by GoogleReleased 6 October 2026
Nano Banana 2.1 generates and edits images from a written description and up to 14 reference images, keeping up to four characters and ten objects consistent across edits. It outputs 1K, 2K or 4K, renders text more cleanly than Nano Banana 2, and can base a picture on web and image search results. Pick it for ad and product visuals that go through many edits.
You pay for what each request uses. No subscription, no minimum.
One image, the ordinary use
Every rate
| Meter | ↑ you send | ↓ comes back |
|---|---|---|
| Picture | 11,18 DA |
per picture returned
Web search · 4,66 DA per call, under every choice
One company runs this model. OpenDunes sends every request to it.
↑ 499,25 DA · ↓ 2 496,27 DA per 1M text tokens
| Provider | Per image | Latency | Uptime |
|---|---|---|---|
| Google AI Studio | ≈ 11,18 DA↑ 499,25 DA · ↓ 2 496,27 DA per 1M text tokens | … | … |
Also billed, on the endpoint that serves by default: Web search 4,66 DA per search.
You pay the price of the provider that served your request. Prices read 15:20 · 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": "google/gemini-nano-banana-2.1",
"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_pseedReasoning
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_choiceAbout 11,18 DA per image. ↓ 9 985,07 DA per 1M image tokens.
No. You pay per use from your balance, with no subscription. Try it in Chat at the same price.
Nano Banana 2.1 generates and edits images from a written description and up to 14 reference images, keeping up to four characters and ten objects consistent across edits. It outputs 1K, 2K or 4K, renders text more cleanly than Nano Banana 2, and can base a picture on web and image search results. Pick it for ad and product visuals that go through many edits.
Deposit dinars with your Edahabia or CIB card. Every model, Nano Banana 2.1 included, is paid from that balance. No foreign card, no conversion.
Google names no languages for Nano Banana 2.1. Arabic, French and Darja: not stated.
Yes. Up to 14 reference pictures in one request.
1:1, 1:4, 1:8, 2:3, 3:2, 3:4, 4:1, 4:3, 4:5, 5:4, 8:1, 9:16, 16:9 and 21:9. Saved as: not stated.
Google. Released 6 October 2026.
This model is designed to handle text, pictures, and video inputs, allowing it to read up to 130 pages of content. It specializes in generating and editing video clips, producing outputs that include both text and moving images. What sets this model apart is its native ability to process and generate video content directly. It is not suitable for tasks requiring external tool usage or the creation of structured data formats.
#1 for speech · Gemini 3.8 Flash TTS turns text into speech in 130+ languages with studio-grade acting, regional accents and a voice that stays consistent through long dialogues. It offers prebuilt voices, custom voice personas and voice replication, with about 8 pages of text per request. Pick it for audiobooks, narration and multi-speaker scenes.
Nano Banana 2, Google's 3.1 Flash Image model, generates and edits images from a written description and reference pictures, returning images with text. It outputs up to 4K, adds very tall and very wide shapes such as 1:8, and renders text in other languages better. Pick it for production batches of ads, banners and edits.
This model accepts text, pictures, and videos as input, allowing it to read up to 130 pages of content. It specializes in creating and editing video content, converting descriptions or pictures into moving images. A key feature is its ability to search the web for information while processing complex visual data. However, it does not utilize external tools or generate structured data formats.
From what its maker and two benchmark sites publish, and where it stands on OpenDunes. Read 7 Nov 2026.
Up to 14 references
Takes up to that many pictures to guide the result.
4K
Makes pictures up to 4K.
Transparent background No.
SVG No.
Several pictures per request No.
Returns more than one picture per request.
Vertical 9:16
Same result twice No.
The same seed gives the same result.
Place several product shots into one new scene and keep each item faithful
Up to 14 references
Edit only a masked or inked region and leave every other pixel as it was
Translate the lettering on a poster into another language in place