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.
Jared Palmer: Kev 4B
jaredpalmer/kev-4bTry Jared Palmer: Kev 4B now
Runs on your balance at the prices above. New accounts start with free usage.
Results will appear here.
Settings
Jared Palmer: Kev 4B at a glance
- Input price is close to the median of 25 Decisions models.
- A typical request (1,000 input / 500 output tokens) costs about $0.000147.
About Jared Palmer: Kev 4B
Jared Palmer: Kev 4B is a small open-weight decision model from Jared Palmer. It is built as a LoRA adapter and pointer head on Qwen3.5-4B-Base, and it is served over the same /v1/systemone contract as TypeSafe's models. Its main category is decisions, and that is the only category it is listed under, so it is a focused model rather than a general purpose assistant.
The model takes text as input and produces decisions as output. It has a context length of 8192 tokens, and the maximum output is 7372 tokens. Because the output modality is decisions rather than free form text, you should expect the model to return a decision rather than a chat style reply or a long written answer. The input side is text only, so there is no image, audio or file input to plan for.
The practical use cases follow directly from that shape. Kev 4B fits workflows where a piece of text needs to be mapped to a decision, such as routing a request, choosing between options, classifying an incoming message or gating a step in a pipeline. It is a small model, so it suits situations where you want a decision made close to the rest of your system rather than a large general model that writes prose. If your task is open ended generation, summarisation or conversation, a general text output model will fit better, because Kev 4B is not built to produce that kind of output.
You call it through api14's OpenAI-compatible API using the model id "jaredpalmer/kev-4b". Because the API is OpenAI-compatible, you point your existing OpenAI client at the api14 base URL and pass that model id in your request. Note that the model lists no supported parameters, so you should not rely on tuning options such as temperature, top_p or similar knobs being accepted or having an effect. Send the text you want a decision on and read the decision back from the response.
Keep the limits in mind when choosing it. The context window is 8192 tokens, which is modest, so very long documents will need to be trimmed or split before they reach the model. The output ceiling of 7372 tokens is also below the context length, and since the output is a decision, long form answers are not what this model is for. For tasks that need large context, rich parameter control or written output, another model on api14 will usually be the better choice.
How to call the Jared Palmer: Kev 4B 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 "jaredpalmer/kev-4b".
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": "jaredpalmer/kev-4b",
"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
- 8,192
- Max output
- 7,372
- Input
- text
- Output
- decisions
Requests on api14 · last 7 days
Jared Palmer: Kev 4B: frequently asked questions
- How much does the Jared Palmer: Kev 4B API cost?
- Jared Palmer: Kev 4B 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 Jared Palmer: Kev 4B?
- Jared Palmer: Kev 4B reads up to 8,192 tokens per request: prompt, history and documents together. It writes up to 7,372 output tokens per response.
- What can Jared Palmer: Kev 4B do?
- Jared Palmer: Kev 4B accepts text and returns decisions.
- How do I call Jared Palmer: Kev 4B from my code?
- Point any OpenAI SDK at https://api14.com/api/v1 and set the model to "jaredpalmer/kev-4b". No other code changes. Copy a ready example from the code panel on this page.
- What are alternatives to Jared Palmer: Kev 4B?
- 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.
Jared Palmer: Kev 4B community
New topicThis community has no topics yet. Open the first one about Jared Palmer: Kev 4B.