Nano Banana Pro Image Editing

google/nano-banana-pro/edit

Nano Banana Pro is Google's new state-of-the-art image generation and editing model

Base price
$0.12USD / run
Execution
async
Model type
image
Input fields
5

Try the model

Playground

Open playground
Input

PNG, JPEG, WebP, or GIF · 20 MiB maximum each

The URLs of the images to use for image-to-image generation or image editing.
The text prompt to generate an image from.
The aspect ratio of the generated image. Allowed values: 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16.
The format of the generated image. Allowed values: jpeg, png.
The resolution of the image to generate. Allowed values: 1K, 2K, 4K.
OutputReady

Your output will appear here

Complete the inputs, then click Run.

Specifications

Pricing

Base price
$0.12 / run
Billing formula
params.resolution == "4K" ? 0.24 : 0.12

Context & modalities

Input
Schema-defined
Output
image

Capabilities

Chat
Not supported
Vision
Not supported
Reasoning
Not supported
Structured output
Not supported
Function calling
Not supported
Audio input
Not supported

Access

Provider
Google
Model ID
google/nano-banana-pro/edit
Execution
async
API
Unified Run API
Endpoint
/v1/run

API README

Google Nano Banana Pro Image Editing

Precision image editing powered by Google's Nano Banana Pro model. Modify existing images with natural language instructions — swap outfits, combine subjects, change backgrounds, or restyle elements — while preserving quality and coherence.

Highlights

Multi-image synthesis — Accepts up to 14 reference images in a single request. Combine product photos, merge elements from different sources, or apply styles from one image to another.

Context-aware editing — Understands spatial relationships and visual context. Edits blend naturally with the original image, maintaining lighting consistency, perspective, and material textures.

Reference-driven generation — Use input images as style guides, subject references, or composition templates. The model extracts relevant features and applies them intelligently to the output.

Cost-efficient — $0.12 per edit (1K/2K), $0.24 for 4K. Competitive pricing regardless of the number of input images.

Pricing

ResolutionPrice
1K$0.12
2K$0.12
4K$0.24

When to Use

✅ Good fit❌ Consider alternatives
Virtual try-on (clothing on models)Generating images from zero (use Generation model)
Product photo background swapsPixel-perfect mask control
Combining multiple items into one sceneReal-time interactive editing
Style transfer across imagesVideo frame manipulation
E-commerce product visualizationSimple crops or color adjustments

Input Requirements

  • Images provided as publicly accessible URLs
  • Supported formats: PNG, JPEG, WebP
  • Up to 14 images per request
  • For best results: use consistent lighting and resolution across input images

Technical Specs

SpecValue
InputText prompt + 1–14 image URLs
OutputPNG or JPEG
Resolution1K / 2K / 4K
Aspect ratioMatches input or specified
ExecutionAsync (submit → poll for result)
Typical latency25–50 seconds

Related

Start building

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

Production API
Unified Run API endpoint
https://api.sandbase.ai/v1/run
Model ID
google/nano-banana-pro/edit
# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
  -X POST "https://api.sandbase.ai/v1/run" \
  -H "Authorization: Bearer $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'SANDBASE_JSON'
{
  "model": "google/nano-banana-pro/edit",
  "images": [
    "https://ai.google.dev/static/gemini-api/docs/images/dress.png",
    "https://ai.google.dev/static/gemini-api/docs/images/model.png"
  ],
  "prompt": "Create a professional e-commerce fashion photo. Take the blue floral dress from the first image and let the woman from the second image wear it. Generate a realistic, full-body shot of the woman wearing the dress, with the lighting and shadows adjusted to match the outdoor environment.",
  "resolution": "1K",
  "output_format": "png"
}
SANDBASE_JSON
)
run_id=$(printf '%s' "$result" | jq -r .id)
for attempt in $(seq 1 120); do
  status=$(printf '%s' "$result" | jq -r .status)
  case "$status" in completed|failed|timeout) break ;; esac
  sleep 2
  result=$(curl --fail-with-body --silent \
    -H "Authorization: Bearer $SANDBASE_API_KEY" \
    "https://api.sandbase.ai/v1/run/$run_id")
done
status=$(printf '%s' "$result" | jq -r .status)
[ "$status" = completed ] || { echo "Generation ended: $status" >&2; exit 1; }
printf '%s\n' "$result"

Choose your model

Compare models

All language models
ModelContextInput / 1MOutput / 1MReleased
Google———Nov 20, 2025
Google———Jun 30, 2026
Google———Jun 30, 2026
Google———Jun 30, 2026
Google———Feb 26, 2026
Google———Feb 26, 2026