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 two edited outputs in one run.

On WaveSpeedAI, Edit Multi costs $0.07 per image, or $0.14 per request for two images.

• 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 two edited versions of your uploaded image(s) in a single request. num_images is fixed at 2.

✔ 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.

✔ Per-image pricing

Each request generates two edited images at $0.07 per image, for a total of $0.14.

✔ 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: two edited images per request.
• num_images: fixed at 2; each request generates two images.
• aspect_ratio: 3:2, 2:3, 3:4, or 4:3.
• output_format: png or jpeg. Default: png.

Example Use Cases

• Produce multiple edited versions of a product shot for ads.
• Explore different lighting or color moods from a single input.
• Generate two 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

• $0.07 per edited image × 2 images = $0.14 per request.

💡 Best for

• Batch creative production – generate two edited alternatives per request.
• 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.
• Each request generates two images. num_images cannot be changed to another value.
• 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 once. Never retry this request automatically:
# a retry after an unclear failure can create a second, billed task.
CHECK='The task may already exist. Check History or the predictions list before submitting again.'
if ! SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  --connect-timeout 10 --max-time 60 \
  -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}"); then
  printf 'Submit failed. %s\n' "${CHECK}" >&2
  exit 1
fi

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 "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id. %s\n' "${CHECK}" >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 2. Poll until the prediction reaches a final status.
BODY_FILE=$(mktemp)
trap 'rm -f "${BODY_FILE}"' EXIT
while true; do
  # Transient errors (429, 5xx) are retried, honoring Retry-After.
  HTTP_CODE=$(curl --silent --show-error --fail-with-body \
    --connect-timeout 10 --max-time 60 --retry 5 --retry-delay 2 \
    --output "${BODY_FILE}" --write-out '%{http_code}' \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}" || true)
  case "${HTTP_CODE}" in
    2??) ;;
    000|429|5??)  # dropped connection or temporary error: keep polling
      printf 'Task %s: HTTP %s, polling again in 10s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      sleep 10; continue ;;
    *) printf 'Task %s: HTTP %s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      cat "${BODY_FILE}" >&2; exit 1 ;;
  esac
  RESULT=$(jq 'if type == "object" and has("data") then .data else . end' "${BODY_FILE}")
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout|deleted)
      printf 'Task %s ended with status %s\n' "${PREDICTION_ID}" "${STATUS}" >&2
      printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Every model also accepts the global request options enable_sync_mode and enable_base64_output; see their pages for details.

Response Parameters

Result Request Parameters

Result Response Parameters