Telnyx's hosted decision models, in beta on Telnyx Inference. One request carries shared state and up to 64 typed questions (choice, yes/no noul, ordered score) and returns a probability per option, with no generated text, on a TypeSafe-compatible /v1/systemone route.
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, route
noul, classify
Architecture
telnyx-decision
laya
Fine-tuned from
—
convaiinnovations/laya-multilingual
License
proprietary
Unspecified; training data includes CC BY-NC-SA 4.0 material (non-commercial), not relicensed
Availability
Hosted API
Open weights
Hosted by
Telnyx
—
Input price
$0.035/MTok
—
Decision accuracy
—
—
Calibration error
—
—
Valid action rate
—
—
Median latency
—
95.4 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 decision-flash and laya-cybersec?
decision-flash is from Telnyx and laya-cybersec from TextCortex. decision-flash is only available as a hosted API; laya-cybersec has open weights you can download and run. Both answer noul and classify questions. Only decision-flash answers choice, score and route. decision-flash is licensed proprietary; laya-cybersec, other.
Which is more accurate, decision-flash or laya-cybersec?
Neither publishes an accuracy figure. Test both on your own labelled examples.
Which is cheaper, decision-flash or laya-cybersec?
decision-flash: $0.035 / $0 per 1M. laya-cybersec: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run decision-flash or laya-cybersec locally?
laya-cybersec yes — systemone pull textcortex/laya-cybersec downloads its weights. The other is only served as a hosted API.
p95 latency
—
149 ms
Evaluation suite
—
TextCortex saved run: 279 single-window inputs, PyTorch batch one