systemonemodels.pro

A new class of AI model you can finally put in a hot loop

On Sep 15, 2026, TypeSafe AI announced Jev — the first commercial System One Model: a frontier model that gives up text generation and instead makes fast, calibrated, structured decisions that software can call directly. This independent site tracks the category: what it is, what it's good for, and tools to evaluate it.

This is an independent, unofficial resource site. Not affiliated with or endorsed by TypeSafe AI. Claims below are labeled as vendor claims until independent benchmarks exist. Sources & dating →

What is a System One Model?

Naming borrowed from psychology's System 1 / System 2: LLMs are System 2 — slow, deliberative text generators. A System One Model is the opposite shape: unstructured state in → typed probabilistic decision out, in a single pass, with calibrated probabilities. No prose. No hallucinated strings. Think of it as a frontier-intelligence function call.

⚡ Two orders of magnitude faster vendor claim

TypeSafe reports Jev matches LLM intelligence on decision tasks at ~100× the speed and efficiency. Site will add measured numbers when available.

🎯 Cannot hallucinate by design

No string generation means no invented facts. Output is a probability distribution over the options you define.

📐 Calibrated probabilities RLCD

Trained with Reinforcement Learning for Calibrated Decisions — the numbers it returns are meant to be trusted as numbers.

Use it for decisions, not conversations

Routing, moderation, field extraction, risk scoring, A/B variant picking, alert triage — anywhere you currently bolt a JSON-mode prompt onto a chat model and pray.

🧮 Cost & Latency Calculator

Model your current LLM function-calling spend vs. a System One approach. Shareable result card.

Open calculator →

🛠 Decision Schema Generator

Pick a scenario, define your options, get the decision schema + curl/JS/Python call snippets.

Generate a schema →

📚 Learn: Jev vs LLM function calling

FAQ, comparison tables, ecosystem tracker (open-source lookalikes, tools), with every claim sourced.

Read the guide →

Quick facts

ItemStatus (2026-09-20)
ModelJev (first System One Model), by TypeSafe AI — founded by Diogo Almeida (ex-OpenAI, research behind ChatGPT instruction-following)
AnnouncedSep 15, 2026 — HN discussion 1900+ points, official post
AvailabilityEarly access / waitlist at TypeSafe; also listed on Cloudflare Workers AI (typesafe/jev)
Public pricingNot published yet — our calculator lets you model it with your own assumed price
Open-source lookalikesEarly research starters exist (e.g. jevlike, MIT) — toy-scale, NOT Jev-equivalent; see ecosystem notes