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 Drex Max: API price, context & features · api14

LiquidAI: d1 vs Nace.AI: Drex Max

A side-by-side comparison of LiquidAI: d1 ($0.07 / 1M tokens) and Nace.AI: Drex Max ($0.21 / 1M tokens) using current USD prices and capabilities from the api14 catalog. Both run through the same OpenAI-compatible API.

Specifications

	LiquidAI: d1	Nace.AI: Drex Max
Provider	LiquidAI	Nace.AI
Input	$0.07 / 1M tokens	$0.21 / 1M tokens
Cache read	$0.07 / 1M tokens	$0.21 / 1M tokens
Context window	65,536	262,144
Max output	58,982	235,929
Input	text, image	text, image
Output	decisions	decisions
Tool calling
Structured output
Reasoning control
Added	Oct 1, 2026	Oct 21, 2026

Key differences

LiquidAI: d1 is 67% cheaper on input tokens.
Nace.AI: Drex Max reads 4.0× more context (262,144 tokens).
A request with 1,000 input and 500 output tokens costs $0.000070 with LiquidAI: d1 and $0.000210 with Nace.AI: Drex Max.

In depth

LiquidAI: d1 is a decisions model from LiquidAI, released on 1 October 2026. Nace.AI: Drex Max is a decisions model from Nace.AI, released on 21 October 2026. Both sit in the same category, so neither is a general chat model or a code completion model; they are built to return decisions as their output. That shared category is the starting point for the comparison, because it means the choice between them is not about what kind of job they do but about how much input they can take and what it costs to run them.

The two models accept the same input modalities, text and image, and both return decisions as output. Neither exposes any supported parameters, so you will not be tuning sampling settings or similar knobs on either one. The clearest capability difference is context length. Drex Max has the bigger context window at 262144 tokens, while d1 sits at 65536 tokens. That is a fourfold difference in how much material you can hand the model in a single call. On price, d1 is the cheaper of the two on input. The qualitative data does not establish a difference on output pricing, so treat output cost as about the same unless the live price table says otherwise.

For practical selection, the deciding factor is usually how much context your task needs. If you are feeding a long document, a large transcript, a big batch of records or a long image plus text payload, Drex Max is the safer pick because its window is much larger and you are less likely to truncate or split the input. If your inputs are short to moderate and input cost matters to you, d1 is the cheaper option on the input side and will usually be the more economical call. Because both are decisions models with the same modalities and no tunable parameters, you are not choosing between different output styles or tool support here; you are choosing between a cheaper, smaller window model and a larger window model at a higher input price.

Calling either one through api14 works the same way, because the API is OpenAI compatible. You point your client at the api14 base URL, send your request in the usual chat completions shape, and set the model field to the id you want. To switch from one model to the other, change only that model id, from "liquid/d1" to "nace-ai/drex-max" or the reverse. Your messages, image parts and other request structure stay as they are. There is no separate endpoint, no different authentication scheme and no different response envelope to handle.

There is a case where the other model is still the better pick. If you start with d1 to save on input cost but your payload grows past what a 65536 token window can hold, moving to Drex Max is the straightforward fix, and it costs you nothing in integration effort since only the model id changes. Conversely, if you are on Drex Max for the large window but your inputs are consistently small, switching to d1 lowers your input cost without changing anything else about the call. Check the live price table for current numbers before you commit, since the figures here are qualitative only.

Switch with one string

Both models use the same endpoint and request shape. Change the model value from "liquid/d1" to "nace-ai/drex-max" and prompts, streaming and tools keep working.

LiquidAI: d1 details & playground →Nace.AI: Drex Max 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": "nace-ai/drex-max",
  "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 Nace.AI: Drex Max

Specifications

Key differences

In depth

Switch with one string

More comparisons