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

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

A side-by-side comparison of Perplexity: Decider V1.2 ($0.07 / 1M tokens) and Respan: Span-01 ($0.07 / 1M tokens) 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
Provider	Perplexity	Respan
Input	$0.07 / 1M tokens	$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

Key differences

Both have about the same input price.
A request with 1,000 input and 500 output tokens costs $0.000070 with Perplexity: Decider V1.2 and $0.000070 with Respan: Span-01.

In depth

Perplexity: Decider V1.2 is a decisions model from Perplexity, released on 2026-10-16. Respan: Span-01 is a decisions model from Respan, released on 2026-09-26. Both are built for the same broad job: taking an input and returning a decision as the output rather than free-form prose. If you are wiring up a classifier, a routing rule, a triage step or any component that needs to commit to a choice, both models sit in that category. The two providers are different companies, so the operational details around each model will come from their respective platforms, but the calling shape through api14 is the same.

The clearest difference is in what each model accepts as input. Decider V1.2 takes text and images, so it can look at a screenshot, a scanned form, a chart or a photo alongside a written instruction and still produce a decision. Span-01 takes text only, which means any visual input has to be converted to text before it reaches the model. Decider V1.2 also publishes a context length of 262144 tokens, which is a large window and useful when the decision depends on a long document, a big log or a lengthy thread. Span-01 does not list a context length, so treat its usable window as unknown and test against your own inputs before relying on it for long-context work. Both output decisions, and neither lists supported parameters, so you should not expect to tune sampling or similar knobs on either one.

For task selection, the input modality is usually the deciding factor. If your pipeline ever sees images, Decider V1.2 is the straightforward pick because it handles them natively and you avoid building a separate OCR or vision step. If your inputs are long text and the decision needs the whole document in view, Decider V1.2's published context length gives you more room to work with. Span-01 remains a reasonable choice for text-only decision tasks where the input is short or already summarised, and where you want a second provider in the mix. On price, the two are about the same for input, so cost is not a strong reason to prefer one over the other on that side. Output pricing is not specified here, so check the live price table before you commit to volume.

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 usual chat completions request, and change only the model id. Use "perplexity/pplx-decider-v1.2" when you want the Perplexity model and "respan/span-01" when you want the Respan one. Everything else in the request body stays as it is, so switching between them for an A/B test or a fallback path is a one-line change. If you already have code written against the OpenAI SDK, you can keep it and just swap the string.

There is a case where Span-01 is still the better pick even though Decider V1.2 covers more input types. If your inputs are plain text, your documents are short enough that context length is not a constraint, and you specifically want to route decision traffic through Respan, then Span-01 does the job without the extra capability you would not use. It is also a sensible option when you want to compare two providers on the same task and keep the text-only path simple. In those situations the missing image support and the unpublished context length do not cost you anything, and you get the decision output you need.

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" and prompts, streaming and tools keep working.

Perplexity: Decider V1.2 details & playground →Respan: Span-01 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",
  "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 V1.2 vs Respan: Span-01

Specifications

Key differences

In depth

Switch with one string

More comparisons