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 Span-01 Lite: API price, context & features · api14

Perplexity: Decider Flash V1.2 vs Respan: Span-01 Lite

A side-by-side comparison of Perplexity: Decider Flash V1.2 ($0.04 / 1M tokens) and Respan: Span-01 Lite (Free) using current USD prices and capabilities from the api14 catalog. Both run through the same OpenAI-compatible API.

Specifications

	Perplexity: Decider Flash V1.2	Respan: Span-01 Lite
Provider	Perplexity	Respan
Input	$0.04 / 1M tokens	-
Context window	262,144	-
Max output	235,929	-
Input	text, image	text
Output	decisions	decisions
Tool calling
Structured output
Reasoning control
Added	Oct 16, 2026	Sep 26, 2026

In depth

Perplexity: Decider Flash V1.2 is a decisions model from Perplexity, released on 2026-10-16. Respan: Span-01 Lite is also a decisions model, made by Respan and released on 2026-09-26. Both are built to return decisions rather than long-form prose, so they sit in the same category even though they come from different providers. If you are already routing other Perplexity or Respan models through your stack, that familiarity may be the only thing separating them at first glance.

The clearest split is in input handling and context. Decider Flash V1.2 accepts text and image input and lists a context length of 262144 tokens. Span-01 Lite accepts text only, and its context length is not published, so you cannot assume it matches. Neither model exposes supported parameters, and neither offers a tools or structured-output flag that the other lacks. On the qualitative fields given, there is no meaningful difference recorded for price, context size, tool use, structured output or reasoning, so treat those as unknown rather than as advantages for either side. The practical difference is that Decider Flash V1.2 can read images and has a stated large context, while Span-01 Lite is text-only with an unspecified window.

For task selection, start with the input type. If your decision input includes screenshots, scanned forms, diagrams or any other image, Decider Flash V1.2 is the one that can take it; Span-01 Lite cannot. If your input is plain text and fits comfortably in a normal prompt, both are candidates, and since the price comparison is not established, you should check the live price table before committing. If your text is very long, such as a full contract, a long log or a large retrieved document set, Decider Flash V1.2 has a published 262144-token window, whereas Span-01 Lite's limit is unknown, so the safer choice for long inputs is Decider Flash V1.2 unless you have tested Span-01 Lite on your own data.

Calling either model through api14 works the same way because the API is OpenAI-compatible. You send a chat completions request to the same endpoint with the same authentication, and the only change is the model id. Use "perplexity/pplx-decider-flash-v1.2" for Decider Flash V1.2 and "respan/span-01-lite" for Span-01 Lite. Your message structure, headers and response parsing stay identical, so switching between them is a one-line edit in your client config or a single string change in your request body.

Span-01 Lite is still the better pick in one situation the facts support: when your input is text only and you want to try the Respan model specifically, perhaps because you already use Respan elsewhere or want to compare its decisions against Perplexity's on the same prompts. It is also a reasonable default when you know your inputs are short text and you would rather not pay for image handling you will never use, though the price relationship between the two is not stated here, so confirm that against the live table before assuming it is cheaper.

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 "respan/span-01-lite" and prompts, streaming and tools keep working.

Perplexity: Decider Flash V1.2 details & playground →Respan: Span-01 Lite 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": "respan/span-01-lite",
  "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 Respan: Span-01 Lite

Specifications

In depth

Switch with one string

More comparisons