TypeSafe's Jev: a "Decision Model" LLM That Returns Floats at $0.042/M Input Tokens
ariG23498 · x · 2026-10-23
TypeSafe AI unveiled Jev, which it calls the first "System One model" (others prefer "decision model"): text in, floating-point outputs out — categories, yes/no answers, and ratings with confidence scores.
- Accepts a state object (string, string array, or key-value pairs) plus questions; supports Bernoulli-style yes/no ("Noul"), classification, and ratings
- Pricing is input-only — output is free — at $0.042/million tokens, cheaper than GPT-5 Nano's $0.05/M, and fast
- Simon Willison's caveat: it's a regression toward black-box ML — you get a float back and can't ask which signals drove a spam verdict
More from Models
- Microsoft's MAI-Base-2 scaling ladder pegs the L42 run at ~1.8×10^23 FLOPs — teortaxesTex · 2026-10-23
- Local model agentic coding benchmark: 27B matches 125B, tool-calling is the lever — Joralk_ · 2026-10-23
- NVIDIA open-sources PersonaPlex-7B, a full-duplex voice AI model that listens and talks simultaneously — solyarisoftware · 2026-10-23
- NVIDIA's KumoRFM-2: a foundation model that predicts churn, fraud and demand straight from relational databases — solyarisoftware · 2026-10-23
- Gemini Analyzes Whether a Simple 'Hi' Is a Jailbreak Attempt in Its Thinking Steps — OldIntroduction2909 · 2026-10-23
- 5 Essential Reads to Master Pi's Agent Harness, from Onboarding to Source Code — solyarisoftware · 2026-10-23