Google Nano Banana Pro API

NB Pro is the Nano Banana Pro image model: text-to-image and editing with up to 14 reference images, one image per request at 1k, 2k or 4k.

Try online · Get an API key · Read the docs

Capabilities

Model
Image
API model
zhenzhen-image-nb-pro
Endpoints
POST /v1/image/generations, GET /v1/image/generations/{id}
Parameters
prompt: 5–5000, images: 0–14, n: 1, size: auto / 1:1 / 2:3 / 3:2 / 3:4 / 4:3 / 4:5 / 5:4 / 9:16 / 16:9 / 21:9, resolution: 1k / 2k / 4k

Current pricing

zhenzhen-image-nb-pro: ≈¥0.18–0.22 per request

Model variants

API modelUse caseCurrent pricing
zhenzhen-image-nb-proImage≈¥0.18–0.22 per request
zhenzhen-image-nb-pro-lowpriceImage¥0.09–0.15 per request

Gallery examples

  • Phone Screen PopoutPhone Screen Popout

    API model: zhenzhen-image-nb-pro

    Phone Screen Popout — explore this zhenzhen-image-nb-pro creation on OpenZhenZhen, with its original prompt and a reusable generation example.

  • Giant Basketball PillGiant Basketball Pill

    API model: zhenzhen-image-nb-pro

    Giant Basketball Pill — explore this zhenzhen-image-nb-pro creation on OpenZhenZhen, with its original prompt and a reusable generation example.

  • Pineapple Bento Grid ShowcasePineapple Bento Grid Showcase

    API model: zhenzhen-image-nb-pro

    Pineapple Bento Grid Showcase — explore this zhenzhen-image-nb-pro creation on OpenZhenZhen, with its original prompt and a reusable generation example.

  • Framed Watercolor PortraitFramed Watercolor Portrait

    API model: zhenzhen-image-nb-pro

    Framed Watercolor Portrait — explore this zhenzhen-image-nb-pro creation on OpenZhenZhen, with its original prompt and a reusable generation example.

  • 1955 Inventions Knolling1955 Inventions Knolling

    API model: zhenzhen-image-nb-pro

    1955 Inventions Knolling — explore this zhenzhen-image-nb-pro creation on OpenZhenZhen, with its original prompt and a reusable generation example.

  • Scrapbook Collage PortraitScrapbook Collage Portrait

    API model: zhenzhen-image-nb-pro

    Scrapbook Collage Portrait — explore this zhenzhen-image-nb-pro creation on OpenZhenZhen, with its original prompt and a reusable generation example.

Explore the prompt gallery

Quick start

Example workflow: generate a 16:9 city nightscape from a prompt, then add images to match a style or edit details. The prompt is 5–5000 characters. Ratio is auto, 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9 or 21:9, defaulting to 1:1 for text-to-image and auto with references. n must be 1; output_format and quality are ignored. The low-price SKU zhenzhen-image-nb-pro-lowprice uses a different upstream: its prompt is 1–5000 characters, output_format, width, height and quality return an error, and result links expire after 2 hours.

cURL

curl --fail-with-body https://www.zzai.app/v1/image/generations \
  -H "Authorization: Bearer $SEEDANCE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"metadata":{"resolution":"1k"},"model":"zhenzhen-image-nb-pro","n":1,"prompt":"A cyberpunk city at night with neon reflections on wet streets.","size":"16:9"}'

Python

import json, os, requests

payload = json.loads(r'''{"metadata":{"resolution":"1k"},"model":"zhenzhen-image-nb-pro","n":1,"prompt":"A cyberpunk city at night with neon reflections on wet streets.","size":"16:9"}''')
response = requests.post(
    "https://www.zzai.app/v1/image/generations",
    headers={"Authorization": "Bearer " + os.environ["SEEDANCE_API_KEY"]},
    json=payload, timeout=120,
)
response.raise_for_status()
print(response.json()["id"])

JavaScript

const response = await fetch("https://www.zzai.app/v1/image/generations", {
  method: 'POST',
  headers: { Authorization: 'Bearer ' + process.env.SEEDANCE_API_KEY, 'Content-Type': 'application/json' },
  body: JSON.stringify({"metadata":{"resolution":"1k"},"model":"zhenzhen-image-nb-pro","n":1,"prompt":"A cyberpunk city at night with neon reflections on wet streets.","size":"16:9"}),
});
if (!response.ok) throw new Error(await response.text());
console.log((await response.json()).id);

Save the returned id as TASK_ID in the query example. Query every 3–5 seconds until success or failure; submission does not mean generation is complete. Save result files promptly. data.status: SUCCESS / FAILURE; data.result_url.

curl --fail-with-body https://www.zzai.app/v1/image/generations/$TASK_ID \
  -H "Authorization: Bearer $SEEDANCE_API_KEY"

Frequently asked questions

How do I call this model?

Create an API key, choose the model name below, and send a request to the documented OpenAI-compatible endpoint. Final billing follows the current price and usage parameters.