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 1.14
typesafe/jev-1.14Try TypeSafe: Jev 1.14 now
Runs on your balance at the prices above. New accounts start with free usage.
Results will appear here.
Settings
TypeSafe: Jev 1.14 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 1.14
TypeSafe: Jev 1.14 is a structured decision model from TypeSafe, and it is the latest version of Jev. It is also the first of TypeSafe's System One models, a line built around making fast, structured decisions for software. Its main category is decisions, and that is the only category it is listed under, so it is a focused tool rather than a general purpose chat model. The provider release date is 2026-10-14.
The model accepts text and images as input, and it returns decisions as output. Its context window is 262144 tokens, and the maximum output is 235929 tokens. Because the output modality is decisions rather than free form text, you should expect the model to return structured results that software can act on directly, which is the behaviour TypeSafe describes for its System One line. The combination of image input and a large context window means it can take in long documents or screenshots alongside text when reaching a decision.
Practical use cases follow from that shape. Anywhere a program needs a fast, structured decision rather than a paragraph of prose, Jev 1.14 is a candidate: routing or triage steps inside an application, classification or gating logic, and decision points that depend on both text and images, such as reviewing a screenshot or a scanned document before choosing an outcome. The large context window also suits decisions that must consider a long body of material at once, for example a lengthy policy document or a large batch of records supplied in a single request.
You call it through api14's OpenAI-compatible API using the model id "typesafe/jev-1.14". Because the API is OpenAI-compatible, existing OpenAI client libraries and request shapes work with it, so you point your client at api14 and set the model field to that id. The model lists no supported parameters, so you should not rely on optional request parameters such as temperature or top_p being accepted or having an effect; send the inputs the decision needs and read the decision back from the response.
Given the empty parameter list and the decision-only output, this model fits best when you want a deterministic style of structured output rather than open ended generation. If your task is conversational writing, summarisation or other free form text, a general purpose text model is likely a better fit. Jev 1.14 is aimed at software that needs a decision made for it.
How to call the TypeSafe: Jev 1.14 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-1.14".
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-1.14",
"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 1.14: frequently asked questions
- How much does the TypeSafe: Jev 1.14 API cost?
- TypeSafe: Jev 1.14 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 1.14?
- TypeSafe: Jev 1.14 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 1.14 do?
- TypeSafe: Jev 1.14 accepts text, image and returns decisions.
- How do I call TypeSafe: Jev 1.14 from my code?
- Point any OpenAI SDK at https://api14.com/api/v1 and set the model to "typesafe/jev-1.14". No other code changes. Copy a ready example from the code panel on this page.
- What are alternatives to TypeSafe: Jev 1.14?
- Comparable Decisions models at a similar price: Microsoft: Microsoft-Decision-1, Cloudflare: Clef, Together: Tev1 4B Experimental. Each runs through the same API key, so switching is one string.
TypeSafe: Jev 1.14 community
New topicThis community has no topics yet. Open the first one about TypeSafe: Jev 1.14.