Simon Willison September 21, 2026

Jev introduces a new shape of LLM - System One, aka Decision Models

TypeSafe AI’s new model, Jev, is a ‘System One’ or decision model that takes text or semi‑structured data as input and outputs floating‑point probabilities for yes/no, choice, or score questions, rather than text. It charges only for input tokens ($0.042/million) and offers free output, making it cheaper and faster than typical LLMs. The API lets users build a state object (string, array, or key‑value pairs) and query it with multiple questions, receiving confidence scores and probability distributions for each answer.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at Simon Willison.

Simon Willison

Oct 6

llm-openai-decisions 0.1a0

Simon Willison announces the release of the llm-openai-decisions 0.1a0 plugin, which interfaces with OpenAI’s new Jev-style Decisions API. The plugin, inspired by llm-typesafe, supports image and text input and offers the same three question types (yes/no, choices, scores) as Jev, with pricing at 10¢ per million input tokens. Installation is simple via `llm install llm-openai-decisions`, and an example query demonstrates image-based evaluation.

llms agents

arXiv AI

Sep 30

Evaluating and Benchmarking the System One Model Jev

arXiv:2609.37647v1 Announce Type: cross Abstract: Jev is a commercial System One model from TypeSafe AI that does not generate text: given a state and typed questions, it returns a choice from fixed...

By Tobias Deu{\ss}er, Lorenz Sparrenberg, Rafet Sifa

benchmarks

Towards Data Science

Oct 15

Jev Your Engines: Seven Open Decision Models vs. a Generative LLM

The article compares seven open decision models with a generative large language model (LLM) in a hands‑on repository called Jev. It evaluates each model based on routing accuracy, latency, and output reliability. The comparison provides practical insights into how these models perform in real‑world scenarios.

By Lambert Leong

llms

arXiv Machine Learning

Oct 22

Our Own Jev: Typed Decisions in One Forward Pass, from an In-House Judge to Open LoRA Models

arXiv:2610. 29052v1 Announce Type: cross Abstract: A typed decision maps evidence, a question and a fixed set of options to a probability for every option, computed in one forward pass, by reading a language model's logits or a small head over its hidden states, instead of generating and parsing text.

By Yuchuan Weng, Chi Liu, Xin Chen, Srinivasan Manoharan

llms agents fine-tuning benchmarks

arXiv AI

Oct 15

Releasing the Inner Jev: A Simple Recipe for Open Decision Models

arXiv:2610.17205v1 Announce Type: new Abstract: LLM-based decision-making systems, also called System One models, have recently gained popularity, most notably through Jev (Almeida, 2026). Given a ty...

By Jonathan Geuter, Andrew Cheng, David Alvarez-Melis

llms fine-tuning benchmarks

Towards Data Science

Sep 25

Jev vs. LLMs: When AI Moves from Generation to Decision-Making

The article reports on a benchmark where the author evaluated TypeSafe AI’s Jev against large language models (LLMs) across 3,080 classification tasks, comparing metrics such as accuracy, latency, calibration, and confidence. It examines whether Jev can serve as a practical decision layer for AI systems, effectively moving AI from merely generating outputs to making informed decisions.

By Nhu Hoang