by OpenAI·Released 16 October 2025
#8 for logos · GPT-5 Image Mini takes text, pictures and files and gives back a picture plus text. It joins GPT-5 Mini's grasp of language to the GPT Image 1 Mini picture-maker, with lettering inside the picture and detailed edits to an existing one. Choose it when you make or edit many pictures from straightforward descriptions.
You pay for what each request uses. No subscription, no minimum.
One image, the ordinary use
Every rate
| Meter | ↑ you send | ↓ comes back |
|---|---|---|
| Picture | 2,81 DA |
per picture returned
Web search · 3,33 DA per call
One company runs this model. OpenDunes sends every request to it.
↑ 832,09 DA · ↓ 665,67 DA per 1M text tokens
| Provider | Per image | Latency | Uptime |
|---|---|---|---|
| OpenAI | ≈ 2,81 DA↑ 832,09 DA · ↓ 665,67 DA per 1M text tokens | … | … |
Also billed, on the endpoint that serves by default: Web search 3,33 DA per search.
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.
Real requests, real replies. Try any of them yourself — one click, pre-filled.
What's the total on this invoice, and when is it due?
invoice-scan.jpg · photoThe total is 42 300,00 DA, due 5 September 2026. Worth a double-check: the handwritten day could read as 8 instead of 3.
Try in Chat LabTurn this customer email into JSON with intent, urgency and order_id.
customer-email.txtTry your own request — same model, pre-selected.
Open Chat LabOne HTTP call. Any language that can send JSON can call it.
import os, requests
BASE = "https://opendunes.com/v1"
KEY = os.environ["OPENDUNES_API_KEY"]
H = {"Authorization": f"Bearer {KEY}"}
resp = requests.post(f"{BASE}/images", headers=H, json={
"model": "openai/gpt-5-image-mini",
"prompt": "A clay tagine on a blue zellige table, morning light",
})
print(resp.json())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_pseedlogprobstop_logprobsReasoning
Let it think before answering — and see the thinking.
reasoninginclude_reasoningStructured output
Get JSON you can parse instead of prose.
response_formatstructured_outputsOther
Also accepted by this model.
verbosityAbout 2,81 DA per image. ↓ 2 662,68 DA per 1M image tokens.
No. You pay per use from your balance, with no subscription. Try it in Chat at the same price.
#8 for logos · GPT-5 Image Mini takes text, pictures and files and gives back a picture plus text. It joins GPT-5 Mini's grasp of language to the GPT Image 1 Mini picture-maker, with lettering inside the picture and detailed edits to an existing one. Choose it when you make or edit many pictures from straightforward descriptions.
GPT-5 Image costs 11,25 DA more for the same image.
Deposit dinars with your Edahabia or CIB card. Every model, GPT-5 Image Mini included, is paid from that balance. No foreign card, no conversion.
OpenAI names no languages for GPT-5 Image Mini. Arabic, French and Darja: not stated.
Yes. Up to 16 reference pictures in one request.
1:1, 3:2 and 2:3. Saved as PNG, JPEG and WEBP.
OpenAI. Released 16 October 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.
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.
Up to 16 references
Takes up to that many pictures to guide the result.
4K No.
Transparent background
Makes pictures with no background.
SVG No.
Several pictures per request
Returns more than one picture per request.
Vertical 9:16 No.
Same result twice No.
The same seed gives the same result.
Write a product listing and make its photo
Make a social post visual with a headline written into it
Edit a photo from a written instruction
Edits your photo · Images