Google Nano Banana Pro Edit Multi API Documentation

Google Nano Banana Pro Edit Multi API Documentation

Playground

Google’s Nano Banana Pro (Gemini 3.0 Pro Image) Edit is a next-generation image editing model capable of generating multiple high-quality edited images in a single run. Extremely low cost — only $0.07 per image. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Nano Banana Pro Edit Multi (Gemini 3.0 Pro Image) is Google’s next-generation multi-image editing model. Instead of generating a single edited image, this endpoint allows you to upload one or more input images and produce multiple edited outputs in one run.

On WaveSpeedAI, Edit Multi delivers exceptional scale efficiency at a flat $0.07 per image, making it the most cost-effective multi-edit pipeline for design, creative production, and batch asset updates.

• Need single-image hero shots? Try Nano Banana Pro Text-to-Image
• Need higher resolution? Try Nano Banana Pro Text-to-Image Ultra
• Need image editing? Try Nano Banana Pro Edit

🌟 What Makes Edit Multi Special

✔ True multi-edit generation

Generate several edited versions of your uploaded image(s) in a single request using num_images—no loops, no repeated API calls.

✔ Consistent editing style across outputs

All variants follow the same instruction but differ naturally in composition, lighting, pose, or mood—ideal for A/B testing and creative exploration.

✔ Industry-leading cost efficiency

Pay only $0.07 per edited image, regardless of batch size. Perfect for workflows needing dozens or hundreds of variations.

✔ Precise editing behavior

Handles object replacement, style changes, background editing, lighting adjustments, composition tweaks, and more.

✔ Fast, reliable, and no cold starts

Powered by WaveSpeedAI’s optimized runtime for low latency and consistent performance.

⚙️ Capabilities

• Input: one or more images + a natural-language editing prompt.
• Output: multiple edited images produced in one inference.
• num_images: number of variants to generate per request.
• aspect_ratio: multiple presets supported (square, portrait, landscape, vertical, etc.).
• output_format: jpeg, png, or webp.

Example Use Cases

• Produce multiple edited versions of a product shot for ads.
• Explore different lighting or color moods from a single input.
• Generate several background-changed variants for e-commerce or marketing.
• Create multiple stylistic interpretations for concept art or thumbnails.
• Build diverse A/B test sets for performance optimization.

💰 Pricing

• Only $0.07 per edited output image.

💡 Best for

• Batch creative production – generate many edited alternatives at once.
• Marketing & ad variations – explore different visual directions quickly.
• Product photography editing – consistent multi-angle or multi-style updates.
• Content pipelines – reduce API overhead with true multi-edit batching.
• Creative ideation – fast style exploration while keeping the source image stable.

📝 Notes

• Edits must comply with Google’s safety requirements.
• For consistent variation, keep the same input image, seed, and prompt while adjusting only num_images.
• Avoid conflicting instructions within the same prompt.
• Higher-level, descriptive prompts typically produce better edits.

🌏 Where Edit Multi Fits In

Use Google Nano Banana Pro Edit Multi when:

• You need multiple edited images from one input.
• You want consistent style but varied frames.
• You require large-scale image editing at extremely low cost.

Complementary WaveSpeedAI Models

• Nano Banana Pro Edit – for single high-precision edits.
• Nano Banana Pro Text-to-Image Multi – for generating multiple images from text.
• Nano Banana Pro Ultra – for ultra-high-resolution hero assets.
• FLUX series – for cinematic, high-impact visuals and experimental aesthetics.
• Seedream series – for cost-effective, style-consistent illustration and multi-image set generation.
• Qwen Image series – for strong LoRA support, flexible style transfer, and advanced controllability.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-api-key"

REQUEST_BODY=$(cat <<'JSON'
{
  "prompt": "A cinematic ocean wave at sunrise, highly detailed",
  "images": [
    "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
  ],
  "aspect_ratio": "3:2",
  "num_images": 2,
  "output_format": "png"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/google/nano-banana-pro/edit-multi" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}")

TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(printf '%s' "${TASK}" | jq -r '.urls.get // empty')
if [ -z "${RESULT_URL}" ]; then RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"; fi

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}")
  RESULT=$(printf '%s' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    created|processing) sleep 2 ;;
    *) printf 'Unexpected status: %s
' "${STATUS}" >&2; exit 1 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters