What is Jev 1.13 for?

Decision points inside software: routing, classification, scoring, and gating. It returns a typed answer your code can branch on — a probability, a labelled choice, or a position on a scale — rather than a sentence you have to parse.

How much does Jev 1.13 cost?

$0.042 per million input tokens, and output is free. A short ticket with three questions costs roughly two thousandths of a cent. Current rates are shown in the Hormouz dashboard.

Can I use it from the OpenAI SDK?

No. It is not a chat model and does not accept messages, so the chat endpoint and the OpenAI SDKs do not apply. Send a plain POST to /v1/alpha/decisions with your state and questions; the model page shows the exact call in curl, Python and JavaScript.

What is the difference between Jev 1.13 and Jev Latest?

Jev 1.13 is pinned to one version and will not change under you. Jev Latest always resolves to the newest model in the Jev family, so it picks up improvements automatically and may change behaviour without notice. Pin the version when a decision boundary has to stay stable.

About 0.26 seconds at the median, which is what makes it practical to put a decision on every request rather than on a sample.

TypeSafe: Jev 1.13: AI model

Jev 1.13 is a structured decision model: you hand it some state and a set of typed questions, and it returns a typed answer to each — a probability, a labelled choice, or a position on an ordered scale. No prose. Served from inside Iran through Hormouz.

Context window:: 64,000 tokens
Input:: $0.04/1M tokens
Output:: $0/1M tokens
Type:: decisions

Structured decisions

Jev is the first of TypeSafe's System One models, built for the decision points inside an application rather than for conversation. Routing a support ticket, classifying an upload, scoring risk, gating a tool call — the places where a fast, predictable answer matters more than a well-written one. Because the answer comes back typed, your code can branch on it directly instead of parsing a sentence and hoping the wording does not change next week.

There are three kinds of question. A noul question returns the probability that a condition holds, so you can gate an action on a threshold you choose. A choice question picks one of the labels you define and reports how much probability each candidate carried, so a close call is visible instead of hidden. A score question places the input on an ordered ladder you supply and returns a continuous position, so "just past this week" is distinguishable from "squarely blocking revenue".

It answers in about a quarter of a second and is billed on input only — output is free — which is what makes it practical to put one on every request rather than on a sample. Through Hormouz it is reached at POST /v1/alpha/decisions with your ordinary API key; the request and response shapes are unchanged, so code written against the upstream API works by swapping the base URL. The alpha in the path is the provider's own signal that the shape may still move.

Jev is a structured decision model from TypeSafe, and the first of its System One models. System One models make fast, structured decisions for software, returning a typed choice rather...

Quickstart

curl https://api.hormouz.net/v1/alpha/decisions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "model": "typesafe/jev-1.13", "state": { "ticket": "My checkout page shows a blank screen after I click Pay." }, "questions": { "is_bug": { "type": "noul", "instructions": "Is the customer reporting a defect?" }, "team": { "type": "choice", "instructions": "Which team owns this?", "criteria": { "frontend": "Rendering or layout.", "payments": "Checkout or billing." } }, "urgency": { "type": "score", "instructions": "How urgent?", "criteria": ["Next release", "This week", "Blocking revenue"] } } }'

Specs

Vendor	TypeSafe
Type	Scoring & decisions
Context window	64,000 tokens
Pricing	$0.04/M in · $0.00/M out
API	decisions

Code example

cURL

curl https://api.hormouz.net/v1/alpha/decisions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "model": "typesafe/jev-1.13", "state": { "ticket": "My checkout page shows a blank screen after I click Pay." }, "questions": { "is_bug": { "type": "noul", "instructions": "Is the customer reporting a defect?" }, "team": { "type": "choice", "instructions": "Which team owns this?", "criteria": { "frontend": "Rendering or layout.", "payments": "Checkout or billing." } }, "urgency": { "type": "score", "instructions": "How urgent?", "criteria": ["Next release", "This week", "Blocking revenue"] } } }'

Python

import requests

resp = requests.post(
    "https://api.hormouz.net/v1/alpha/decisions",
    headers={"Authorization": "Bearer ng-YOUR_API_KEY"},
    json={
  "model": "typesafe/jev-1.13",
  "state": { "ticket": "My checkout page shows a blank screen after I click Pay." },
  "questions": {
    "is_bug": { "type": "noul", "instructions": "Is the customer reporting a defect?" },
    "team": { "type": "choice", "instructions": "Which team owns this?",
              "criteria": { "frontend": "Rendering or layout.", "payments": "Checkout or billing." } },
    "urgency": { "type": "score", "instructions": "How urgent?",
                 "criteria": ["Next release", "This week", "Blocking revenue"] }
  }
},
)
answers = resp.json()["answers"]
print(answers["team"]["choice"], answers["is_bug"]["noul"])

JavaScript

const resp = await fetch("https://api.hormouz.net/v1/alpha/decisions", {
  method: "POST",
  headers: {
    Authorization: "Bearer ng-YOUR_API_KEY",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
  "model": "typesafe/jev-1.13",
  "state": { "ticket": "My checkout page shows a blank screen after I click Pay." },
  "questions": {
    "is_bug": { "type": "noul", "instructions": "Is the customer reporting a defect?" },
    "team": { "type": "choice", "instructions": "Which team owns this?",
              "criteria": { "frontend": "Rendering or layout.", "payments": "Checkout or billing." } },
    "urgency": { "type": "score", "instructions": "How urgent?",
                 "criteria": ["Next release", "This week", "Blocking revenue"] }
  }
}),
});
const { answers } = await resp.json();
console.log(answers.team.choice, answers.is_bug.noul);

Buy the TypeSafe: Jev 1.13 API, paid in rial

Buy credit with an Iranian bank card; no foreign card or account needed.
One Hormouz key reaches TypeSafe: Jev 1.13 and 600+ other models, and you pay only for what you use.
No VPN and no risk of a banned account; just change the base URL to api.hormouz.net/v1.

Create an account

Use via Hormouz

Connect to this model and 600+ others with one API key, then see usage down to each request.

Request company access

FAQ

What is Jev 1.13 for?: Decision points inside software: routing, classification, scoring, and gating. It returns a typed answer your code can branch on — a probability, a labelled choice, or a position on a scale — rather than a sentence you have to parse.
How much does Jev 1.13 cost?: $0.042 per million input tokens, and output is free. A short ticket with three questions costs roughly two thousandths of a cent. Current rates are shown in the Hormouz dashboard.
Can I use it from the OpenAI SDK?: No. It is not a chat model and does not accept messages, so the chat endpoint and the OpenAI SDKs do not apply. Send a plain POST to /v1/alpha/decisions with your state and questions; the model page shows the exact call in curl, Python and JavaScript.
What is the difference between Jev 1.13 and Jev Latest?: Jev 1.13 is pinned to one version and will not change under you. Jev Latest always resolves to the newest model in the Jev family, so it picks up improvements automatically and may change behaviour without notice. Pin the version when a decision boundary has to stay stable.
How fast is it?: About 0.26 seconds at the median, which is what makes it practical to put a decision on every request rather than on a sample.

Updated 2026-10-13