We use cookies. Cookies and browser storage keep you signed in and remember your preferences. With your permission we also measure how the site is used. You can any time. See our cookie policy.
TypeSafe: Jev 1.13
typesafe/jev-1.13Try TypeSafe: Jev 1.13 now
Runs on your balance at the prices above. New accounts start with free usage.
Results will appear here.
Settings
TypeSafe: Jev 1.13 at a glance
- Input price is close to the median of 25 Decisions models.
- Context window of 262,144 tokens, enough for long documents and multi-turn conversations.
- A typical request (1,000 input / 500 output tokens) costs about $0.000147.
About TypeSafe: Jev 1.13
TypeSafe: Jev 1.13 is a structured decision model from TypeSafe, and the first of its System One models. TypeSafe positions System One models as tools that make fast, structured decisions for software, returning a typed choice rather than free-form prose. Jev 1.13 is therefore not a general chat or writing model: its main category is decisions, and decisions are the only category it covers. If you are building software that needs a model to pick between defined options, this is the class of model TypeSafe built it to be.
The model accepts text as its input and produces decisions as its output. It has a context window of 64,000 tokens and a maximum output of 57,600 tokens. Because the output is a typed choice rather than open-ended text, you should think of Jev 1.13 as a component that slots into a decision point in your system, not as a model you ask to draft an essay or hold a conversation. The input side is text only, so any images, audio or other modalities would need to be converted to text before they reach the model.
The practical use cases follow directly from that shape. Jev 1.13 fits routing and triage logic, where a request or record must be assigned to one of a known set of categories. It fits classification and labelling steps inside a pipeline, where the output feeds the next stage of code rather than a human reader. It fits gating and approval decisions, where software needs a consistent choice among defined outcomes. It also fits any workflow where you want the decision to arrive as a structured value you can branch on, instead of parsing prose and hoping the format holds.
You call the model through api14's OpenAI-compatible API using the model id "typesafe/jev-1.13". Because the API is OpenAI-compatible, existing OpenAI client libraries and the usual chat completion request shape work without a rewrite; you change the model id and point your client at api14. Note that the model lists no supported parameters, so you should send a plain request and not rely on tuning options such as temperature or top_p being honoured. The model id is the only identifier you need.
One limit to keep in mind is scope. Jev 1.13 returns decisions, so tasks that need generated prose, summarisation, translation or multi-turn conversation are a poor fit, and a general text generation model would serve you better there. Likewise, if your decision problem needs image or audio input, this model does not accept it. Within its lane, structured choices over text input, it is the purpose-built option.
How to call the TypeSafe: Jev 1.13 API
- Create an API key in your dashboard.
- Install the official openai SDK for your language.
- Set baseURL to https://api14.com/api/v1 and model to "typesafe/jev-1.13".
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api14.com/api/v1",
apiKey: process.env.API14_API_KEY,
});
const result = await client.post("/decisions", { body: {
"model": "typesafe/jev-1.13",
"state": "Customer: I was charged twice for my order and want my money back.",
"questions": {
"team": {
"type": "choice",
"instructions": "Which team should handle this message?",
"criteria": {
"billing": "Payments, refunds, invoices",
"support": "Product questions and bugs",
"sales": "Pricing and new purchases"
}
},
"urgent": {
"type": "noul",
"instructions": "Does this need a reply today?",
"criteria": {
"true": "Money, outage or legal risk",
"false": "Can wait"
}
}
}
} });
console.log(result.answers);
Specifications
- Context length
- 262,144
- Max output
- 235,929
- Input
- text, image
- Output
- decisions
Requests on api14 · last 7 days
TypeSafe: Jev 1.13: frequently asked questions
- How much does the TypeSafe: Jev 1.13 API cost?
- TypeSafe: Jev 1.13 costs Input $0.15 / 1M tokens. It is charged from your USD balance only for successful requests; failed requests are free.
- What is the context window of TypeSafe: Jev 1.13?
- TypeSafe: Jev 1.13 reads up to 262,144 tokens per request: prompt, history and documents together. It writes up to 235,929 output tokens per response.
- What can TypeSafe: Jev 1.13 do?
- TypeSafe: Jev 1.13 accepts text, image and returns decisions.
- How do I call TypeSafe: Jev 1.13 from my code?
- Point any OpenAI SDK at https://api14.com/api/v1 and set the model to "typesafe/jev-1.13". No other code changes. Copy a ready example from the code panel on this page.
- What are alternatives to TypeSafe: Jev 1.13?
- Comparable Decisions models at a similar price: TypeSafe: Jev 1.14, Microsoft: Microsoft-Decision-1, Cloudflare: Clef. Each runs through the same API key, so switching is one string.
TypeSafe: Jev 1.13 community
New topicThis community has no topics yet. Open the first one about TypeSafe: Jev 1.13.