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.

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

A side-by-side comparison of Perplexity: Decider V1.2 ($0.07 / 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 V1.2	Respan: Span-01 Lite
Provider	Perplexity	Respan
Input	$0.07 / 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 V1.2 is a decisions model from Perplexity, released on 16 October 2026. Respan: Span-01 Lite is a decisions model from Respan, released on 26 September 2026. Both belong to the same category, so neither is a general chat model or a coding assistant in the usual sense. They are built to return decisions rather than free form prose, which shapes everything below.

The clearest difference between them is input handling. Decider V1.2 accepts text and image input, while Span-01 Lite accepts text only. If your pipeline needs to feed in a screenshot, a scanned form, a diagram or any other visual artifact alongside the prompt, Decider V1.2 is the one that can take it. Decider V1.2 also lists a context length of 262144 tokens, whereas Span-01 Lite does not publish a context length, so treat its usable window as unknown and plan accordingly. Both models output decisions, and neither lists any supported parameters, so you should not expect to tune sampling behaviour, temperature or similar knobs through the request body. On price, the qualitative comparison marks input and output cost as not meaningfully different or unknown, so there is no basis to call one cheaper than the other; check the live price table on this page for the current figures.

For practical selection, start from the input side. Tasks that involve reading images, such as classifying a screenshot, extracting a decision from a document scan or judging a visual state, point to Decider V1.2 because Span-01 Lite cannot see them. Tasks that are purely text and fit comfortably in a modest prompt are reasonable candidates for Span-01 Lite. Long text workloads, such as deciding over a large transcript, a long log or a big retrieved document set, favour Decider V1.2 because its context length is stated and large, while Span-01 Lite's is not stated at all. Since neither model exposes supported parameters, the decision is mostly about modality and context rather than tuning.

Calling either model through api14 works the same way. Both are served behind an OpenAI-compatible API, so you keep your existing client, your existing request shape and your existing response parsing, and you change only the model id. Use "perplexity/pplx-decider-v1.2" for the Perplexity model and "respan/span-01-lite" for the Respan model. That single string is the switch between them, which makes it cheap to route different requests to different models inside one application, or to swap one for the other while testing.

There is one case where Span-01 Lite remains the sensible pick even though Decider V1.2 covers more ground. If your inputs are text only and short, and you simply want a decisions model from Respan, Span-01 Lite matches the task without the extra modality surface you would not use. The facts given do not establish a price advantage for either side, so choose on input type and context needs rather than on cost.

Switch with one string

Both models use the same endpoint and request shape. Change the model value from "perplexity/pplx-decider-v1.2" to "respan/span-01-lite" and prompts, streaming and tools keep working.

Perplexity: Decider 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);

More comparisons

Decider V1.2 vs Span-01 Lite: API price, context & features · api14