Skip to content

security-one-27b

SuperagentDecision modelOpen weights

security-one-27b by Superagent is a decision model: it answers typed questions with a probability for each allowed answer instead of generating text.

Pricing

No hosted price is listed. The weights are open: the cost is your own compute.

Specifications

Provider
Superagent
Parameters
27B
Released
Sep 2026
Open weights
Yes
Question types
Choice (one of N options), Score (ordered rubric), Yes / no
Mechanism
Decoder LM with a decision readout
Backbone
denis-pplx/autojev-27b
Jev-compatible request
Yes
Runs on CPU
No
License
apache-2.0
Hugging Face
superagent-ai/security-one-27b

Compare security-one-27b with…

FAQ

How much does security-one-27b cost?

security-one-27b has no hosted price listed; its weights are open, so the cost is the compute you run it on.

What questions can security-one-27b answer?

security-one-27b answers choice (one of n options), score (ordered rubric), yes / no questions, returning a probability for each allowed answer.

Is security-one-27b well calibrated?

No calibration measurement for security-one-27b is recorded yet.

Is security-one-27b open weight, and can it run on a CPU?

Yes, security-one-27b has open weights. It needs a GPU to run at useful speed.

Data as of 2026-10-14. Source: Metatext decision-model catalogue, 2026-10-14 (Hugging Face). Pricing is per 1M tokens (USD); confirm with the provider before production use.