How to get Jev: API key, free trial and every way in

Hi, I've been trying to connect my Stripe account for 3 days and it keeps failing with 'invalid redirect'. I'm losing sales every hour this is down. Please help ASAP.

The three ways to use Jev

Jev is TypeSafe’s System One model. There are two public builds: jev-1.14.0, released on 2026-10-14 (the jev-preview alias, and jev-latest about a week later), and jev-1.13.0, which stays available. You can reach Jev three ways:

1. JevStation playground — in the browser, free account, 50 credits, no card.
2. JevStation account and API key — 50 free credits, then one-time credit packs.
3. TypeSafe direct — the model’s own API, behind a waitlist.

1. JevStation playground in the browser

Steps. Sign up for a free account, open the playground, pick a preset such as the support triage example above, edit the text if you like, and run it.

Price. Free to start: a new account gets 50 credits, valid for 30 days, with no card and no code. A standard evaluation costs 1 credit.

Pros. No card, no code, no waitlist. You see real probabilities from the real model within seconds, and you can write your own questions as well as run the presets.

Cons. You need an account before the first run, and browser runs spend the same credits as the API. It is the quickest way to see how Jev answers, not a way to run volume.

Suits anyone deciding whether Jev is worth a closer look.

2. JevStation account and API key

Steps. Sign up, open Settings › API Keys, create a key, and call POST https://jevstation.com/api/v1/systemone with it. The same account can use the playground with your own questions.

Price. New accounts get 50 free credits, valid for 30 days, with no card and no provider key required. After that, credits come in one-time packs, not subscriptions: $9.90 for 5,000 credits or $15.90 for 12,000, valid for 24 months. A standard evaluation — state up to 8,000 characters and up to 5 questions — costs 1 credit. A larger one, up to 24,000 characters and 12 questions, costs 3. A failed evaluation is refunded automatically. See pricing.

Pros. No waitlist. You pay per evaluation rather than per token, so a request’s price never depends on how the model tokenizes it. You also get a playground for designing question sets, saved evaluation threads and automatic refunds.

Cons. Per call, it costs more than raw tokens. A typical evaluation costs about $0.00002 at Jev’s list price; one credit costs $0.00198 in the small pack and $0.00133 in the large one. Throughput is capped per account, and the cap rises with the pack you buy; GET /api/v1/systemone returns your current limits. The deployment pins the model version, so the model field in your request is ignored.

Suits developers who want to call Jev today, teams that want a playground alongside the API, and anyone below very high volume.

3. TypeSafe direct

Steps. Join TypeSafe’s waitlist (check TypeSafe for whether new sign-ups are currently open). Once admitted, call POST https://api.typesafe.ai/v1/systemone with your TypeSafe key. LangChain publishes an integration for it: langchain-typesafe for Python and @langchain/typesafe for JavaScript.

Price. Pay as you go at $0.042 per million input tokens; output tokens are free. There are no self-serve plans and no free usage. Higher limits and zero data retention go through TypeSafe’s sales team.

Pros. The lowest price per call, the highest rate limits (TypeSafe states 1,200 requests a minute and 250,000 tokens a second), and control over the model version, including the jev-latest and jev-preview aliases.

Cons. You wait to get in. TypeSafe also says its rate limits are adjusting dynamically and can change without notice.

Suits high-volume production workloads that can wait for access.

Call the JevStation API

Every example sends the support ticket from the example above with two questions. Replace $JEVSTATION_API_KEY with the key you created.

cURL

curl -X POST https://jevstation.com/api/v1/systemone \
  -H "Authorization: Bearer $JEVSTATION_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "state": "I have been trying to connect my Stripe account for 3 days and it keeps failing with invalid redirect. I am losing sales every hour.",
    "questions": {
      "category": {
        "type": "choice",
        "instructions": "Which team should handle this support ticket?",
        "criteria": {
          "billing": "Payments, invoices, refunds or plan changes",
          "integrations": "Connecting or syncing a third-party service",
          "bug": "The product behaves incorrectly",
          "account": "Login, access or account settings"
        }
      },
      "churn_risk": {
        "type": "noul",
        "instructions": "Is the customer at risk of churning?"
      }
    }
  }'

Python (requests)

import os
import requests

resp = requests.post(
    "https://jevstation.com/api/v1/systemone",
    headers={"Authorization": f"Bearer {os.environ['JEVSTATION_API_KEY']}"},
    json={
        "state": "I have been trying to connect my Stripe account for 3 days "
                 "and it keeps failing with invalid redirect. I am losing sales every hour.",
        "questions": {
            "category": {
                "type": "choice",
                "instructions": "Which team should handle this support ticket?",
                "criteria": {
                    "billing": "Payments, invoices, refunds or plan changes",
                    "integrations": "Connecting or syncing a third-party service",
                    "bug": "The product behaves incorrectly",
                    "account": "Login, access or account settings",
                },
            },
            "churn_risk": {
                "type": "noul",
                "instructions": "Is the customer at risk of churning?",
            },
        },
    },
    timeout=30,
)
body = resp.json()
if body["code"] != 0:
    raise RuntimeError(body["message"])

data = body["data"]
print(data["answers"]["category"]["choice"], data["answers"]["category"]["confidence"])
print(data["answers"]["churn_risk"]["noul"])
print("credits left:", data["credits"]["remaining"])

Node (fetch)

const res = await fetch('https://jevstation.com/api/v1/systemone', {
  method: 'POST',
  headers: {
    Authorization: `Bearer ${process.env.JEVSTATION_API_KEY}`,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    state:
      'I have been trying to connect my Stripe account for 3 days and it keeps failing with invalid redirect. I am losing sales every hour.',
    questions: {
      category: {
        type: 'choice',
        instructions: 'Which team should handle this support ticket?',
        criteria: {
          billing: 'Payments, invoices, refunds or plan changes',
          integrations: 'Connecting or syncing a third-party service',
          bug: 'The product behaves incorrectly',
          account: 'Login, access or account settings',
        },
      },
      churn_risk: {
        type: 'noul',
        instructions: 'Is the customer at risk of churning?',
      },
    },
  }),
});

const body = await res.json();
if (body.code !== 0) throw new Error(body.message);

const { answers, credits } = body.data;
console.log(
  answers.category.choice,
  answers.churn_risk.noul,
  credits.remaining
);

What comes back

Responses use an envelope: code is 0 on success and -1 on an error, message is ok or the error text, and the result is under data. The values below show the shape only; your numbers will differ.

{
  "code": 0,
  "message": "ok",
  "data": {
    "model": "jev-1.13.0",
    "answers": {
      "category": {
        "type": "choice",
        "choice": "integrations",
        "probabilities": {
          "billing": 0.2,
          "integrations": 0.7,
          "bug": 0.08,
          "account": 0.02
        },
        "confidence": 0.6
      },
      "churn_risk": { "type": "noul", "noul": 0.8 }
    },
    "usage": { "input_tokens": 180, "output_tokens": 0 },
    "credits": { "charged": 1, "remaining": 199 },
    "latency_ms": 400
  }
}

A Choice answer carries the top option, every option’s probability and a confidence value. A Score answer carries a value along your levels, a legend and confidence. A Noul answer is a single probability from 0 to 1, with no confidence. Errors also set a real HTTP status: 401 for a missing or invalid key, 400 or 413 for a bad or oversized request, 402 when you are out of credits (with a top_up_url to the pricing page), 429 when you hit a rate limit, and 502 when the evaluation fails, in which case the credits are refunded. The docs cover every field.

Jev redeem code? There isn’t one, but you get 50 free credits

Free credits. Every new JevStation account gets 50 free credits on sign-up, valid for 30 days, with no card and no code to enter. That covers 50 standard evaluations, in the playground or through the API.

Redeem codes. There is no Jev redeem code. JevStation does not publish redeem, promo or coupon codes for Jev credits, and you do not need one: the 50 free credits arrive with the account. Codes posted on other sites that claim to unlock Jev credits on JevStation are not issued by us. TypeSafe direct has no free usage at all.

Sign up and claim your 50 free credits — no card, no code, and your first API key takes about a minute.

Subscriptions. There are none. Credits come in one-time packs — $9.90 for 5,000 or $15.90 for 12,000, valid for 24 months — so there is nothing recurring to cancel. Through TypeSafe direct you pay as you go per token. See pricing for a cost calculator.

Comparison at a glance

How Jev compares with other decision models

Jev is not the only model that answers typed questions with probabilities. Microsoft, Perplexity, Cloudflare, OpenAI and Liquid AI have each released one, and a JevStation key runs all of them through the same endpoint. If you are choosing between them, these pages test them on the same inputs:

• Decision models compared: Jev, Clef, Decider, Luna and the rest in one table
• Jev vs Microsoft-Decision-1
• Jev vs Perplexity Decider
• Jev vs Clef
• Jev vs Liquid AI d1-ultra
• Is Jev open source?: what is on GitHub and Hugging Face, and what you can self-host

Or try Jev online in the playground first: a free account comes with 50 credits, no card.

Get an API key and make your first call

1. Sign up. Create an account at /sign-up. It starts with 50 free credits, valid for 30 days.
2. Create a key. Open Settings › API Keys and create a key. Store it as JEVSTATION_API_KEY rather than in code.
3. Check it. Send GET https://jevstation.com/api/v1/systemone with the same Bearer header. It costs nothing and returns your plan, remaining credits and rate limits.
4. Make the first call. Run any of the examples above. It is a standard evaluation, so it costs 1 credit.

Before writing code, it is worth designing the questions in the playground first: it uses the same contract, and the answers you see there are what your code will get. Designing Questions Jev Can Answer covers how to phrase them, and What One Jev Evaluation Costs breaks down the token cost behind each call.

The same key and endpoint also run Cloudflare’s Clef decision models: add "model": "clef-flash" or "model": "clef" to the request. How to get Clef covers every way to reach it, and Jev vs Clef covers when each model is the better choice.