Jev Model Guide · TypeSafe Jev tutorial & resources

Jev is the first System One model from TypeSafe AI, released in September 2026. You send a state (context) and a set of typed questions; it returns structured answers your code can consume directly. It is not a chatbot and generates no text — it only makes decisions.

This site is maintained by the independent community with no affiliation with TypeSafe AI. Every fact carries a source and verification date, and community opinions are strictly separated from official claims (see About this site).

Understanding Jev

What it is, why it’s fast, and how it differs from an LLM. Start reading →

Three question types

Choice, Score, and Noul — and how to ask many questions in one request. Capabilities →

Guides

From curl to the official SDKs, with the full HTTP reference including errors, limits, and retries. API reference →

Use cases

Four production-ready patterns: model routing, content ranking, tool approval, ticket triage. Use cases →

Ecosystem

24 verified GitHub projects: official SDKs, community integrations, and open replicas (replicas ≠ open weights). Projects →

Video tutorials

21 videos in English and Chinese, titles and channels verified, sorted by topic. Tutorials →

Jev in three minutes

One request: state + questions

{
  "model": "jev-latest",
  "state": "The customer's ticket text…",
  "questions": {
    "department": { "type": "choice", "criteria": { "billing": "…", "technical": "…" } },
    "urgent": { "type": "noul", "instructions": "Needs same-day handling" }
  }
}

Answers: structured, ready for business logic

{
  "answers": {
    "department": { "type": "choice", "choice": "technical", "confidence": 0.78 },
    "urgent": { "type": "noul", "noul": 0.91 }
  },
  "usage": { "input_tokens": 412, "output_tokens": 67 }
}

Key official numbers (verified 2026-09-22): input $0.042 per million tokens, output free; up to 64k tokens per request; the launch blog claims 70–500 ms typical latency. See Capabilities and Limitations.

Where to start

• New to Jev: What is Jev → Capabilities → Get started
• Ready to code: API reference, JavaScript, Python
• Evaluating fit: Use cases and the FAQ