opendunes

GPT-6.2 Astra Pro

New

by OpenAIReleased 17 November 2026

This model reads text files and pictures and answers in writing, taking in about 1,000 pages at a time and writing up to 120 pages back. It runs in a setting that spends extra effort on every answer, made for work that takes hours to untangle: a drawer of reports read whole and turned into one decision memo, or a codebase audited end to end. It can think before answering, search the web, call your tools and cost less when the same material is sent again. It writes words only, so picture, audio or video work needs a different kind of model.

TakesTextImagesFiles
GivesText

Where your request runs

Two companies run this model. OpenDunes sends each request to one of them. DA per 1M tokens: ↑ what you send · ↓ what comes back.

OpenAI…
↑ Sent, per 1M
2 662,68 DA
↓ Back, per 1M
13 313,42 DA
Cache read
133,13 DA
Latency
…
Throughput
…
Azure…
↑ Sent, per 1M
2 662,68 DA
↓ Back, per 1M
13 313,42 DA
Cache read
133,13 DA
Latency
…
Throughput
…
AzureUnited States…
↑ Sent, per 1M
2 928,95 DA
↓ Back, per 1M
14 644,77 DA
Cache read
146,45 DA
Latency
…
Throughput
…
AzureEurope…
↑ Sent, per 1M
3 195,22 DA
↓ Back, per 1M
15 976,11 DA
Cache read
159,76 DA
Latency
…
Throughput
…
Provider↑ Sent↓ BackCache readLatencyThroughputUptime
OpenAI2 662,68 DA13 313,42 DA133,13 DA………
Azure2 662,68 DA13 313,42 DA133,13 DA………
AzureUnited States2 928,95 DA14 644,77 DA146,45 DA………
AzureEurope3 195,22 DA15 976,11 DA159,76 DA………

Also charged: prompts over 272 000 tokens ↑ 5 325,37 ↓ 19 970,14 · writing to the cache ↑ 3 328,36 · a web search 3,33 DA each.

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.

≈ 9,32 DA per message3 000 DA buys about 320 messages

One message, the ordinary use

1 000 sent1 000 tokens sent× 2 662,68 per 1M× 2 662,68 DA per 1M2,66 DA
500 back500 tokens back× 13 313,42 per 1M× 13 313,42 DA per 1M6,66 DA
Total≈ 9,32 DA

Every rate

Meter↑ you send↓ comes back
Text tokens2 662,68 DA13 313,42 DA
Cached tokens read133,13 DA
Cache-write tokens3 328,36 DA

per 1M tokens

Web search · 3,33 DA per call, under every choice

Everyday jobs, priced

Check app screenshots against a compliance checklist≈ 159,76 DA
Summarise 100 pages of quarterly reports into an 8-page brief≈ 372,78 DA
Review a 60-page contract clause by clause with comments≈ 1 118,33 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
openai/gpt-6.2-astra-pro
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="openai/gpt-6.2-astra-pro",
    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_tokensseed

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

Other

Also accepted by this model.

max_completion_tokensverbosity

Limits

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

Context window
1 050 000 tokens
Max output
128 000 tokens
Reads at once
≈ 1 000 pages
Longest reply
≈ 96 000 words
Tokenizer
GPT
Released
17 Nov 2026
Full API reference

Questions about GPT-6.2 Astra Pro

How much does GPT-6.2 Astra Pro cost in dinars?

About 9,32 DA per message. ↑ 2 662,68 DA · ↓ 13 313,42 DA per 1M tokens.

Is GPT-6.2 Astra Pro 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 GPT-6.2 Astra Pro best for?

This model reads text files and pictures and answers in writing, taking in about 1,000 pages at a time and writing up to 120 pages back. It runs in a setting that spends extra effort on every answer, made for work that takes hours to untangle: a drawer of reports read whole and turned into one decision memo, or a codebase audited end to end. It can think before answering, search the web, call your tools and cost less when the same material is sent again. It writes words only, so picture, audio or video work needs a different kind of model.

GPT-6.2 Astra Pro or GPT-6.2 Astra?

GPT-6.2 Astra costs the same for the same message.

How do I pay for GPT-6.2 Astra Pro without an international card?

Add credit in dinars with your Edahabia or CIB card. Every model, GPT-6.2 Astra Pro included, is paid from that balance. No foreign card, no conversion.

Does GPT-6.2 Astra Pro work in Arabic, French or Darja?

OpenAI names no languages for GPT-6.2 Astra Pro. Arabic, French and Darja: not stated.

Can it read PDFs, images or a whole book?

It reads text, images and PDFs. Up to 1.1M tokens in one request, about 1 000 pages. It writes up to 96 000 words at once.

Is GPT-6.2 Astra Pro open source?

No. OpenAI has not published its weights.

Who makes GPT-6.2 Astra Pro, and when was it released?

OpenAI. Released 17 November 2026.

Other OpenAI models, priced in dinars

See all OpenAI models
Text Embedding 3 SmallOpenAI · Oct 30, 2025

Text Embedding 3 Small turns text of up to about 8 pages into a fingerprint of its meaning, so search finds passages that mean the same thing even when the words differ. It replaces the older ada-002 and is the sensible default for search over your documents, grouping similar messages or labelling them.

8 pages per call
≈0,0067 DAper page
View model
GPT Image 2.5 SunburstOpenAI · Sep 9, 2026

GPT Image 2.5 Sunburst takes a written description, with optional reference pictures, and gives back an image, new or edited, as PNG, JPEG or WebP, with transparent backgrounds on PNG and WebP. It is the precision tier of the 2.5 series, for detailed creative work where an edit has to land exactly as asked, and it adds top quality settings named xhigh and max.

Up to 16 referencesTransparent background
≈4,38 DAper image
View model
Text Embedding 3 LargeOpenAI · Oct 30, 2025

Text Embedding 3 Large turns text of up to about 8 pages into a fingerprint of its meaning, so search finds passages that mean the same thing even when the words differ. It is the most accurate of OpenAI's models of this kind, in English and other languages. Choose it when the quality of matches matters most, for search, grouping or labelling documents.

8 pages per call
≈0,043 DAper page
View model
GPT-6 LunaOpenAI · Sep 22, 2026

GPT-6 Luna reads your text, pictures and files and writes back, and it can take in about a thousand pages at once. It is the quick, low-cost tier of the GPT-6 series, below GPT-6 Sol, built for heavy traffic and tight response times: chat, sorting messages into categories and light multi-step tasks. Turn its thinking up and it can also take software and computer-use jobs that used to need a Sol-class model.

Searches the webThinks firstUses your tools
≈0,12 DAper message
View model