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

LiquidAI: d1 vs Respan: Span-01

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

	LiquidAI: d1	Respan: Span-01
Provider	LiquidAI	Respan
Input	$0.07 / 1M tokens	$0.07 / 1M tokens
Cache read	$0.07 / 1M tokens	-
Context window	65,536	-
Max output	58,982	-
Input	text, image	text
Output	decisions	decisions
Tool calling
Structured output
Reasoning control
Added	Oct 1, 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 LiquidAI: d1 and $0.000070 with Respan: Span-01.

In depth

LiquidAI: d1 is a decisions model from LiquidAI, released on 1 October 2026. Respan: Span-01 is a decisions model from Respan, released on 26 September 2026. Both sit in the same category, meaning they are built to return a decision as their output rather than free form prose, and both are reached through the same gateway. The two providers are different companies, so the model ids differ at the vendor prefix as well as the model name.

The clearest split between them is in input handling. LiquidAI: d1 accepts text and image input, so it can look at a screenshot, a diagram or a scanned page alongside your prompt. Respan: Span-01 accepts text only. The context window is where the published facts run out: LiquidAI: d1 lists 65,536 tokens, while Respan: Span-01 does not publish a context length, so you should treat its limit as unknown and test with your own payloads before committing to a long document workflow. Neither model exposes supported parameters, and neither advertises tool use, structured output or reasoning as a distinguishing feature, so on those axes there is nothing to separate them. Both output decisions only, which means neither is a general chat or generation model.

For practical selection, start with the input type. If your task involves reading an image, such as classifying a form, checking a chart or routing a screenshot, LiquidAI: d1 is the only one of the two that can take that input at all. If your task is purely text, such as triaging a support ticket, labelling a message or making a yes or no call on a paragraph of content, both models are candidates and the decision comes down to price and to how much text you need to feed in. Because Respan: Span-01 does not state a context length, keep its inputs modest or verify behaviour yourself before sending anything long. On price, the two are about the same for input, so cost is unlikely to be the deciding factor on that side; output pricing is not differentiated in the available information, so check the live table on this page for the current numbers.

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 request to the chat completions endpoint with your api14 key, and set the model field. The only change between the two is that string: use "liquid/d1" for LiquidAI: d1 and "respan/span-01" for Respan: Span-01. Your message structure, headers and response parsing stay identical, so you can switch models with a one line edit, or run both side by side on the same input to compare their decisions before you settle on one.

There is one case where Respan: Span-01 remains the better pick even though LiquidAI: d1 covers more input types. If your workload is text only and you want the narrower, single modality model, Span-01 is a straightforward choice, and its slightly earlier release means it has been available a little longer. It is also the sensible default when you do not need image input and prefer to keep the request surface as simple as possible. Neither model supports tools or structured output flags, so if your pipeline depends on those, plan to handle parsing on your side regardless of which id you call.

Switch with one string

Both models use the same endpoint and request shape. Change the model value from "liquid/d1" to "respan/span-01" and prompts, streaming and tools keep working.

LiquidAI: d1 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);

LiquidAI: d1 vs Respan: Span-01

Specifications

Key differences

In depth

Switch with one string

More comparisons