Jev AI Hub
Start Learning

Independent Jev developer hub

Jev by TypeSafe AI

Independent guides to TypeSafe Jev — the System One model for typed decisions, not a chat LLM. Learn the API, tutorials, and how to use Jev in code.

Start LearningAPI GuideExamples

Real request shape from TypeSafe's quickstart

{
  "model": "jev-latest",
  "state": "Hi, I've been trying to connect my Stripe account for 3 days and the integration keeps failing. I'm losing sales. Please help ASAP.",
  "questions": {
    "department": {
      "type": "choice",
      "instructions": "Which team should handle this",
      "criteria": {
        "billing": "Payment or subscription issues",
        "technical": "Bugs or integration problems",
        "sales": "Pricing or account questions"
      }
    },
    "is_urgent": {
      "type": "noul",
      "instructions": "The message conveys urgency or time-sensitivity"
    }
  }
}

What is Jev?

Jev is a System One Model developed by TypeSafe for fast structured decisions such as classification, routing and scoring. You send a state — a string, JSON object, or array of text — plus typed questions. Jev returns answers your code can use directly: a selected option, a rubric score, or a yes/no probability. It is not a chatbot and it does not write replies. TypeSafe is the vendor; Jev is the model; System One is the model class.

What is Jev AI?What is TypeSafe AI?Is Jev an LLM?How to use Jev

Learn Jev

How to Use JevGet access, send state plus questions, and branch on typed answers.Getting StartedGet an API key, send state plus questions, and read typed answers.Is Jev an LLM?Jev is a System One model: natural-language in, typed decisions out.What is TypeSafe AI?TypeSafe is the vendor. Jev is the model. System One is the class.APIPOST /v1/systemone: authentication, request shape, responses, and errors.PythonInstall typesafe-sdk and make your first sync or async Jev call.TypeScriptUse @typesafe-ai/sdk with inferred Choice, Score, and Noul answers.NoulAsk a yes/no question and get the probability that the answer is yes.

Jev Examples

Browse examples
Route Customer Support TicketsAssign a ticket to billing, technical, account, or other, and score urgency in the same Jev call.Detect Customer IntentClassify a customer message as refund, rebooking, information, or other with a Choice.Score Inbound LeadsRate inbound leads on a situational rubric, then threshold the Score in your CRM code.Score Customer SentimentRate message tone on an ordered rubric instead of asking Jev for a happy/sad adjective.Moderate User ContentScreen a message with Noul hazard checks and a Score for severity, then apply your own pass / review / block rules.Filter RAG PassagesScore each retrieved passage, then keep, flag, or drop it before a generative model sees it.Route Requests to the Right AI ModelDecide whether a request stays on a cheap path, goes to a writer LLM, or needs a slower reasoner.Classify DocumentsLabel an uploaded file as invoice, contract, resume, policy, or other from a text excerpt.Detect EscalationsAsk a Noul whether a thread needs a human or a manager now, then threshold P(yes) in code.Select an Agent ToolPick at most one tool from a closed catalog, and ask a Noul whether any tool should run.

Developer Tools

API ExamplesRequest and response shapes for Choice, Score, Noul, and mixed questions.Jev Cost CalculatorEstimate monthly token usage and cost from official published rates.
Jev PlaygroundComing later. We will not ship a fake live API until a real backend is connected.

Popular Guides

What is Jev AI?What is Jev? Jev is TypeSafe's Jev AI model — a System One model for classification, routing and scoring, not a chat LLM.How to Use JevHow to use TypeSafe Jev: get access, send state plus Choice, Score, or Noul questions, and branch on typed answers in Python, TypeScript, or cURL.Getting Started with JevHow to use Jev: get waitlist or console access, set TYPESAFE_API_KEY, and make your first TypeSafe Jev API call with Playground, cURL, Python, or TypeScript.Jev APITypeSafe Jev API documentation: authentication, POST /v1/systemone, question types, responses, errors and examples.What is a System One Model?What is a System One model? Jev is TypeSafe's first System One model: fast structured decisions for software, trained with RLCD.Jev PricingJev API pricing from TypeSafe's official models page: $0.042 per million input tokens, output free, last verified 2026-09-20.

Latest Jev Updates

Changelog

Jev 1.13 jaggedness notes published

TypeSafe documented known failure modes for jev-1.13, including literal reading, weak numeric precision, date comparison, context rot, and generation limits.

TypeSafe exits stealth with Jev as its first public model

Third-party reporting described TypeSafe as a San Francisco lab leaving stealth with seed funding and Jev as its first System One model. Treat company-size and funding figures as third-party reports, not independently verified facts.

Current public model remains jev-1.13.0

Official models documentation lists jev-1.13.0 as the current version. Aliases jev-latest and jev-preview both pointed at that version when last verified. Input pricing was listed at $0.042 per million tokens, with output tokens free.

FAQ

What is Jev?

Jev is TypeSafe's flagship System One model. You send a state and typed questions; it returns structured answers, probabilities, and, for Choice and Score, confidence.

What is TypeSafe AI?

TypeSafe AI is the company that builds Jev. TypeSafe is the vendor; Jev is the model; System One is the model class.

Is Jev AI Hub the official TypeSafe site?

No. Jev AI Hub is an independent educational resource. It is not affiliated with or endorsed by TypeSafe.

Is Jev an LLM?

No. Jev understands natural-language input but does not generate prose, code, or explanations. It returns Choice, Score, and Noul answers your code can branch on.

How do I use Jev?

Get access (TypeSafe waitlist/console, or OpenRouter / Vercel AI Gateway), set an API key, and POST state plus typed questions. Start with How to Use Jev.

What are Choice, Score, and Noul?

They are Jev's three question primitives: pick one option, rate on a rubric, or return a yes/no probability.

How much does the Jev API cost?

When last verified, official docs listed $0.042 per million input tokens, with output tokens free. Check the pricing page and TypeSafe's models page before budgeting.

Can I fine-tune Jev?

Official docs say Jev is not fine-tuned or LoRA-adapted with customer data. You shape answers through state, instructions, and criteria.