by OpenAI·Released 18 July 2024
GPT-4o mini reads text and pictures and writes text back, keeping about 128 pages in mind and replying up to 16 pages, and it can use connected tools and fill in exact forms. It is the small member of the GPT-4o family and the one OpenAI recommends in place of GPT-3.5 Turbo. Choose it for high-volume chat, pulling details out of documents or tagging pictures where GPT-4o's extra ability is not needed. GPT-4.1 mini reads about a thousand pages if your inputs are longer.
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 | 24,96 DA | 99,85 DA |
| Cached tokens read | 12,48 DA |
per 1M tokens
Web search · 3,33 DA per call
One company runs this model. OpenDunes sends every request to it. DA per 1M tokens: ↑ what you send · ↓ what comes back.
| Provider | ↑ Sent | ↓ Back | Cache read | Latency | Throughput | Uptime |
|---|---|---|---|---|---|---|
| OpenAI | 24,96 DA | 99,85 DA | 12,48 DA | … | … | … |
Also charged: a web search 3,33 DA each.
You pay the price of the provider that served your request. Prices read 15:19 · speed over the last 30 minutes · uptime over 3 days.
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-4o-mini: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.
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_pstopseedfrequency_penaltypresence_penaltylogit_biaslogprobstop_logprobsStructured 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.
predictionweb_search_optionsAbout 0,075 DA per message. ↑ 24,96 DA · ↓ 99,85 DA per 1M tokens.
No. You pay per use from your balance, with no subscription. Run it once from Call it in code, at the same price.
GPT-4o mini reads text and pictures and writes text back, keeping about 128 pages in mind and replying up to 16 pages, and it can use connected tools and fill in exact forms. It is the small member of the GPT-4o family and the one OpenAI recommends in place of GPT-3.5 Turbo. Choose it for high-volume chat, pulling details out of documents or tagging pictures where GPT-4o's extra ability is not needed. GPT-4.1 mini reads about a thousand pages if your inputs are longer.
Deposit dinars with your Edahabia or CIB card. Every model, GPT-4o-mini (batch) included, is paid from that balance. No foreign card, no conversion.
OpenAI names no languages for GPT-4o-mini (batch). Arabic, French and Darja: not stated.
It reads text, images and PDFs. Up to 128K tokens in one request, about 120 pages. It writes up to 12 000 words at once.
No. OpenAI has not published its weights.
OpenAI. Released 18 July 2024. It knows the world up to 31 October 2023.
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 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.
GPT-6 Luna Decisions does not write text. You send content as text, a table of data or a picture, plus up to 200 named questions of three kinds: yes or no, pick among options, or grade against an ordered scale. It returns a probability for every answer, with the likeliest option or expected score, so your own system can set its thresholds for routing, moderation or marking.
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.
From what its maker and two benchmark sites publish, and where it stands on OpenDunes. Read 7 Nov 2026.
Thinks first No.
Works through the problem before it answers.
Uses your tools
Can call functions your code provides.
Fills your JSON
Answers in the JSON shape you give it.
Searches the web
Can look things up online while it answers.
Cheaper on repeats
A prompt it saw a moment ago costs less the second time.
Open weights No.
Read on developers.openai.com.
Knows events up to 31 Oct 2023
What it learned stops at this date.
Sort user messages by intent
Fills your JSON
Pull search keywords from a product question
Fills your JSON
Translate short texts for your app