gpt-image-2.5-sunburst API

Use the exact model ID gpt-image-2.5-sunburst. The model field must match this page exactly.

Sample outputgpt-image-2.5-sunburstPOST /v1/images/generations

Parameters: size=1536x1024n=1

Prompt: The open top deck of a car park at dusk, wet asphalt still throwing back the sky. A woman in a cobalt-blue structured trench coat has just thrown a stack of contact sheets and film strips out of her hands. The strips are not falling: they have started to unwind and climb around her in a slow rotating ribbon, every frame lit a different neon colour, magenta and acid green and amber running through the coil. One hard magenta light rakes across the deck from behind her, the city beyond still cold blue. Wide low camera, 35mm, real weight in the paper, film grain, slight vignette, no text.

Request that produced this sample

{
  "model": "gpt-image-2.5-sunburst",
  "prompt": "The open top deck of a car park at dusk, wet asphalt still throwing back the sky. A woman in a cobalt-blue structured trench coat has just thrown a stack of contact sheets and film strips out of her hands. The strips are not falling: they have started to unwind and climb around her in a slow rotating ribbon, every frame lit a different neon colour, magenta and acid green and amber running through the coil. One hard magenta light rakes across the deck from behind her, the city beyond still cold blue. Wide low camera, 35mm, real weight in the paper, film grain, slight vignette, no text.",
  "n": 1,
  "size": "1536x1024"
}

Authentication and endpoint

Use a Modelflare API key with https://modelflare.dev/v1. The gateway entry point is POST /v1/images/generations.

HTTP

Authorization: Bearer YOUR_MODELFLARE_API_KEY

Generate an image

bash

curl https://modelflare.dev/v1/images/generations \
  -H "Authorization: Bearer YOUR_MODELFLARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-image-2.5-sunburst",
    "prompt": "A white cat runs through a neon-lit street in the rain",
    "size": "1536x1024", "quality": "xhigh", "background": "opaque", "output_format": "jpeg",
    "output_compression": 85, "moderation": "auto", "n": 1
  }'

Request notes

GPT Image 2.5 Sunburst targets higher-fidelity, higher-control creation and editing; preserve images[], image[], mask, xhigh/max, and output controls for both operations.

Request parameters

GPT Image 2.5 uses the OpenAI-compatible Images API. Generation uses JSON; editing accepts JSON image references or multipart files; responses return Base64 image data in data[].b64_json.

Field	Required	Notes
model	Yes	gpt-image-2.5-sunburst
prompt	Yes	Generation or editing instruction, 1–32,000 characters
images[]	Conditional	For JSON edits, up to 16 file_id or image_url objects
images[].file_id	Conditional	Uploaded File API ID
images[].image_url	Conditional	Image URL or Base64 data URL; data URLs are limited to 20,971,520 characters
image	Conditional	One multipart source file; use image[] for multiple files
image[]	Conditional	For multipart edits, up to 16 source files
mask	No	Alpha mask matching the first source format/size and under 50 MB
size	No	auto or custom WIDTHxHEIGHT; 16-pixel multiples, 1:3–3:1 aspect ratio, 3,840px max edge, and 655,360–8,294,400 total pixels
quality	No	low / medium / high / xhigh / max / auto; default auto
background	No	auto / opaque / transparent; transparent backgrounds require PNG or WebP output
output_format	No	png / jpeg / webp; default png
output_compression	No	0–100 for JPEG/WebP, default 100; ignored for PNG
moderation	No	auto / low; default auto
n	No	1–10 outputs; default 1

Response and input limits

GPT Image 2.5 Flare and Sunburst support up to 16 edit inputs. JSON edits use images[] with file_id or image_url; multipart edits use image/image[], with each source image and mask under 50 MB. Prompts are 1–32,000 characters; quality supports low/medium/high/xhigh/max/auto; size rules are 16-pixel multiples, 1:3–3:1 aspect ratio, 3,840px max edge, and 655,360–8,294,400 total pixels. Transparent backgrounds require PNG or WebP; compression applies only to JPEG/WebP and is ignored for PNG. Resolutions above 2560x1440 are experimental. Read data[].b64_json; do not send DALL·E-only response_format. Flare is the fast, high-quality default for everyday generation and editing; Sunburst is for higher-fidelity, higher-control work.

Edit images

GPT Image 2.5 supports JSON image references and multipart file uploads through /v1/images/edits. JSON accepts up to 16 objects using file_id or image_url; multipart accepts up to 16 source files. Do not mix images with image/image[] in one request.

bash

curl https://modelflare.dev/v1/images/edits \
  -H "Authorization: Bearer YOUR_MODELFLARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-image-2.5-sunburst",
    "images": [{"file_id": "file-example123"}, {"image_url": "https://example.com/reference.png"}],
    "prompt": "Keep the product unchanged and replace the background with a warm studio gradient",
    "size": "1536x1024", "quality": "xhigh", "background": "opaque", "output_format": "png", "n": 1
  }'

bash

curl https://modelflare.dev/v1/images/edits \
  -H "Authorization: Bearer YOUR_MODELFLARE_API_KEY" \
  -F "model=gpt-image-2.5-sunburst" \
  -F "image[]=@/path/to/product.png" \
  -F "mask=@/path/to/mask.png" \
  -F "prompt=Keep the product unchanged and replace the background with a warm studio gradient" \
  -F "size=1536x1024" \
  -F "quality=xhigh" \
  -F "background=opaque" \
  -F "output_format=png" \
  -F "n=1"

Response shape

Read generated and edited results from data[]. GPT Image 2.5 returns Base64 image data; do not treat the response as URL output.

Field	Notes
created	Creation time as a Unix timestamp in seconds
data	Generated or edited image results
data[].b64_json	Base64-encoded image data
background	Final background mode: opaque or transparent
output_format	Returned image format: png, jpeg, or webp
quality	Quality tier used
size	Final dimensions as WIDTHxHEIGHT

Errors and failed tasks

Invalid model parameters return a 4xx with a request ID; use the response fields and error message defined by the selected model contract.

Supported scope

This page covers Modelflare model generation and editing calls. Search or map enrichment, voice management, and element-library management are resource APIs outside this public model-call surface and are not required request fields.

Pricing and billing

This model uses token-based billing. See the model pricing page for the current customer price, reference list price, and complete specification.

Note

This page documents Modelflare’s public interface; the fields and limits shown here are the current contract.