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.

New here? See how it works A 1-minute tour of the playground, models and your API key.

Microsoft-Decision-1 vs Jev 1.14: API price, context & features · api14

Microsoft: Microsoft-Decision-1 vs TypeSafe: Jev 1.14

A side-by-side comparison of Microsoft: Microsoft-Decision-1 ($0.15 / 1M tokens) and TypeSafe: Jev 1.14 ($0.15 / 1M tokens) using current USD prices and capabilities from the api14 catalog. Both run through the same OpenAI-compatible API.

Specifications

	Microsoft: Microsoft-Decision-1	TypeSafe: Jev 1.14
Provider	Microsoft	TypeSafe
Input	$0.15 / 1M tokens	$0.15 / 1M tokens
Context window	32,768	262,144
Max output	29,491	235,929
Input	text	text, image
Output	decisions	decisions
Tool calling
Structured output
Reasoning control
Added	Oct 9, 2026	Oct 14, 2026

Key differences

Both have about the same input price.
TypeSafe: Jev 1.14 reads 8.0× more context (262,144 tokens).
A request with 1,000 input and 500 output tokens costs $0.000147 with Microsoft: Microsoft-Decision-1 and $0.000147 with TypeSafe: Jev 1.14.

In depth

Microsoft: Microsoft-Decision-1 is a decisions model from Microsoft, listed under the model id microsoft/microsoft-decision-1. TypeSafe: Jev 1.14 is a decisions model from TypeSafe, listed under the model id typesafe/jev-1.14. Both are built to return decisions rather than free form prose, so they sit in the same category and are aimed at the same broad job: taking an input and producing a choice or verdict. The two providers are different companies, and the provider release dates are close together, with Microsoft-Decision-1 listed at 2026-10-09 and Jev 1.14 at 2026-10-14.

The clearest split between them is context and input modality. Jev 1.14 has the bigger context window at 262144 tokens, while Microsoft-Decision-1 sits at 32768 tokens. Jev 1.14 also accepts both text and image input, whereas Microsoft-Decision-1 accepts text only. Both output decisions, so the output side is the same shape. On price, the qualitative data says input pricing is a tie, so neither is meaningfully cheaper on input, and there is no meaningful difference recorded on output pricing. Neither model lists supported parameters, so you should not expect tuning knobs beyond the basics.

For practical selection, the deciding factor is usually how much material the model has to read before it decides. If your input is a long document, a large transcript, a big batch of records, or anything that would blow past roughly thirty thousand tokens, Jev 1.14 is the one to call, because Microsoft-Decision-1 cannot hold that much at once. The same applies if the decision depends on an image, a screenshot, a scanned form or a diagram, since only Jev 1.14 takes image input. Microsoft-Decision-1 remains a reasonable choice for shorter, text only decision tasks where the input fits comfortably inside its context window and you do not need to send images. Since input pricing is a tie, you are not paying a premium either way on that dimension, so let context size and modality drive the choice rather than cost.

Calling either model through api14 works the same way, because the API is OpenAI compatible. You point your client at the api14 base URL, send your request to the chat completions endpoint, and set the model field to the id you want. To use Microsoft's model, set the model to microsoft/microsoft-decision-1. To use TypeSafe's model, set the model to typesafe/jev-1.14. Everything else in the request body stays as it is, so switching between the two is a one line change to the model id. If you already have working code against one of them, you can compare the other by editing that single string and re running the same request.

There is one case where the smaller model is still the better pick. If your inputs are short, text only, and you want the model from Microsoft specifically, Microsoft-Decision-1 covers that ground without the extra context capacity you would not use. It is not cheaper on input, so the reason to prefer it is fit rather than price: a text only decision task that fits inside 32768 tokens is squarely within what it handles. For anything longer, or anything that includes an image, Jev 1.14 is the model to call.

Switch with one string

Both models use the same endpoint and request shape. Change the model value from "microsoft/microsoft-decision-1" to "typesafe/jev-1.14" and prompts, streaming and tools keep working.

Microsoft: Microsoft-Decision-1 details & playground →TypeSafe: Jev 1.14 details & playground →

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);

Microsoft: Microsoft-Decision-1 vs TypeSafe: Jev 1.14

Specifications

Key differences

In depth

Switch with one string

More comparisons