Skip to main content
Jev AI logoJev AI

LIVE JEV PLAYGROUND

Jev Playground

Try Jev in your browser — type a question, pick a question type, and get a real Choice, Score or Noul answer in seconds. Free, no API key, no sign-up

LIVE JEV PLAYGROUND

Free to use with no API key or sign-up. We do not store your submissions.

Paste the ticket, email, log, user input, or model output that every question should evaluate.

285 / 8,000

Questions

Ask up to six typed questions about the same state. Jev answers them in one request.

Question 1

One key and description per line: billing: Payments or refunds

Question 2

Enter 2–10 levels, lowest to highest, one per line.

Question 3

Use exactly two lines beginning with true: and false:.

Try a preset

One request evaluates every question above.

Your state and questions are processed by Jev. We do not store them or include them in analytics.

Results

Run the preset to see real Jev answers, probabilities, confidence, latency, tokens, and cost.

Choice and Noul answers at or above this confidence can be marked for automatic action.

Continue from the Jev Playground

After testing a Choice question, a Score scale, or a Noul check, try one of the free Jev AI tools for a ready-made classification, spam, sentiment, or email workflow.

DECISIONS, NOT CHAT

Why Jev AI is not a chatbot

The Jev Playground evaluates text or structured state against questions you define. Jev returns typed decisions and probabilities for software to use, rather than composing an open-ended response.

What Jev does

  • Selects from options you define.
  • Scores an ordered scale or estimates a yes probability.
  • Answers several focused questions about the same state in one request.

What Jev does not do

  • Write replies, articles, or other generated prose.
  • Generate code or act as a programming assistant.
  • Return a narrative explanation of its reasoning.
  • Accept image, audio, or video input in this Playground.

CHOICE · SCORE · NOUL

Use Choice questions, Score scales, or Noul checks in the Jev Playground

Jev AI has three typed primitives. Choice selects from fixed options, Score rates an ordered scale, and Noul estimates a yes probability. Each constrains the answer differently, so you can match the type to the decision your application needs.

Choice, Score, and Noul quick reference
TypeReturnsRulesWhen to use it
ChoiceOne option, probabilities, and confidence2–255 predefined optionsRouting, categorization, or selecting one next action
ScoreA position on an ordered scale plus probabilities2–10 ordered levels; the score can be fractionalSeverity, quality, sentiment, or priority
NoulThe probability that a statement is trueA value from 0 to 1Binary checks, gates, or verification

JEV VS GENERAL-PURPOSE LLMs

How Jev AI compares with general-purpose LLMs

Jev is optimized for focused decisions built with Choice questions, Score scales, and Noul probabilities. General-purpose LLMs are designed for open-ended generation, conversation, and multi-step reasoning.

Jev and general-purpose language model comparison
DimensionJevGeneral-purpose LLM
Output shapeChoice, Score, or Noul with probabilitiesGenerated text; structured output may be optional
ParsingAnswer shape is defined before the requestOften needs schema enforcement, validation, or text parsing
LatencyDesigned for fast, focused decisionsVaries with model size and generated output length
BillingInput tokens; decision output is currently freeUsually input tokens plus generated output tokens
Generates textNoYes
Best fitClassification, routing, scoring, and verificationChat, writing, code, explanations, and broad reasoning

A constrained answer can still be wrong. Test on your own data and use confidence thresholds or human review for consequential decisions.

JEV API PRICING

Jev cost calculator: compare input-token costs

Estimate monthly spend at current standard input rates for Jev, GPT-5.6 Terra, and Claude Sonnet 5.

Enter a token count or use K, M, and B shorthand.

tokens

Quick estimates

Estimated monthly input cost

Jev

TypeSafe AI

Lowest input cost
$0.042

per month

$0.042

per 1M input tokens

TypeSafe pricing

GPT-5.6 Terra

OpenAI

$2.00

per month

$2.00

per 1M input tokens

OpenAI pricing

Claude Sonnet 5

Anthropic

$2.00

per month

$2.00

per 1M input tokens

Anthropic pricing

At this volume

For 1M input tokens, Jev is 97.9% less and saves $1.96 versus GPT-5.6 Terra or Claude Sonnet 5.

Input-token prices only. Estimates use standard API rates and exclude LLM output tokens, caching, batch discounts, taxes, and provider fees.

Prices checked September 19, 2026.

COPY-PASTE JEV CODE EXAMPLES

Run Jev with Python, Node, LangChain, or Vercel

These minimal examples follow the current provider documentation. Set the required API key in your environment before running them.

Python

Jev Python example

pip install typesafe-sdk
from typesafe_sdk import Choice, TypeSafeClient

with TypeSafeClient() as client:
    response = client.system_one(
        state="I was charged twice. Please refund the duplicate.",
        questions={
            "route": Choice(
                instructions="Which team should handle this?",
                criteria={"billing": None, "technical": None},
            )
        },
    )

print(response.choices["route"].choice)
TypeSafe Python SDK
Node.js

Jev Node SDK example

npm install @typesafe-ai/sdk
import { choice, TypeSafeClient } from "@typesafe-ai/sdk";

const client = new TypeSafeClient();
const response = await client.systemOne({
  state: { document: "I was charged twice. Please refund it." },
  questions: {
    route: choice("Which team should handle this?", {
      billing: null,
      technical: null,
    }),
  },
});

console.log(response.answers.route.choice);
TypeSafe JavaScript SDK
LangChain

Jev LangChain example

pip install langchain-typesafe
from langchain_typesafe import Noul, TypeSafeClassifier

classifier = TypeSafeClassifier()
response = classifier.invoke(
    state="The deploy failed twice. Customers are seeing 500s.",
    questions={
        "urgent": Noul(
            instructions="Does this need attention right now?"
        )
    },
)

print(response.nouls["urgent"].noul)
LangChain Jev guide
Vercel

Jev Vercel AI Gateway example

npm install ai
import { experimental_evaluate as evaluate } from "ai";

const result = await evaluate({
  model: "typesafe-ai/jev",
  state: "The support agent issued a full refund.",
  questions: {
    refunded: {
      type: "boolean",
      instructions: "Was a refund issued?",
    },
  },
});

console.log(result);
Vercel Jev model page

JEV PLAYGROUND FAQ

Jev Playground questions, answered

What is Jev AI?

Jev is a decision model from TypeSafe AI. It evaluates shared text or structured state and returns typed Choice, Score, or Noul answers with probabilities instead of free-form prose.

Do I need an API key to use this Jev Playground?

No. You can run limited shared requests here without an account or API key. To integrate Jev into your own application, you need your own API credentials.

How is Jev different from ChatGPT or Claude?

Jev makes constrained decisions inside an answer shape you define. ChatGPT and Claude are general-purpose models designed to generate text, code, explanations, and conversational responses.

What are Choice, Score, and Noul?

Choice selects one option from a predefined set. Score places the state on an ordered scale. Noul returns the probability that a yes-or-no statement is true.

How many questions can I ask in one request?

The Jev Playground supports up to six questions about the same state. Sending them together avoids repeating the shared state in separate requests.

Can Jev hallucinate or return a wrong answer?

Jev cannot invent an option outside the answer shape you define, but it can still choose the wrong option or assign a misleading probability. Review confidence and test important workflows on your own data.

Does this site store my Playground input?

No. We do not store the state or questions you submit or include them in analytics.