Skip to content
System One

System One models return decisions, not text.

A System One model is an AI model that returns typed answers and calibrated probabilities instead of generated text. You give it content and typed questions; it returns the selected option, a probability for every option, and a confidence value. Jev, from TypeSafe AI, was the first one, announced on 15 September 2026.

What is a System One modelBrowse examples

427 examples18 use cases8 recipes1 model

The three question types

Every System One call is a state plus questions. A question is one of three shapes, and each returns a number you can branch on.

Choice

Pick one option from a set you define, up to 255 of them. You get the winning option, a probability for every option, and one confidence number.

Confidence0.82
Choice in the glossary

Score

Rate the content against ordered levels you write, 2 to 10 of them. The answer is a probability-weighted mean, so it can land between levels.

Confidence0.64
Score in the glossary

Noul

Ask a yes/no question and get one number from 0 to 1: the probability that the answer is yes. There is no separate confidence value.

Probability0.91
Noul in the glossary

Models

All models

Every model announced as a System One model, with its prices, limits and sources.

Jev

TypeSafe AI
Early access

The first System One model: typed answers and calibrated probabilities, never generated text.

ChoiceScoreNoul
Input price
$0.042/MTok
Latency
70-500 ms

More vendors will appear here as they ship System One models. Know one? Submit it.

Featured examples

All examples

Projects, tools, cookbooks and write-ups from people building on these models.

Project

openjev

Attempt to run a Jev-style System One decision model locally on a single RTX 3090. Companion site at openjev.com.

TheoLeeCJ882Openopenjev on github.com
Project

jevlike

Open reimplementation that trains a small model to choose among a changing list of text options, emitting one probability per option in a single forward pass. Ships Doom, chess and Wikispeedia demos.

vinnylarouge703Openjevlike on github.com
Choice

Use cases by category

All use cases

The patterns people reach for, grouped by the job they do.

Recipes

All recipes

Code you can paste, with the thresholds left in your code.

pythontsStarter

Check a citation against its source with a noul

An LLM cites a document for a claim. This recipe checks the citation in two steps: a plain string match that catches quotes missing from the source, then one noul question that returns the probability the quoted section actually supports the claim. Your code turns that probability into a verdict.

Noul
pythontsStarter

Route a support ticket with one Choice

A single Choice question sorts an inbound support ticket into one of four queues and returns a probability for every option. The model supplies the label and the certainty; your router applies the thresholds, holds the doubtful tickets for a human, and keeps every side effect in your code rather than in the prompt.

Choice
pythontsIntermediate

Ask four questions in one call and route in code

A support ticket needs a category, a severity, and two yes/no facts that only matter for one category each. Asking in sequence costs four round trips and four copies of the ticket. This recipe sends all four questions in one call, including the speculative ones, and lets the routing code ignore what it does not need.

ChoiceNoulScore
pythontsIntermediate

Gate a destructive action on confidence

One Choice names the action the user is asking for and one Noul says whether the message confirms it. Two numbers come back, and a table of per-action thresholds in your code decides the rest: a read runs at moderate confidence, a refund needs more, and anything below the floor goes to a person.

ChoiceNoul

Guides

All guides

Start here if the category is new to you.

What is a System One model?

A System One model returns typed, calibrated decisions instead of text. What that means, where the name comes from, and how Jev fits.

Updated

System One models vs LLMs

System One models return typed decisions; LLMs return text. A side-by-side on output, latency, cost, hallucination and when each one wins.

Updated

Is Jev just a zero-shot classifier?

Engineers called Jev a zero-shot classifier within hours of launch. What the comparison gets right, what it misses, and what is actually new.

Updated

Latest additions

All examples

The eight most recent entries in the directory.

Built something with a System One model?

Send the link. Projects, tools, cookbooks, videos, write-ups and threads all count. Every entry is checked and credited to its author.

Submit an example