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

LiquidAI: d1 vs Perplexity: Decider V1.2

A side-by-side comparison of LiquidAI: d1 ($0.07 / 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

	LiquidAI: d1	Perplexity: Decider V1.2
Provider	LiquidAI	Perplexity
Input	$0.07 / 1M tokens	$0.07 / 1M tokens
Cache read	$0.07 / 1M tokens	-
Context window	65,536	262,144
Max output	58,982	235,929
Input	text, image	text, image
Output	decisions	decisions
Tool calling
Structured output
Reasoning control
Added	Oct 1, 2026	Oct 16, 2026

Key differences

Both have about the same input price.
Perplexity: Decider V1.2 reads 4.0× more context (262,144 tokens).
A request with 1,000 input and 500 output tokens costs $0.000070 with LiquidAI: d1 and $0.000070 with Perplexity: Decider V1.2.

In depth

LiquidAI: d1 is a decisions model from LiquidAI, and Perplexity: Decider V1.2 is a decisions model from Perplexity. Both sit in the same category, so neither is a general chat model you would use to draft an email or write a function. You call them when you want a decision returned rather than prose. LiquidAI released d1 on 2026-10-01, and Perplexity released Decider V1.2 on 2026-10-16, so the two are close together in time and target the same job.

The clearest difference is context. Decider V1.2 accepts up to 262144 tokens, while d1 accepts 65536, so Perplexity's model takes roughly four times as much input in one call. Both accept text and image as input, and both return decisions as output, so the modality story is the same on either side. Neither model lists supported parameters, which means you should not expect to tune sampling or similar knobs through the request body. The qualitative comparison marks input pricing as a tie, so cost per input token is about the same for both, and there is no meaningful difference recorded on output pricing or on tool, structured output or reasoning exclusivity.

For task selection, the deciding factor is how much material the model has to weigh. If your decision depends on a long document, a large transcript, a big set of retrieved passages or several images at once, Decider V1.2 is the safer choice because its context window is much larger and you are less likely to truncate evidence that matters. If your inputs are short and well scoped, d1 is a reasonable pick and the input price is about the same, so you are mainly trading context headroom for nothing in particular. Where the evidence fits comfortably in 65536 tokens, either model can serve, and you can choose on the basis of which provider's decisions you have found more useful in your own evaluations.

Calling either model through api14 works the same way because the gateway exposes an OpenAI-compatible API. You point your client at the api14 base URL, send your request to the chat completions endpoint, and set the model field. To use LiquidAI's model, set the model id to "liquid/d1". To use Perplexity's model, set it to "perplexity/pplx-decider-v1.2". Everything else in the request, including your messages and any images, stays as it is. Switching between the two is a one line change, so you can run the same prompt against both and compare the decisions you get back.

There is a case for staying with d1 even when context is not the constraint. If your inputs are consistently short, if you have already tuned your pipeline around LiquidAI's decision format, or if you simply prefer its outputs on your data, the larger window of Decider V1.2 buys you nothing and the input cost is about the same. In that situation the extra headroom is unused capacity, and there is no listed capability difference that would force the switch.

Switch with one string

Both models use the same endpoint and request shape. Change the model value from "liquid/d1" to "perplexity/pplx-decider-v1.2" and prompts, streaming and tools keep working.

LiquidAI: d1 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);

LiquidAI: d1 vs Perplexity: Decider V1.2

Specifications

Key differences

In depth

Switch with one string

More comparisons