LiquidAI: d1-ultra vs Nace.AI: Drex v2.0
A side-by-side comparison of LiquidAI: d1-ultra ($0.15 / 1M tokens) and Nace.AI: Drex v2.0 ($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-ultra | Nace.AI: Drex v2.0 | |
|---|---|---|
| Provider | LiquidAI | Nace.AI |
| Input | $0.15 / 1M tokens | $0.21 / 1M tokens |
| Cache read | $0.15 / 1M tokens | - |
| Context window | 32,768 | 131,072 |
| Max output | 29,491 | 117,964 |
| Input | text, image | text |
| Output | decisions | decisions |
| Tool calling | ||
| Structured output | ||
| Reasoning control | ||
| Added | Oct 15, 2026 | Oct 12, 2026 |
Key differences
- LiquidAI: d1-ultra is 30% cheaper on input tokens.
- Nace.AI: Drex v2.0 reads 4.0× more context (131,072 tokens).
- A request with 1,000 input and 500 output tokens costs $0.000147 with LiquidAI: d1-ultra and $0.000210 with Nace.AI: Drex v2.0.
In depth
LiquidAI: d1-ultra is made by LiquidAI and Nace.AI: Drex v2.0 is made by Nace.AI. Both sit in the decisions category, meaning their output is a decision rather than free form prose, and both were released within days of each other in October 2026, with Drex v2.0 arriving on 12 October and d1-ultra on 15 October. Neither model exposes any supported parameters, so you will not be tuning sampling settings on either one.
The clearest split is context and input. Drex v2.0 accepts up to 131072 tokens of text, four times the 32768 token window of d1-ultra, so long documents, large transcripts or big batches of records fit comfortably in Drex and may need chunking in d1-ultra. d1-ultra is the more flexible on input, taking both text and images, while Drex v2.0 takes text only. Both return decisions as their sole output modality, and the comparison data marks neither as the only one with tool use, structured output or reasoning, so there is no documented capability edge there.
For a developer choosing, the input type usually decides it. If your decision task involves screenshots, scanned pages, diagrams or any visual evidence, d1-ultra is the only option of the two, since Drex v2.0 cannot see images. If your task is text only but the material is long, such as a full contract, a lengthy support thread or a large log, Drex v2.0 is the safer pick because everything fits in one call without splitting context. When the input is short text and no images are involved, both models can serve the same decision task, and price becomes the tiebreaker: d1-ultra is the cheaper of the two on input, while the comparison gives no meaningful difference on output cost, so the input side is where the saving shows up.
Calling either model through api14 works the same way because the API is OpenAI compatible. You point your existing client at api14, keep your usual request shape, and set the model field to "liquid/d1-ultra" or "nace-ai/drex-v2.0". Switching between them is a one line change of that model id, with no other code changes needed, which makes it cheap to test both against your own decision cases before committing. Since neither model lists supported parameters, send a plain request and read the decision from the response.
There are still cases where the other model wins. If you have already built around d1-ultra for image based decisions but a particular batch is text only and very long, Drex v2.0 is the better pick for that batch because of its larger context, even though you give up image input. Conversely, if cost is the main constraint and your inputs are short text, d1-ultra remains the cheaper choice on input.
Switch with one string
Both models use the same endpoint and request shape. Change the model value from "liquid/d1-ultra" to "nace-ai/drex-v2.0" and prompts, streaming and tools keep working.
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-v2.0",
"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
- LiquidAI: d1 Latest vs LiquidAI: d1-ultra Latest
- LiquidAI: d1 Latest vs Baseten: Joey 1
- LiquidAI: d1 Latest vs LiquidAI: d1.1
- LiquidAI: d1 Latest vs Morph: Reflex
- LiquidAI: d1-ultra Latest vs Baseten: Joey 1
- LiquidAI: d1-ultra Latest vs LiquidAI: d1.1
- LiquidAI: d1-ultra Latest vs Morph: Reflex
- Baseten: Joey 1 vs LiquidAI: d1.1