Nace.AI: Drex v1.5 vs Perplexity: Decider Flash V1.2
A side-by-side comparison of Nace.AI: Drex v1.5 ($0.14 / 1M tokens) and Perplexity: Decider Flash V1.2 ($0.04 / 1M tokens) using current USD prices and capabilities from the api14 catalog. Both run through the same OpenAI-compatible API.
Specifications
| Nace.AI: Drex v1.5 | Perplexity: Decider Flash V1.2 | |
|---|---|---|
| Provider | Nace.AI | Perplexity |
| Input | $0.14 / 1M tokens | $0.04 / 1M tokens |
| Context window | 131,072 | 262,144 |
| Max output | 117,964 | 235,929 |
| Input | text | text, image |
| Output | decisions | decisions |
| Tool calling | ||
| Structured output | ||
| Reasoning control | ||
| Added | Oct 9, 2026 | Oct 16, 2026 |
Key differences
- Perplexity: Decider Flash V1.2 is 75% cheaper on input tokens.
- Perplexity: Decider Flash V1.2 reads 2.0× more context (262,144 tokens).
- A request with 1,000 input and 500 output tokens costs $0.000140 with Nace.AI: Drex v1.5 and $0.000035 with Perplexity: Decider Flash V1.2.
In depth
Nace.AI: Drex v1.5 is a decision model from Nace.AI, and Perplexity: Decider Flash V1.2 is a decision model from Perplexity. Both sit in the same category on api14, meaning they are built to return decisions rather than free form chat text, and both are reached through the same gateway. Nace.AI released Drex v1.5 on 2026-10-09, and Perplexity released Decider Flash V1.2 on 2026-10-16, so the two are close in age and neither is a legacy option you would pick only out of habit.
The clearest split is context and input modalities. Drex v1.5 accepts text only and offers a context window of 131,072 tokens. Decider Flash V1.2 accepts both text and images and doubles the window to 262,144 tokens, so it is the larger context model here. On price, Decider Flash V1.2 is the cheaper of the two on input. Output pricing is not meaningfully different between them, so the input side is where the cost gap shows up. Neither model exposes supported parameters, and the comparison data does not mark either one as the only model with tools, structured output or reasoning, so you should not assume a capability edge there. Both output decisions, so the difference is what you can feed them and how much you can feed at once, not what shape the answer comes back in.
For day to day work, the choice follows your input. If your task is text only and fits comfortably inside 131,072 tokens, Drex v1.5 is a reasonable default and keeps you on the Nace.AI side of the catalogue. If you need to pass screenshots, scanned pages, diagrams or any other image alongside the text, Decider Flash V1.2 is the one that accepts it, since Drex v1.5 takes text only. The same applies when your prompt, transcript or document set is long: Decider Flash V1.2 gives you roughly twice the room before you have to chunk or summarise, and it is also the cheaper input option, which matters when you are sending large volumes of tokens per call.
Calling either model through api14 works the same way, because the API is OpenAI compatible. You point your existing client at the gateway, keep your usual request shape, and change only the model id. Use "nace-ai/drex-v1.5" for Drex v1.5 and "perplexity/pplx-decider-flash-v1.2" for Decider Flash V1.2. Everything else in the request stays as it is, so switching between them for an A/B test or a fallback path is a one line change rather than a rewrite. Check the live price table on the page for current rates before you commit to volume.
There are still cases where Drex v1.5 is the better pick. If your pipeline is strictly text and your inputs are short enough to fit the smaller window, the extra context and image support in Decider Flash V1.2 buy you nothing, and staying with the Nace.AI model keeps your stack consistent if you already standardised on it. The input price difference favours Decider Flash V1.2, but output pricing is about the same, so for short text prompts the total cost gap is small and consistency may outweigh it.
Switch with one string
Both models use the same endpoint and request shape. Change the model value from "nace-ai/drex-v1.5" to "perplexity/pplx-decider-flash-v1.2" 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": "perplexity/pplx-decider-flash-v1.2",
"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