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

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

A side-by-side comparison of Perplexity: Decider V1.2 ($0.07 / 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 V1.2	ScaleDown: Classify-1
Provider	Perplexity	ScaleDown
Input	$0.07 / 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 V1.2 is 50% 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 $0.000070 with Perplexity: Decider V1.2 and $0.000140 with ScaleDown: Classify-1.

In depth

Perplexity: Decider V1.2 is a decisions model from Perplexity, released on 2026-10-16. ScaleDown: Classify-1 is a decisions model from ScaleDown, released on 2026-10-13. Both sit in the same category, so they are aimed at the same broad job: taking an input and returning a decision rather than free form prose. Neither model exposes any supported parameters, so you configure them through the request body fields the gateway accepts, not through model specific knobs.

The clearest split is context and input handling. ScaleDown: Classify-1 accepts up to 1,000,000 tokens of context, while Perplexity: Decider V1.2 accepts 262,144 tokens, so ScaleDown gives you roughly four times the room for long documents or large batches in a single call. On modalities, Decider V1.2 takes text and images, while Classify-1 takes text, images and files, so Classify-1 covers one more input type. Both return decisions as their only output modality, so neither produces chat style text or structured JSON as a separate output type. On price, Decider V1.2 is the cheaper of the two on input; output pricing is not meaningfully different between them, so the cost gap depends mostly on how input heavy your workload is.

For practical selection, reach for Perplexity: Decider V1.2 when your inputs are text or images, fit inside 262,144 tokens, and you want the lower input cost. That covers most routing, triage, moderation and classification calls where the payload is a prompt plus perhaps a screenshot. Reach for ScaleDown: Classify-1 when the input is very large, such as a full contract, a long log dump or a multi file bundle, or when you need to pass files directly rather than converting them to text first. If your inputs are small and text only, Decider V1.2 is the natural default because it is cheaper on input and the extra context of Classify-1 buys you nothing.

Calling either model through api14 works the same way, because the gateway is OpenAI compatible. You point your existing client at the api14 base URL, send your key, and set the model field to the id you want. To use Perplexity, set the model to "perplexity/pplx-decider-v1.2". To use ScaleDown, set it to "scaledown/classify-1". Everything else in the request stays as it is, so switching between the two is a one line change and you can compare them on the same traffic without rewriting your integration.

There is one case where the model that is not your default still wins. If you have standardized on Decider V1.2 for cost reasons but a request arrives with a file attachment or a context that exceeds 262,144 tokens, Classify-1 is the better pick, since it accepts files and holds up to 1,000,000 tokens. Keep both ids in your config and route on payload size and input type rather than committing to a single model for every call.

Switch with one string

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

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

Specifications

Key differences

In depth

Switch with one string

More comparisons