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.
Nace.AI: Drex v1.5
nace-ai/drex-v1.5Try Nace.AI: Drex v1.5 now
Runs on your balance at the prices above. New accounts start with free usage.
Results will appear here.
Settings
Nace.AI: Drex v1.5 at a glance
- Input price is close to the median of 25 Decisions models.
- Context window of 131,072 tokens, enough for long documents and multi-turn conversations.
- A typical request (1,000 input / 500 output tokens) costs about $0.000140.
About Nace.AI: Drex v1.5
Nace.AI: Drex v1.5 is a decision model from Nace.AI. It is listed on api14 under the decisions category, and its model id is nace-ai/drex-v1.5. The provider describes it as a small decision model, and it was released by the provider on 2026-10-09. If you are evaluating models for a task that is about making a choice rather than generating prose, this is the kind of model the catalogue places in that group.
The model takes text as its input and produces decisions as its output. Its context window is 131072 tokens, and the maximum output is 117964 tokens. The provider description gives more detail on the shape of a call: you send a state together with typed questions, where the questions can be yes/no, multiple choice, or score. That means the output is not free-form text but a structured answer to the questions you pose. The model is served over the same /v1/systemone contract as TypeSafe's Jev, so the calling convention is shared with that model rather than being unique to Drex.
The practical uses follow from that design. A yes/no question over a supplied state fits gating and eligibility checks, where you need a decision rather than an explanation. Multiple choice questions fit classification and routing, for example picking a category, a queue, or a next step from a fixed set of options. Score questions fit ranking and thresholding, where you need a value you can compare against a cutoff. Because the input is text and the context window is large, the state you send can be a substantial document or a long record, and you can attach several typed questions to the same state in one call.
To call it through api14, use the OpenAI-compatible endpoint with the model id nace-ai/drex-v1.5. The supported parameters list for this model is empty, so there are no request parameters documented as supported beyond what the shared contract requires. The provider notes that Drex 1.5 is served over the /v1/systemone contract, so the request format follows that contract rather than the usual chat completions shape. Check the contract documentation for the exact fields before you build against it.
One limit to keep in mind is that the output modality is decisions, not text. If your application needs generated prose, summaries, or conversational replies, a text output model is the better fit. Drex v1.5 is aimed at the narrower job of answering typed questions about a state, and it is described by its provider as a small decision model, so treat it as a component in a pipeline rather than a general assistant.
How to call the Nace.AI: Drex v1.5 API
- Create an API key in your dashboard.
- Install the official openai SDK for your language.
- Set baseURL to https://api14.com/api/v1 and model to "nace-ai/drex-v1.5".
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-v1.5",
"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);
Specifications
- Context length
- 131,072
- Max output
- 117,964
- Input
- text
- Output
- decisions
Requests on api14 · last 7 days
Nace.AI: Drex v1.5: frequently asked questions
- How much does the Nace.AI: Drex v1.5 API cost?
- Nace.AI: Drex v1.5 costs Input $0.14 / 1M tokens. It is charged from your USD balance only for successful requests; failed requests are free.
- What is the context window of Nace.AI: Drex v1.5?
- Nace.AI: Drex v1.5 reads up to 131,072 tokens per request: prompt, history and documents together. It writes up to 117,964 output tokens per response.
- What can Nace.AI: Drex v1.5 do?
- Nace.AI: Drex v1.5 accepts text and returns decisions.
- How do I call Nace.AI: Drex v1.5 from my code?
- Point any OpenAI SDK at https://api14.com/api/v1 and set the model to "nace-ai/drex-v1.5". No other code changes. Copy a ready example from the code panel on this page.
- What are alternatives to Nace.AI: Drex v1.5?
- Comparable Decisions models at a similar price: ScaleDown: Classify-1, LiquidAI: d1, TypeSafe: Jev 1.14. Each runs through the same API key, so switching is one string.
Nace.AI: Drex v1.5 community
New topicThis community has no topics yet. Open the first one about Nace.AI: Drex v1.5.