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.

Decider Flash V1.2 vs Classify-1: API price, context & features · api14

Perplexity: Decider Flash V1.2 vs ScaleDown: Classify-1

A side-by-side comparison of Perplexity: Decider Flash V1.2 ($0.04 / 1M tokens) and ScaleDown: Classify-1 ($0.14 / 1M tokens) using current USD prices and capabilities from the api14 catalog. Both run through the same OpenAI-compatible API.

Specifications

	Perplexity: Decider Flash V1.2	ScaleDown: Classify-1
Provider	Perplexity	ScaleDown
Input	$0.04 / 1M tokens	$0.14 / 1M tokens
Context window	262,144	1,000,000
Max output	235,929	900,000
Input	text, image	text, image, file
Output	decisions	decisions
Tool calling
Structured output
Reasoning control
Added	Oct 16, 2026	Oct 13, 2026

Key differences

Perplexity: Decider Flash V1.2 is 75% cheaper on input tokens.
ScaleDown: Classify-1 reads 3.8× more context (1,000,000 tokens).
A request with 1,000 input and 500 output tokens costs $0.000035 with Perplexity: Decider Flash V1.2 and $0.000140 with ScaleDown: Classify-1.

In depth

Perplexity: Decider Flash V1.2 is a decisions model from Perplexity, released on 16 October 2026. ScaleDown: Classify-1 is also a decisions model, made by ScaleDown and released a few days earlier on 13 October 2026. Both sit in the same category, so neither is a general chat model in the usual sense. They take input and return decisions, which means you should expect them to be used as classifiers or routing components inside a larger pipeline rather than as conversational assistants.

The clearest split between the two is scale. ScaleDown: Classify-1 accepts a context window of 1,000,000 tokens, roughly four times the 262,144 tokens that Decider Flash V1.2 accepts, so it is the model to reach for when your input is a long document, a large batch of records, or a transcript that would otherwise need chunking. Decider Flash V1.2 takes text and images as input. ScaleDown: Classify-1 takes text, images and files, so it covers one more input modality. Both return decisions only, and neither lists supported parameters, so you cannot tune sampling behaviour through the request body on either one. On price, Decider Flash V1.2 is the cheaper of the two for input tokens; the comparison for output tokens is not meaningfully different, so cost differences will mostly show up on the input side.

For day to day work, the choice usually comes down to how much you are feeding in and what form it arrives in. If your inputs are short or moderate, mostly text with the occasional image, and you want to keep input costs down, Decider Flash V1.2 is the natural default. If your inputs are very long, or arrive as files rather than pasted text, ScaleDown: Classify-1 saves you the work of extracting and chunking, and its larger window means fewer calls per document. Where the two overlap, on ordinary text classification with images, the cheaper input price on Decider Flash V1.2 is the deciding factor unless you are bumping against its context limit.

Calling either model through api14 works the same way, because the API is OpenAI compatible. You point your existing client at the api14 base URL, keep your usual request shape, and change only the model id. Use "perplexity/pplx-decider-flash-v1.2" for Decider Flash V1.2 and "scaledown/classify-1" for ScaleDown: Classify-1. Everything else in the request, including how you send text and images, stays as it is, so switching between them for an A/B test is a one line change rather than an integration project.

There is one case where the other model is still the better pick even if you have standardised on one. If you have settled on ScaleDown: Classify-1 for its long context and file support, Decider Flash V1.2 remains worth keeping for high volume, short input classification where its cheaper input pricing matters more than window size. Conversely, if Decider Flash V1.2 is your default, keep ScaleDown: Classify-1 in reserve for the documents that simply will not fit.

Switch with one string

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

Perplexity: Decider Flash V1.2 details & playground →ScaleDown: Classify-1 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": "scaledown/classify-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);

Perplexity: Decider Flash V1.2 vs ScaleDown: Classify-1

Specifications

Key differences

In depth

Switch with one string

More comparisons