Jev Models

TypeSafe AI's product site for Jev, its first System One Model: typed decisions with calibrated confidence, performance and pricing claims, a FAQ, and links to the docs, console, workflow evals, and launch post.

A TypeSafe blog essay arguing that in ML the order that matters is doing the right task, then data, then compute, then algorithms, using the InstructGPT result as its example.

Cloudflare Workers AI's model page for typesafe/jev: run the structured evaluation model through an env.AI.run binding or the REST /ai/run endpoint, with typed Noul, Choice, and Score questions and worked examples.

Wikipedia's article on Jev: TypeSafe AI, the September 15, 2026 early-access release of jev-1.13.0, the Choice, Score, and Noul primitives, RLCD training, and the unpublished weights and technical paper.

The Register's launch report on TypeSafe AI's Jev: the $40 million raise, typed probabilistic decisions, the Doom demo, the 70-500 ms latency and $0.042/MTok pricing claims, and the structured-output caveat.

Tom's Hardware's launch report on Jev, covering how the API takes program state and typed statements and returns yes/no answers, choices, or probability distributions with confidence values.

Latent Space's AINews roundup of launch day: the Jev thread atop Hacker News, the RLCD decision-model framing, and community readings that compare it to DSPy-style typed signatures for routing and scoring.

The Hacker News launch thread for Jev, with the CEO agreeing the shape is a zero-shot classifier and commenters mapping it to encoders, constrained decoding, and typed classification.

News analysis arguing Jev's refusal to generate text is the feature, covering the $40M seed, the OpenAI-veteran founding team, and what structured, thresholdable decisions mean for agent pipelines.

An independent benchmark of hosted Jev against six LLMs on PubMedQA, Banking77, and HelpSteer2, scoring decisions against human labels and reporting per-board results for each model.

A Telegram channel X-ray that pulls up to 1,500 public posts from the past year and has Jev rate each one, tallying news, ads, jokes, and clickbait into a shareable card.

A semantic mapping playground where you choose any two concepts as axes, add words or phrases, and Jev places each one by how strongly it relates to both axes.

The model card for jev-1.13.0: $42 per billion input tokens with free output, a 64k context, 250k tokens per second, and how to list the models your account can call.

The idea behind Jev: models that return typed decisions and probabilities instead of generated text, named after Kahneman's fast-thinking System 1, with confidence to route around uncertainty.