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.
Microsoft: Microsoft-Decision-1
microsoft/microsoft-decision-1Try Microsoft: Microsoft-Decision-1 now
Runs on your balance at the prices above. New accounts start with free usage.
Results will appear here.
Settings
Microsoft: Microsoft-Decision-1 at a glance
- Input price is close to the median of 25 Decisions models.
- Context window of 32,768 tokens, enough for long documents and multi-turn conversations.
- A typical request (1,000 input / 500 output tokens) costs about $0.000147.
About Microsoft: Microsoft-Decision-1
Microsoft-Decision-1 is a model from Microsoft, listed on api14 under the model id microsoft/microsoft-decision-1. It sits in the decisions category rather than the general chat category, which reflects what it was built to do: make fast decisions rather than hold a conversation. Microsoft describes it as a small model, so it is aimed at workloads where a quick answer matters more than long-form generation.
The model takes text as its only input and returns decisions as its output. It does not write prose. Instead, it reads the content you provide and returns a calibrated probability for each fixed answer option you give it. That means you define the possible answers, and the model scores them rather than picking one in free text. The context window is 32768 tokens, and the maximum output is 29491 tokens. No request parameters are listed as supported for this model.
Because the output is a probability per option, the natural use cases are classification and routing tasks. You can use it to sort incoming text into one of several known labels, to decide which queue or handler should process a request, or to score candidate answers when you need a confidence value rather than a single hard choice. Anywhere you would otherwise prompt a chat model to reply with one word from a fixed set, this model gives you the same decision with a calibrated probability attached, which is useful when downstream logic needs to act on how confident the model is.
Calling it through api14 works the same way as any other model on the gateway, using the OpenAI-compatible API with the model id microsoft/microsoft-decision-1. You send your content and your fixed answer options in the request, and you get back the probabilities. Since no request parameters are listed as supported, plan on the basic request shape and avoid relying on optional knobs such as temperature or top_p to change behaviour. Check the live price table on the page for current rates.
The main limits follow from the design. Input is text only, so images, audio and other modalities are out of scope. Output is decisions, not prose, so if you need an explanation, a summary or a generated document, a text generation model is the better fit. The context window of 32768 tokens also caps how much content you can feed in per call. Within those bounds, it is a focused tool for turning text into scored choices quickly.
How to call the Microsoft: Microsoft-Decision-1 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 "microsoft/microsoft-decision-1".
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": "microsoft/microsoft-decision-1",
"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
- 32,768
- Max output
- 29,491
- Input
- text
- Output
- decisions
Requests on api14 · last 7 days
Microsoft: Microsoft-Decision-1: frequently asked questions
- How much does the Microsoft: Microsoft-Decision-1 API cost?
- Microsoft: Microsoft-Decision-1 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 Microsoft: Microsoft-Decision-1?
- Microsoft: Microsoft-Decision-1 reads up to 32,768 tokens per request: prompt, history and documents together. It writes up to 29,491 output tokens per response.
- What can Microsoft: Microsoft-Decision-1 do?
- Microsoft: Microsoft-Decision-1 accepts text and returns decisions.
- How do I call Microsoft: Microsoft-Decision-1 from my code?
- Point any OpenAI SDK at https://api14.com/api/v1 and set the model to "microsoft/microsoft-decision-1". No other code changes. Copy a ready example from the code panel on this page.
- What are alternatives to Microsoft: Microsoft-Decision-1?
- Comparable Decisions models at a similar price: TypeSafe: Jev 1.14, Together: Tev1 4B Experimental, Jared Palmer: Kev 4B. Each runs through the same API key, so switching is one string.
Microsoft: Microsoft-Decision-1 community
New topicThis community has no topics yet. Open the first one about Microsoft: Microsoft-Decision-1.