Sign inGet an API key

Image model

Gemini Nano Banana 2.1

Gemini Nano Banana 2.1 is Google’s Flash-tier image model for text-to-image and multi-image editing, with stronger layout, text, and subject consistency than Nano Banana 2.

Model IDgoogle/gemini-nano-banana-2.1
Open in playgroundRead the docs

API

Call Gemini Nano Banana 2.1

Every model takes the same request, so switching to Gemini Nano Banana 2.1 is a change to the model field. These samples are written for its own contract and send as they are.

import Mynth from "@mynthio/sdk";

const mynth = new Mynth();

const task = await mynth.image.generate({
  model: "google/gemini-nano-banana-2.1",
  prompt: "A lighthouse at dusk, 35mm film",
  size: "16:9",
});

console.log(task.urls[0]);

Specifications

What Gemini Nano Banana 2.1 accepts

Read from the same registry the API validates against. A request outside it is refused when the task is created, before anything is charged.

Modes and inputs

Text → Image
Prompt only
Image → Image
  • Up to 14 images

Output

Aspect ratios
  • 1:1
  • 2:3
  • 3:2
  • 3:4
  • 4:3
  • 4:5
  • 5:4
  • 9:16
  • 16:9
  • 21:9
  • 4:1
  • 1:4
  • 8:1
  • 1:8

Leave out size, or send auto, and Mynth picks one for the prompt. Any other ratio snaps to the closest of these. Sizes

4K
Yes · any ratio with _4k, such as 16:9_4k

Prompt

Negative prompt
Not supported. Dropped before the provider call, no error
The contract as GET /models returns it
{
  "modes": {
    "txt->img": {},
    "img->img": {
      "inputs": {
        "rules": [
          {
            "type": "image",
            "max": 14
          }
        ]
      }
    }
  }
}

Pricing

What it costs

Pay per result, in USD, with no subscription. A failed image or video costs nothing. How pricing works

Rates

Image
$0.08 / image
Image at 4K
$0.15 / image
Input image
$0.003 / input

An input is charged once for every image it goes into: two inputs on four images are eight input charges.

Estimate a request

Images
1
Scale
Input images
0

$0.081 × $0.08

Held when the task is created. Only images that succeed are charged.

Related

Other models to consider

More from Google

Similar models

  • Wan 2.7 Image Pro
    wan/wan2.7-image-pro

    Text → ImageImage → Image4K

    $0.075 / image

  • FLUX.3
    black-forest-labs/flux-3

    Text → ImageImage → Image4K

    $0.10 / image

  • Riverflow 2.0 Pro
    sourceful/riverflow-2.0-pro

    Text → ImageImage → Image4K

    $0.15 / image

  • Kling IMAGE O3
    klingai/kling-image-o3

    Text → ImageImage → Image4K

    $0.028 / image

  • Qwen Image 2.1 Pro
    alibaba/qwen-image-2.1-pro

    Text → ImageImage → Image

    $0.075 / image