Edits up to 16 reference images from natural-language instructions, with five quality tiers up to 4K. Sunburst is the precision tier: it spends longer per image for extra fidelity on intricate detail.
gpt-image-2-5-sunburst-editThe price changes with the quality and the resolution. The estimate call returns the exact figure for your input, free.
API keys come with the Scale and Ultra plans

The smallest request that works: the required fields only.
curl https://api.percify.io/v3/playground/v1/run \
-H "Authorization: Bearer $PERCIFY_API_TOKEN" \
-H "Content-Type: application/json" \
-d '{
"modelId": "gpt-image-2-5-sunburst-edit",
"input": {
"prompt": "A red fox running through fresh snow at sunrise",
"images": "https://example.com/photo.jpg"
}
}'8 fields in input, required first.
imagesRequiredList of URLs of input images for editing.
promptRequiredThe positive prompt for the generation.
qualityOptionalRendering quality tier. Higher tiers add detail and cost more: low is the fastest draft tier, medium is the balanced default, high and xhigh add fidelity, max is the highest-fidelity tier.
resolutionOptionalThe resolution of the output image.
aspect_ratioOptionalThe aspect ratio of the generated image. Auto-detected from input image if not specified.
output_formatOptionalThe format of the output image.
enable_sync_modeOptionalIf set to `true`, the request attempts to wait for the generated result and return outputs in the same response. If the result is not ready within the sync wait window, the API can return a timeout body while the task continues processing. This option is only available via the API and is supported only by some models.
enable_base64_outputOptionalIf set to `true`, the prediction's `output` strings are returned as **naked base64** (no `data:<mime>;base64,` prefix). When `false` (default), outputs are returned as URLs pointing to our CDN.
from $0.10Edits up to 16 reference images from natural-language instructions, with five quality tiers up to 4K.
$0.125Image 2 Image version of z-image-turbo with lora support.
$0.125A state-of-the-art text-based image editing model that delivers high-quality outputs with excellent prompt following and consistent results for transforming images through natural language
$0.125Ultra fast flux kontext endpoint

Pick a use case, run it in the playground, copy the call.
API keys come with the Scale and Ultra plans