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 Decider V1.2: API price, context & features · api14

Microsoft: Microsoft-Decision-1 vs Perplexity: Decider V1.2

A side-by-side comparison of Microsoft: Microsoft-Decision-1 ($0.15 / 1M tokens) and Perplexity: Decider V1.2 ($0.07 / 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	Perplexity: Decider V1.2
Provider	Microsoft	Perplexity
Input	$0.15 / 1M tokens	$0.07 / 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 16, 2026

Key differences

Perplexity: Decider V1.2 is 52% cheaper on input tokens.
Perplexity: Decider V1.2 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 $0.000070 with Perplexity: Decider V1.2.

In depth

Microsoft-Decision-1 is a decisions model from Microsoft, listed under the model id microsoft/microsoft-decision-1. Perplexity: Decider V1.2 is a decisions model from Perplexity, listed as perplexity/pplx-decider-v1.2. Both sit in the same category, so they are aimed at the same broad job: taking an input and returning a decision rather than a chat reply or a block of prose. Neither model exposes any supported parameters, so you configure them the same way and pass your input as text.

The clearest split is context and input modalities. Decider V1.2 accepts text and images and carries a context window of 262144 tokens. Microsoft-Decision-1 accepts text only and carries 32768 tokens. That means Decider V1.2 can take in far more material per call and can also read images, while Microsoft-Decision-1 is limited to text and to a much smaller window. Both return decisions as their output modality, so the shape of the answer is comparable even though the inputs are not. On price, Decider V1.2 is the cheaper of the two for input; output pricing is not meaningfully different between them, so the input side is where the cost gap shows up.

For practical selection, the deciding factors are how much text you need to feed in and whether any of it is an image. If your decision depends on a long document, a large batch of records, or a mix of text and screenshots, Decider V1.2 is the natural fit because of its larger context and image input. If your input is short and purely textual, Microsoft-Decision-1 covers that case and keeps you on a Microsoft model, which may matter if you already standardise on that provider. The input price difference favours Decider V1.2, so at high call volumes with large prompts that gap compounds, while for small prompts the two are close enough that other factors can drive the choice.

Calling either model through api14 works the same way, because the gateway exposes an OpenAI-compatible API. You point your existing client at api14, keep your usual request structure, and set the model field to the id you want. Switching between them is a one line change: use microsoft/microsoft-decision-1 for the Microsoft model, or perplexity/pplx-decider-v1.2 for the Perplexity model. Nothing else in the request needs to change, since both take text input and both return decisions, and neither declares extra supported parameters you would have to add or remove.

There is a case where Microsoft-Decision-1 remains the better pick even though Decider V1.2 has the larger window and image support. If your inputs are short, text only, and you specifically want a Microsoft model in the path, the extra context and image handling of Decider V1.2 buy you nothing, and the simpler text only input surface is enough. In that situation the choice comes down to provider preference rather than capability, and Microsoft-Decision-1 fits without asking you to change anything about how you build the request.

Switch with one string

Both models use the same endpoint and request shape. Change the model value from "microsoft/microsoft-decision-1" to "perplexity/pplx-decider-v1.2" and prompts, streaming and tools keep working.

Microsoft: Microsoft-Decision-1 details & playground →Perplexity: Decider V1.2 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": "perplexity/pplx-decider-v1.2",
  "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 Perplexity: Decider V1.2

Specifications

Key differences

In depth

Switch with one string

More comparisons