nano-banana-2-lite: image generation model
Nano Banana 2 Lite is Google's fastest image model — the low-cost member of the Nano Banana 2 family, built for quick generation and editing at high volume. Served asynchronously through Hormouz from inside Iran.
- Pricing:
- $0.0340 / run
- Type:
- image
- Image generation
Nano Banana 2 Lite is the lightweight, low-cost member of the Nano Banana 2 family, tuned for speed and high-volume use where you want a good image at the lowest price. It handles text-to-image generation, image editing and multi-image composition through a single flow, and accepts up to 14 reference images for style transfer, composition or editing.
Images are generated at 1K, roughly one megapixel. For the highest fidelity or larger 2K and 4K output, use Nano Banana 2 or Nano Banana Pro instead. This model does not support Google Search or Image Search grounding.
It is served through Hormouz behind an asynchronous predictions API. Submit a prediction with your prompt and optional reference images, then poll until the image is ready. Aspect ratio can be any of 14 standard ratios, or match_input_image to follow your input; output format is jpg or png.
Generation is billed at a flat $0.034 per image. Hormouz provides stable access to Nano Banana 2 Lite from inside Iran, with no foreign credit card or circumvention tooling required.
Quickstart
# Create the prediction, then poll until succeeded
curl -s https://api.hormouz.net/v1/predictions \
-H "Authorization: Bearer ng-YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"version":"google/nano-banana-2-lite","input":{"prompt":"A beautiful sunset"}}'Specs
| Vendor | |
|---|---|
| Type | Image |
| Context window | — |
| Pricing | $0.0340 / run |
| API | predictions |
Code example
# Create the prediction, then poll until succeeded
curl -s https://api.hormouz.net/v1/predictions \
-H "Authorization: Bearer ng-YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"version":"google/nano-banana-2-lite","input":{"prompt":"A beautiful sunset"}}'import requests
BASE = "https://api.hormouz.net/v1"
H = {"Authorization": "Bearer ng-YOUR_API_KEY", "Content-Type": "application/json"}
r = requests.post(f"{BASE}/predictions", headers=H,
json={"version": "google/nano-banana-2-lite", "input": {"prompt":"A beautiful sunset"}})
print(r.json()["id"])const BASE = "https://api.hormouz.net/v1";
const res = await fetch(`${BASE}/predictions`, {
method: "POST",
headers: { Authorization: "Bearer ng-YOUR_API_KEY", "Content-Type": "application/json" },
body: JSON.stringify({ version: "google/nano-banana-2-lite", input: {"prompt":"A beautiful sunset"} }),
});
const { id } = await res.json();Buy the nano-banana-2-lite API, paid in rial
- Buy credit with an Iranian bank card; no foreign card or account needed.
- One Hormouz key reaches nano-banana-2-lite and 600+ other models, and you pay only for what you use.
- No VPN and no risk of a banned account; just change the base URL to api.hormouz.net/v1.
Use via Hormouz
Connect to this model and 600+ others with one API key, then see usage down to each request.
Request company accessFAQ
- How much does Nano Banana 2 Lite cost?
- Billing is a flat $0.034 per output image on Hormouz, or roughly 29 images per dollar. Current rates are shown in the Hormouz dashboard.
- How do I access Nano Banana 2 Lite from inside Iran?
- Create an account on Hormouz and generate an API key. Hormouz provides a stable path to Nano Banana 2 Lite from inside Iran, with no foreign credit card or circumvention tooling required.
- How is Nano Banana 2 Lite different from Nano Banana 2?
- Lite is faster and cheaper, and its output is 1K only (roughly one megapixel), where Nano Banana 2 also reaches 2K and 4K. Lite has no Google Search or Image Search grounding either. If you need the highest fidelity or a larger resolution, use Nano Banana 2 or Nano Banana Pro.
- Can Nano Banana 2 Lite edit existing images?
- Yes. Pass up to 14 input images along with a text prompt to change backgrounds, swap colours, adjust styles, or combine several images into one scene. Set the aspect ratio to match_input_image and the output follows the aspect ratio of your input.
Updated 2026-10-13