by Nace AiReleased 21 October 2026
Drex Max reads long stretches of text — about 260 pages at once — and answers typed questions about them: yes or no calls, choices from a set list, or scores on a scale. It is built for sitting down with a document or a situation and getting a firm decision back, not a chat or an essay. It can also write up to 230 pages of output in one go, which few decision models of this kind manage. It does not take in pictures, audio or video, so jobs that need to look at an image or listen to a recording need a different kind of model.
You pay for what each request uses. No subscription, no minimum.
50 % offDeepInfra has cut its price. Every figure here is the new one.
One case, the ordinary use
Every rate
| Meter | ↑ you send | ↓ comes back |
|---|---|---|
| Text tokens | 19,97 DA | |
| Cached tokens read | 19,97 DA |
per 1M tokens
One company runs this model. OpenDunes sends every request to it. DA per 1M tokens: ↑ what you send.
You pay the price of the provider that served your request. Prices read 15:18 · speed over the last 30 minutes · uptime over 3 days.
One HTTP call, with your questions named as you like.
import os, requests
BASE = "https://opendunes.com"
KEY = os.environ["OPENDUNES_API_KEY"]
H = {"Authorization": f"Bearer {KEY}"}
resp = requests.post(f"{BASE}/alpha/decisions", headers=H, json={
"model": "nace-ai/drex-max",
"state": "The courier came two days late and the box was open.",
"questions": {
"is_complaint": {
"type": "noul",
"instructions": "Is it a complaint?",
"criteria": {
"true": "The customer is unhappy with the service.",
"false": "The customer is asking a question or saying thanks.",
},
},
},
})
print(resp.json())Runs this request once on your balance.
About 0,020 DA per case. Was 0,040 DA. ↑ 19,97 DA per 1M tokens.
No. You pay per use from your balance, with no subscription. Run it once from Call it in code, at the same price.
Drex Max reads long stretches of text — about 260 pages at once — and answers typed questions about them: yes or no calls, choices from a set list, or scores on a scale. It is built for sitting down with a document or a situation and getting a firm decision back, not a chat or an essay. It can also write up to 230 pages of output in one go, which few decision models of this kind manage. It does not take in pictures, audio or video, so jobs that need to look at an image or listen to a recording need a different kind of model.
Deposit dinars with your Edahabia or CIB card. Every model, Drex Max included, is paid from that balance. No foreign card, no conversion.
Nace Ai names no languages for Drex Max. Arabic, French and Darja: not stated.
Yes or no, one choice from your list, or a score on your scale. Each answer comes with its probability.
Nace Ai. Released 21 October 2026.
Drex v1.5 does not write text. You send a situation as text or a table of data, plus questions that are yes or no, multiple choice or a score on an ordered scale, and in one pass it gives every option a probability you can set a cut-off on. That suits routing a ticket, sorting a document or checking a policy where your own system needs a number to act on.
Drex v2.0 does not write text. You send a situation as text or a table of data, plus questions of set types, and in a single pass it gives every answer to every question a probability, which fits ticket routing, document sorting and rule checks where your own system reads the number. It is the bigger model that follows Drex v1.5. Both take the same inputs, so moving between them needs no change to your questions.
From what its maker and two benchmark sites publish, and where it stands on OpenDunes. Read 7 Nov 2026.
Read a 200-page contract and answer yes/no checks on each clause
Score submitted answers on a fixed scale from long text
Pick the best option from a list after reading a long brief