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.
GPT-6.2 Astra (batch)
Newby OpenAIReleased 17 November 2026
#2 for reasoningThis model reads text files and pictures and answers in writing, taking in about 1,000 pages at once and writing up to 120 pages back. It suits a buyer who sits down with a long contract, codebase or research pile and needs it read whole, then answered, checked or rewritten at length. It can pause to reason before answering, search the web for up-to-date facts, call your tools, and cost less when the same material is sent again. It only writes words, so it cannot produce pictures, audio or video, and that work needs a different kind of model.
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.
Also charged: prompts over 272 000 tokens ↑ 2 662,68 ↓ 9 985,07 · writing to the cache ↑ 1 664,18 · a web search 3,33 DA each.
You pay the price of the provider that served your request. Prices read 05:44 · 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 message, the ordinary use
Every rate
| Meter | ↑ you send | ↓ comes back |
|---|---|---|
| Text tokens | 1 331,34 DA | 6 656,71 DA |
| Cached tokens read | 66,57 DA | |
| Cache-write tokens | 1 664,18 DA |
per 1M tokens
Web search · 3,33 DA per call, under every choice
Everyday jobs, priced
- 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.
Call it in code
Swap the base URL and the key. Your OpenAI code runs unchanged.
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:batch",
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_tokensseedReasoning
Let it think before answering — and see the thinking.
reasoningreasoning_effortinclude_reasoningStructured output
Get JSON you can parse instead of prose.
response_formatstructured_outputsTools
Let the model call your functions.
toolstool_choiceOther
Also accepted by this model.
verbosityLimits
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
Questions about GPT-6.2 Astra (batch)
How much does GPT-6.2 Astra (batch) cost in dinars?
About 4,66 DA per message. ↑ 1 331,34 DA · ↓ 6 656,71 DA per 1M tokens.
Is GPT-6.2 Astra (batch) 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 (batch) best for?
#2 for reasoning · This model reads text files and pictures and answers in writing, taking in about 1,000 pages at once and writing up to 120 pages back. It suits a buyer who sits down with a long contract, codebase or research pile and needs it read whole, then answered, checked or rewritten at length. It can pause to reason before answering, search the web for up-to-date facts, call your tools, and cost less when the same material is sent again. It only writes words, so it cannot produce pictures, audio or video, and that work needs a different kind of model.
How do I pay for GPT-6.2 Astra (batch) without an international card?
Add credit in dinars with your Edahabia or CIB card. Every model, GPT-6.2 Astra (batch) included, is paid from that balance. No foreign card, no conversion.
Does GPT-6.2 Astra (batch) work in Arabic, French or Darja?
OpenAI names no languages for GPT-6.2 Astra (batch). 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 (batch) open source?
No. OpenAI has not published its weights.
Who makes GPT-6.2 Astra (batch), and when was it released?
OpenAI. Released 17 November 2026.
Other OpenAI models, priced in dinars
See all OpenAI modelsGPT 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.
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.
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.