner2-5-decide is from Fastino Labs and laya-cybersec from TextCortex. gliner2-5-decide has open weights and a hosted API; laya-cybersec has open weights you can download and run. Both answer noul and classify questions. Only gliner2-5-decide answers choice, score, extract and route. laya-cybersec is the smaller model, at 322M parameters to 340M. gliner2-5-decide is licensed apache-2.0; laya-cybersec, other.
Which is more accurate, gliner2-5-decide or laya-cybersec?
Only gliner2-5-decide publishes an accuracy figure (60.2% on Fastino fast-decisions suite (17 datasets)); laya-cybersec does not, so there is no comparison to make without your own test.
Which is cheaper, gliner2-5-decide or laya-cybersec?
gliner2-5-decide: Hosted, price not published, or free to self-host. laya-cybersec: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, gliner2-5-decide or laya-cybersec?
By their publishers’ figures, gliner2-5-decide answers in about 38.3 ms at the median and laya-cybersec in about 95.4 ms — measured on different hardware, so treat it as a rough guide.
Can I run gliner2-5-decide or laya-cybersec locally?
Yes, both: systemone pull fastino-labs/gliner2-5-decide and systemone pull textcortex/laya-cybersec download the weights.
—
149 ms
Evaluation suite
Fastino fast-decisions suite (17 datasets)
TextCortex saved run: 279 single-window inputs, PyTorch batch one
