
Nano Banana Pro
Text to image · Image editing
Starting price $0.24 / image
By OpenAI
OpenAI's image model for detailed briefs and careful edits. Generate from text, or edit up to 16 images with an optional mask, with a transparent background when you need one.
openai/gpt-image-2.5/sunburst/editThis model has other modes with their own ids: openai/gpt-image-2.5/sunburst/text-to-image.
Quote the input, start the generation with the quote, then poll the job. Set RAYWAKE_API_KEY first; see Authentication.
# 1. Price the exact input (quotes are valid for up to 10 minutes)
curl -s https://api.raywake.com/v1/quotes \
-H "Authorization: Bearer $RAYWAKE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "openai/gpt-image-2.5/sunburst/edit",
"input": {
"prompt": "Replace the plain wall behind the product with a soft pastel gradient and add a gentle shadow under it. Keep the product itself unchanged.",
"image_urls": [
"https://example.com/input.png"
]
}
}'
# 2. Start the generation with the quote_id from step 1
curl -s https://api.raywake.com/v1/generate \
-H "Authorization: Bearer $RAYWAKE_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $(uuidgen)" \
-d '{"model": "openai/gpt-image-2.5/sunburst/edit", "quote_id": "QUOTE_ID", "input": {"prompt":"Replace the plain wall behind the product with a soft pastel gradient and add a gentle shadow under it. Keep the product itself unchanged.","image_urls":["https://example.com/input.png"]}}'
# 3. Poll until the status is terminal
curl -s https://api.raywake.com/v1/jobs/JOB_ID \
-H "Authorization: Bearer $RAYWAKE_API_KEY"| Name | Type | Description |
|---|---|---|
promptrequired | string | The prompt for image generation |
image_urlsrequired | array of image URLs | The URLs of the images to use as a reference for the generation. A maximum of 16 images are allowed. |
mask_url | string (image URL) | Mask image URL. White marks regions to edit and black marks regions to keep. |
image_size | string (enum) | The size of the generated image. Use 'auto' to infer from input images. |
background | string (enum) | Background for the generated image |
quality | string (enum) | Quality for the generated image. Higher settings increase detail, latency, and token usage. Use 'auto' to let the model choose. |
num_images | integer | Number of images to generate |
output_format | string (enum) | Output format for the images |
output_compression | integer | Compression level from 0 to 100. Only supported when output_format is 'jpeg' or 'webp'. |
sync_mode | boolean | If `True`, the media will be returned as a data URI and the output data won't be available in the request history. |
A succeeded job lists its results under outputs, stored on our side. See Jobs for every field.
"outputs": [
{ "type": "image", "url": "https://…", "mime_type": "image/png", "thumbnail_url": "https://…" }
]The exact charge for your input comes from a quote. How charges settle
Fields marked * are required. Review the price before generating.
GPT Image 2.5 Sunburst turns a written brief into up to 10 images per run, in square, portrait or landscape presets or a size of your own. Quality runs from low to max, and the background can be transparent for cutouts and stickers.
The edit mode takes up to 16 images. Add a mask to keep the change inside one area: white marks what to edit and black what to keep.
Check fine texture, repeated objects and any requested text. For an edit, specify one change at a time so you can judge which instruction made the difference.