Nace.AI: Drex v2.0 vs ScaleDown: Classify-1
A side-by-side comparison of Nace.AI: Drex v2.0 ($0.21 / 1M tokens) and ScaleDown: Classify-1 ($0.14 / 1M tokens) using current USD prices and capabilities from the api14 catalog. Both run through the same OpenAI-compatible API.
Specifications
| Nace.AI: Drex v2.0 | ScaleDown: Classify-1 | |
|---|---|---|
| Provider | Nace.AI | ScaleDown |
| Input | $0.21 / 1M tokens | $0.14 / 1M tokens |
| Context window | 131,072 | 1,000,000 |
| Max output | 117,964 | 900,000 |
| Input | text | text, image, file |
| Output | decisions | decisions |
| Tool calling | ||
| Structured output | ||
| Reasoning control | ||
| Added | Oct 12, 2026 | Oct 13, 2026 |
Key differences
- ScaleDown: Classify-1 is 33% cheaper on input tokens.
- ScaleDown: Classify-1 reads 7.6× more context (1,000,000 tokens).
- A request with 1,000 input and 500 output tokens costs $0.000210 with Nace.AI: Drex v2.0 and $0.000140 with ScaleDown: Classify-1.
In depth
Nace.AI: Drex v2.0 is a decisions model from Nace.AI, released on 2026-10-12. ScaleDown: Classify-1 is a decisions model from ScaleDown, released on 2026-10-13. Both sit in the same category, so they are aimed at the same broad job: taking an input and returning a decision rather than free-form prose. Neither model exposes any supported parameters, so you configure them through the request body you already send, not through a list of tunable knobs.
The clearest split is in context and input handling. Drex v2.0 accepts text only and carries a context window of 131,072 tokens. Classify-1 accepts text, images and files, and its context window is 1,000,000 tokens, so it is the larger of the two by a wide margin. Both return decisions as their output modality, so the difference is on the way in, not the way out. If your input is a scanned form, a screenshot, a PDF or a long document bundle, Classify-1 can take it directly; Drex v2.0 expects you to extract text first. On price, Classify-1 is the cheaper of the two for input, while output pricing is about the same or not meaningfully different between them.
For day to day work, the choice usually follows your input format. If you already have clean text and your prompts fit comfortably inside 131,072 tokens, Drex v2.0 is a reasonable default and keeps your pipeline simple, since there is no extraction step to maintain. If you are classifying documents that arrive as PDFs, images or mixed files, or if the material is long enough that chunking would lose the context the decision depends on, Classify-1 removes that preprocessing work and gives you more room before you have to split anything. The input price difference also matters if you run high volume, though you should check the live price table on this page for the current numbers rather than relying on a rule of thumb.
Calling either model through api14 works the same way, because the gateway is OpenAI-compatible. You point your client at the same base URL, send the same chat completions style request, and change only the model id: "nace-ai/drex-v2.0" for Drex v2.0, or "scaledown/classify-1" for Classify-1. Your authentication, retry logic, logging and response parsing stay untouched, which makes it cheap to test both against your own data. A common pattern is to build the request once, run it against both ids on a sample of real inputs, and compare the decisions before committing to one.
There are still cases where Drex v2.0 is the better pick. If your inputs are plain text and short enough to fit its context window, adding image and file handling buys you nothing, and a text-only model keeps the surface area of your integration smaller. Teams that already do their own OCR or document parsing, and want the decision step to stay separate from extraction, may prefer it for that reason alone. Since output pricing is about the same between the two, the decision often comes down to whether multimodal input and the larger context window are worth it for your workload.
Switch with one string
Both models use the same endpoint and request shape. Change the model value from "nace-ai/drex-v2.0" to "scaledown/classify-1" 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": "scaledown/classify-1",
"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