opendunes

Nex-N2.6

New

by Nex AGIReleased 10 November 2026

This model reads about 260 pages of text and pictures at once and writes up to 230 pages back. It was built to work through long tasks step by step, using your own tools as it goes: sit it down to code, drive a computer screen, or carry a job across many steps without losing the thread. It can think before it answers and fill answers into your own record format, and it cuts the bill on repeated reading, so long running jobs cost less the second time round. It cannot search the web, so jobs that need fresh news or live lookups need a model that can.

TakesTextImages
GivesText

Where your request runs

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

Nex AGI20 % offAsia…
↑ Sent, per 1M
Was 49,9339,94 DA
↓ Back, per 1M
Was 166,41133,13 DA
Cache read
Was 9,997,99 DA
Latency
…
Throughput
…
Provider↑ Sent↓ BackCache readLatencyThroughputUptime
Nex AGI20 % offAsiaWas 49,9339,94 DAWas 166,41133,13 DAWas 9,997,99 DA………

You pay the price of the provider that served your request. Prices read 02:47 · speed over the last 30 minutes · uptime over 3 days.

What it costs

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

≈ 0,11 DA per message3 000 DA buys about 28 000 messages

20 % offNex AGI has cut its price. Every figure here is the new one.

One message, the ordinary use

1 000 sent1 000 tokens sent× 39,94 per 1M× 39,94 DA per 1M0,040 DA
500 back500 tokens back× 133,13 per 1M× 133,13 DA per 1M0,067 DA
Total≈ 0,11 DA

Every rate

Meter↑ you send↓ comes back
Text tokens39,94 DA133,13 DA
Cached tokens read7,99 DA

per 1M tokens

Everyday jobs, priced

Filling sets of records in your own format from pasted papers≈ 3,46 DA
Carrying a multi-step task through your tools from start to finish≈ 3,59 DA
Watching screenshots and typing the next step for a computer task≈ 5,33 DA
Rerunning the same long reading many times a day≈ 10,38 DA
Writing and fixing code across a whole small project≈ 11,98 DA
When you pay
After the answer, from your balance. Nothing is held.
Why it varies
A longer question or a longer answer costs more.
After each one
The exact charge shows on the request.
Add creditDeposits from 100 DA, withEdahabiaCIB

See it in action

Real requests, real replies. Try any of them yourself — one click, pre-filled.

Understands images
You send

What's the total on this invoice, and when is it due?

invoice-scan.jpg · photoTry in Chat Lab
Structured output
You send

Turn this customer email into JSON with intent, urgency and order_id.

customer-email.txtTry in Chat Lab

Try your own request — same model, pre-selected.

Open Chat Lab

Call it in code

Swap the base URL and the key. Your OpenAI code runs unchanged.

POST /v1/chat/completions
Base URL
https://opendunes.com/v1
Model ID
nex-agi/nex-n2.6
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://opendunes.com/v1",
    api_key=os.environ["OPENDUNES_API_KEY"],
)

resp = client.chat.completions.create(
    model="nex-agi/nex-n2.6",
    messages=[{"role": "user", "content": "Two lines to welcome a shop in Oran."}],
)

print(resp.choices[0].message.content)

Runs this request once on your balance.

Parameters you can send

Standard OpenAI fields, grouped by what they control. Anything not listed is accepted and ignored.

Shaping the reply

How long, how varied, where to stop.

max_tokenstemperaturetop_ptop_klogprobstop_logprobs

Reasoning

Let it think before answering — and see the thinking.

reasoningreasoning_effortinclude_reasoning

Structured output

Get JSON you can parse instead of prose.

response_formatstructured_outputs

Tools

Let the model call your functions.

toolstool_choice

Limits

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

Context window
262 144 tokens
Max output
235 929 tokens
Reads at once
≈ 260 pages
Longest reply
≈ 177 000 words
Tokenizer
Other
Released
10 Nov 2026
Full API reference

Questions about Nex-N2.6

How much does Nex-N2.6 cost in dinars?

About 0,11 DA per message. Was 0,14 DA. ↑ 39,94 DA · ↓ 133,13 DA per 1M tokens.

Is Nex-N2.6 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 Nex-N2.6 best for?

This model reads about 260 pages of text and pictures at once and writes up to 230 pages back. It was built to work through long tasks step by step, using your own tools as it goes: sit it down to code, drive a computer screen, or carry a job across many steps without losing the thread. It can think before it answers and fill answers into your own record format, and it cuts the bill on repeated reading, so long running jobs cost less the second time round. It cannot search the web, so jobs that need fresh news or live lookups need a model that can.

How do I pay for Nex-N2.6 without an international card?

Add credit in dinars with your Edahabia or CIB card. Every model, Nex-N2.6 included, is paid from that balance. No foreign card, no conversion.

Does Nex-N2.6 work in Arabic, French or Darja?

Nex AGI names no languages for Nex-N2.6. Arabic, French and Darja: not stated.

Can it read PDFs, images or a whole book?

It reads text and images. Up to 262K tokens in one request, about 260 pages. It writes up to 177 000 words at once.

Is Nex-N2.6 open source?

Yes, its weights are public. Open weights on Hugging Face

Who makes Nex-N2.6, and when was it released?

Nex AGI. Released 10 November 2026.

Other Nex AGI models, priced in dinars

See all Nex AGI models
Nex-N2.5-MiniNex AGI · Sep 8, 2026

Nex-N2.5-Mini reads text and pictures and writes text back, and it is built to finish a task and prove it worked. It explores a codebase, edits several files, runs commands, launches the app, drives a browser or a desktop and tests as a user would, then revises when the result is wrong. It keeps about 256 pages in mind.

Thinks first260 pages at onceOpen weights
≈0,025 DAper message
View model
Nex-N2.5-ProNex AGI · Sep 8, 2026

Nex-N2.5-Pro reads text and pictures and writes text back, and it is built for coding that looks at the result on screen: it explores a codebase, changes several files, runs commands, opens the app, uses a browser or a desktop and checks the outcome as a user would. It also suits testing screens, automating a computer and deep research.

Thinks firstUses your tools260 pages at once
≈0,067 DAper message
View model