opendunes

d1.2-ultra

New

by LiquidReleased 16 November 2026

It takes in text and pictures, up to about 65 pages of material at once, and hands back a decision for each case rather than written pages. A buyer who must sort a long batch of mixed files into fixed groups, then approve or flag each one, is the person this is built for. It is tuned for sorting documents and pulling details from them. It gives no prose and takes in no sound or video, so a spoken or moving-picture job needs a different kind of model.

TakesTextImages
GivesClassification

Where your request runs

One company runs this model. OpenDunes sends every request to it. DA per 1M tokens: ↑ what you send.

Liquid…
↑ Sent, per 1M
13,98 DA
Latency
…
Provider↑ SentLatencyUptime
Liquid13,98 DA……

You pay the price of the provider that served your request. Prices read 04:42 · speed over the last 30 minutes · uptime over 3 days.

What it costs

You pay for what each request uses. No subscription, no minimum.

≈ 0,014 DA per case3 000 DA buys about 210 000 cases

One case, the ordinary use

1 000 sent1 000 tokens sent× 13,98 per 1M× 13,98 DA per 1M0,014 DA
Total≈ 0,014 DA

Every rate

Meter↑ you send↓ comes back
Text tokens13,98 DA

per 1M tokens

Everyday jobs, priced

Reading a single 10-page form before one decision≈ 0,14 DA
Reading one full batch of 65 pages before a decision≈ 0,91 DA
When you pay
After the answer, from your balance. Nothing is held.
Why it varies
The length of the text.
After each one
The exact charge shows on the request.
Add creditDeposits from 100 DA, withEdahabiaCIB

Call it in code

One HTTP call, with your questions named as you like.

POST /alpha/decisions
Base URL
https://opendunes.com/v1
Model ID
liquid/d1.2-ultra
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": "liquid/d1.2-ultra",
    "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())
pip install requestsFull reference for this route

Runs this request once on your balance.

Limits

The hard numbers — what it can take in, what it can give back, and where it stops.

Context window
65 536 tokens
Max output
58 982 tokens
Reads at once
≈ 65 pages
Longest reply
≈ 44 000 words
Tokenizer
Other
Released
16 Nov 2026
Full API reference

Questions about d1.2-ultra

How much does d1.2-ultra cost in dinars?

About 0,014 DA per case. ↑ 13,98 DA per 1M tokens.

Is d1.2-ultra free? Can I try it?

No. You pay per use from your balance in dinars, with no subscription. The chat has free models for free messages every day.

What is d1.2-ultra best for?

It takes in text and pictures, up to about 65 pages of material at once, and hands back a decision for each case rather than written pages. A buyer who must sort a long batch of mixed files into fixed groups, then approve or flag each one, is the person this is built for. It is tuned for sorting documents and pulling details from them. It gives no prose and takes in no sound or video, so a spoken or moving-picture job needs a different kind of model.

How do I pay for d1.2-ultra without an international card?

Add credit in dinars with your Edahabia or CIB card. Every model, d1.2-ultra included, is paid from that balance. No foreign card, no conversion.

Does d1.2-ultra work in Arabic, French or Darja?

Liquid names no languages for d1.2-ultra. Arabic, French and Darja: not stated.

What can it answer?

Yes or no, one choice from your list, or a score on your scale. Each answer comes with its probability.

Who makes d1.2-ultra, and when was it released?

Liquid. Released 16 November 2026.

Other Liquid models, priced in dinars

See all Liquid models
d1.1Liquid · Oct 27, 2026

This model accepts both text and images to understand a current situation. It can process up to 65 pages of information and generate up to 58 pages of structured choices. Its primary purpose is to act as a decision-making system, taking a defined state and specific questions to output a clear choice. Because it is built for structured outcomes, it is not suited for tasks requiring open-ended creative generation.

65 pages per call
≈0,0067 DAper case
View model
d1-ultraLiquid · Oct 15, 2026

Liquid d1-ultra is the largest decision model from Liquid AI. You send a situation made of words and pictures with questions of a fixed kind, and for each one you get a yes or no, a score or a pick from a list, with a probability and no written text. It suits moderation, routing, sorting and checks on pictures.

32 pages per call
≈0,014 DAper case
View model
d1Liquid · Oct 1, 2026

Liquid d1 takes a situation described in text and pictures, plus questions of a fixed kind, and answers each with a yes or no, a score or a pick from options, with a probability and never with written text. Use it to route requests, sort items and run policy checks where you want a fast, scored answer to act on. It reads about 65 pages at once.

65 pages per call
≈0,0067 DAper case
View model
d1.2Liquid · Nov 16, 2026

This model reads text and pictures and gives back decisions rather than long written answers: it classifies, routes, extracts information and detects objects automatically. It can take in about 65 pages at once, so large batches of documents or images can be handled in a single pass. It was built as a fast, cost-efficient decision model, and only what you send is metered, so the answers it returns cost nothing extra. It is not a model for drafting essays or open-ended writing; for that you need a text-generation model.

65 pages per call
≈0,0067 DAper case
View model