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

LiquidAI: d1-ultra vs Perplexity: Decider V1.2

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

	LiquidAI: d1-ultra	Perplexity: Decider V1.2
Provider	LiquidAI	Perplexity
Input	$0.15 / 1M tokens	$0.07 / 1M tokens
Cache read	$0.15 / 1M tokens	-
Context window	32,768	262,144
Max output	29,491	235,929
Input	text, image	text, image
Output	decisions	decisions
Tool calling
Structured output
Reasoning control
Added	Oct 15, 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 LiquidAI: d1-ultra and $0.000070 with Perplexity: Decider V1.2.

In depth

LiquidAI: d1-ultra is a decisions model from LiquidAI, released on 15 October 2026. Perplexity: Decider V1.2 is a decisions model from Perplexity, released a day later on 16 October 2026. 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 is a general chat model, and neither is positioned as a coding or writing assistant. If your application needs a model that outputs a decision, both belong on your shortlist.

The two differ most clearly in context window and price. Decider V1.2 accepts up to 262144 tokens of context, while d1-ultra accepts 32768 tokens. That is roughly an eightfold difference, and it matters when you are feeding long documents, large retrieved chunks or extended conversation history into the model before asking for a decision. On input pricing, Decider V1.2 is the cheaper of the two. Output pricing is not meaningfully different between them, so the input side is where the cost gap shows up. Both accept text and image as input, and both return decisions as output. Neither lists any supported parameters, so you should not expect tuning knobs such as temperature or top_p to have an effect. Neither is distinguished as the only one offering tools, structured output or reasoning, so on those axes there is nothing to separate them.

For practical selection, start with the context requirement. If your prompt plus retrieved material fits comfortably inside 32768 tokens, d1-ultra is a reasonable choice and keeps you on LiquidAI's model. If you routinely exceed that, or you want headroom so you are not trimming context, Decider V1.2 is the one to call, and its cheaper input pricing reinforces that for long prompts. For short, image bearing decision tasks where the input is compact, either model can serve, and the deciding factor becomes which provider you already trust or integrate with. Where the input is long and the call volume is high, the combination of the larger window and the lower input price points to Decider V1.2.

Calling either model through api14 works the same way, because the gateway exposes an OpenAI compatible API. You point your existing OpenAI client at the api14 base URL, send your request to the chat completions endpoint, and set the model field to the id you want. To use LiquidAI's model, set the model id to "liquid/d1-ultra". To use Perplexity's model, set it to "perplexity/pplx-decider-v1.2". Nothing else in the request body needs to change to switch between them, since both take text and image input and both return decisions. That means you can keep one code path and swap the id, or route per request based on how large the input is.

There is a case where d1-ultra remains the better pick even though Decider V1.2 has the larger window and cheaper input. If your inputs are short and you specifically want to stay on LiquidAI, or you are already standardized on that provider elsewhere in your stack, there is no capability listed here that forces you onto Decider V1.2. The models tie on output pricing, on modalities and on the absence of tools, structured output and reasoning distinctions, so for compact decision tasks the choice is largely a matter of provider preference rather than a technical gap.

Switch with one string

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

LiquidAI: d1-ultra 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-ultra vs Perplexity: Decider V1.2

Specifications

Key differences

In depth

Switch with one string

More comparisons