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.

Clef vs d1-ultra: API price, context & features · api14

Cloudflare: Clef vs LiquidAI: d1-ultra

A side-by-side comparison of Cloudflare: Clef ($0.67 / 1M tokens) and LiquidAI: d1-ultra ($0.15 / 1M tokens) using current USD prices and capabilities from the api14 catalog. Both run through the same OpenAI-compatible API.

Specifications

	Cloudflare: Clef	LiquidAI: d1-ultra
Provider	Cloudflare	LiquidAI
Input	$0.67 / 1M tokens	$0.15 / 1M tokens
Cache read	-	$0.15 / 1M tokens
Context window	65,537	32,768
Max output	58,983	29,491
Input	text, image	text, image
Output	decisions	decisions
Tool calling
Structured output
Reasoning control
Added	Oct 1, 2026	Oct 15, 2026

Key differences

LiquidAI: d1-ultra is 78% cheaper on input tokens.
Cloudflare: Clef reads 2.0× more context (65,537 tokens).
A request with 1,000 input and 500 output tokens costs $0.000672 with Cloudflare: Clef and $0.000147 with LiquidAI: d1-ultra.

In depth

Cloudflare: Clef is made by Cloudflare, while LiquidAI: d1-ultra comes from LiquidAI. Both sit in the decisions category, meaning their output is a decision rather than free form prose, and both were released in October 2026, with Clef arriving on the first of the month and d1-ultra two weeks later. If you are already running workloads on Cloudflare, Clef keeps you inside that vendor's ecosystem, whereas d1-ultra is the choice when you want LiquidAI's take on the same decision task.

The two models accept the same kinds of input, text and image, and both return decisions, so the meaningful split is context and price. Clef offers a context window of 65537 tokens, roughly double the 32768 tokens d1-ultra accepts. That matters when your prompt carries long documents, transcripts or several images alongside instructions. On cost, d1-ultra is the cheaper of the two for input tokens, and the two are about the same price on output, so the input side is where the saving shows up. Neither model exposes any supported parameters, so you cannot tune sampling behaviour through the API on either one.

For practical selection, reach for Clef when the decision depends on a large body of context, such as reviewing a long contract, a full log file or a stack of screenshots in one call. Its larger window means fewer truncation workarounds and less chunking logic on your side. Reach for d1-ultra when prompts are short and you send many of them, since its cheaper input pricing rewards high volume, small payloads. If your inputs are mostly brief text or a single image and you care about per call cost at scale, d1-ultra is the sensible default.

Calling either model through api14 works the same way, because the gateway speaks the OpenAI compatible chat completions format. You point your client at the api14 base URL, send your messages with text and image content as usual, and set the model field. To use Clef, set the model id to cloudflare/clef. To use d1-ultra, set it to liquid/d1-ultra. Everything else in the request body stays identical, so switching between the two is a one line change and you can compare them on the same prompt without rewriting integration code.

There is one case where the cheaper model is still the better pick even if you have Clef available. If your decision task never approaches 32768 tokens and you run it at volume, d1-ultra's lower input cost makes it the more economical choice, and the smaller window costs you nothing because you were not using the extra room. Conversely, if a prompt does exceed that limit, d1-ultra cannot take it at all, so Clef becomes the only option between the two.

Switch with one string

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

Cloudflare: Clef details & playground →LiquidAI: d1-ultra 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": "liquid/d1-ultra",
  "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);

Cloudflare: Clef vs LiquidAI: d1-ultra

Specifications

Key differences

In depth

Switch with one string

More comparisons