Loading comparison…
HEAD TO HEAD
Convai Innovations: laya and Superagent: security-one, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | convai-innovations/laya | superagent/security-one |
|---|---|---|
| Summary | An open-weights System One model from Convai Innovations. A fully fine-tuned ModernBERT-large encoder with a from-scratch decision head that scores one marker per option and answers every question in a single 33–39 ms pass. Runs on your own CPU or GPU. | 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. |
| Decides | choice, score, noul, classify, route | choice, score, noul, classify, route |
| Architecture | laya | security-one |
| Fine-tuned from | answerdotai/modernbert-large | denis-pplx/autojev-27b |
| License | apache-2.0 | apache-2.0 |
| Availability | Open weights | Open weights + hosted API |
| Hosted by | — | Superagent |
| Input price | — | — |
| Decision accuracy | — | 99.8% |
| Calibration error | — | — |
| Valid action rate | — | — |
| Median latency | 39.5 ms | — |
| p95 latency | — | — |
| Evaluation suite | — | BIPIA binary prompt-injection detector adaptation (800 rows; Superagent's frozen evaluation, unsafe if P(unsafe) >= 0.70) |
| Latest version | 2026.09.25 | 2026.09 |
| Variants | multilingual, tokenizer, typed-decisions, eval, encoder | — |
| Size of latest version | 2.2 GB | — |
| Files | 19 | 0 |
| Downloads | 139 | 0 |
| Stars | 0 | 0 |
| Tags | system-one, encoder, modernbert, rlcd, multilingual, 421m | system-one, security, prompt-injection, qwen, sglang, hosted, gated, 27b |
| Updated | Oct 7, 2026 | Oct 7, 2026 |
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.
laya is from Convai Innovations and security-one from Superagent. laya 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. security-one reads up to 256K tokens of state, against 512 tokens for laya. laya is the smaller model, at 421M parameters to 27B.
Only security-one publishes an accuracy figure (99.8% on BIPIA binary prompt-injection detector adaptation (800 rows; Superagent's frozen evaluation, unsafe if P(unsafe) >= 0.70)); laya does not, so there is no comparison to make without your own test.
laya: Free (open weights). security-one: Hosted, price not published, or free to self-host. Open weights cost nothing per call beyond your own hardware.
Yes, both: systemone pull convai-innovations/laya and systemone pull superagent/security-one download the weights.