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.
d1.2
Newby LiquidReleased 16 November 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.
Where your request runs
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 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.
One case, the ordinary use
Every rate
| Meter | ↑ you send | ↓ comes back |
|---|---|---|
| Text tokens | 6,66 DA |
per 1M tokens
Everyday jobs, priced
- 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.
Call it in code
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": "liquid/d1.2",
"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.
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
Questions about d1.2
How much does d1.2 cost in dinars?
About 0,0067 DA per case. ↑ 6,66 DA per 1M tokens.
Is d1.2 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 best for?
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.
How do I pay for d1.2 without an international card?
Add credit in dinars with your Edahabia or CIB card. Every model, d1.2 included, is paid from that balance. No foreign card, no conversion.
Does d1.2 work in Arabic, French or Darja?
Liquid names no languages for d1.2. 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, and when was it released?
Liquid. Released 16 November 2026.
Other Liquid models, priced in dinars
See all Liquid modelsLiquid 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.
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.
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.