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.

d1 vs Classify-1: API price, context & features · api14

LiquidAI: d1 vs ScaleDown: Classify-1

A side-by-side comparison of LiquidAI: d1 ($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

	LiquidAI: d1	ScaleDown: Classify-1
Provider	LiquidAI	ScaleDown
Input	$0.07 / 1M tokens	$0.14 / 1M tokens
Cache read	$0.07 / 1M tokens	-
Context window	65,536	1,000,000
Max output	58,982	900,000
Input	text, image	text, image, file
Output	decisions	decisions
Tool calling
Structured output
Reasoning control
Added	Oct 1, 2026	Oct 13, 2026

Key differences

LiquidAI: d1 is 50% cheaper on input tokens.
ScaleDown: Classify-1 reads 15.3× more context (1,000,000 tokens).
A request with 1,000 input and 500 output tokens costs $0.000070 with LiquidAI: d1 and $0.000140 with ScaleDown: Classify-1.

In depth

LiquidAI: d1 is a decision model from LiquidAI, released on 2026-10-01. ScaleDown: Classify-1 is a decision model from ScaleDown, released on 2026-10-13. Both sit in the decisions category, meaning their output is a decision rather than free form prose, so you call them when you want a verdict from your input rather than a written answer. Neither model exposes any supported parameters, so you work with the defaults the provider sets.

The two differ most in context and input handling. ScaleDown: Classify-1 accepts text, image and file inputs and carries a context window of 1,000,000 tokens, while LiquidAI: d1 accepts text and image only and carries 65,536 tokens. That makes ScaleDown the model with the bigger context by a wide margin, and the only one of the two that can take a file directly. Both return decisions as their output modality, so the shape of what comes back is comparable. On price, LiquidAI: d1 is the cheaper of the two on input; output pricing is not meaningfully different between them, so cost differences will mostly show up on the input side.

For practical selection, reach for LiquidAI: d1 when your inputs are text or images, fit comfortably inside 65,536 tokens, and input cost matters to you, since it is the cheaper option on input. Reach for ScaleDown: Classify-1 when you need to feed in files, when your text or image payloads are large enough that 65,536 tokens is a real constraint, or when you want the headroom of a 1,000,000 token window for long documents or many examples in a single call. If your task is a short classification over a snippet or a single image, LiquidAI: d1 is usually the leaner choice; if your task involves whole documents, attachments or long histories, ScaleDown: Classify-1 is the one that will accept them.

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 with your api14 key, and set the model field to the id you want. The only change between the two is that string: use "liquid/d1" for LiquidAI: d1 and "scaledown/classify-1" for ScaleDown: Classify-1. Your message structure, headers and response parsing stay as they are, so you can switch models by editing one value, or route between them per request based on input size or type.

There is one case where the cheaper model is still the better pick even though ScaleDown: Classify-1 is more capable on paper. If your inputs are plain text or images that fit inside 65,536 tokens, and you are running high volume decision calls where input spend adds up, LiquidAI: d1 gives you the same decision output modality at a lower input price. The larger context and file support of ScaleDown: Classify-1 only pay off when you actually need them, so for small, text or image only decisions, LiquidAI: d1 remains a reasonable default.

Switch with one string

Both models use the same endpoint and request shape. Change the model value from "liquid/d1" to "scaledown/classify-1" and prompts, streaming and tools keep working.

LiquidAI: d1 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);

LiquidAI: d1 vs ScaleDown: Classify-1

Specifications

Key differences

In depth

Switch with one string

More comparisons