curl --request POST \
--url https://api.modellix.ai/api/v1/openai/gpt-image-2.5-flare-edit \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"images": [
"https://example.com/input.png"
],
"prompt": "Add a watercolor effect to this image"
}
'{
"code": 0,
"message": "success",
"data": {
"status": "pending",
"task_id": "12345678-1234-4234-8234-123456789abc",
"model_id": "openai/gpt-image-2.5-flare-edit",
"get_result": {
"method": "GET",
"url": "https://api.modellix.ai/api/v1/tasks/12345678-1234-4234-8234-123456789abc"
}
}
}{
"code": 400,
"message": "Invalid request parameters",
"details": {}
}{
"code": 400,
"message": "Invalid request parameters",
"details": {}
}{
"code": 400,
"message": "Invalid request parameters",
"details": {}
}{
"code": 400,
"message": "Invalid request parameters",
"details": {}
}GPT Image 2.5 Flare Edit
[Core Function] GPT Image 2.5 Flare Edit is a speed-oriented image editing model. [Strengths] Supports up to 16 input images, optional mask-based local edits, resolution tiers up to 4K, and transparent backgrounds. [Best For] Product image changes, masked object replacements, and edits guided by multiple reference images. [Limitations] Do NOT use this for editing more than 16 input images or selecting arbitrary pixel dimensions. Exact input fidelity control is not exposed. [Routing] Choose this variant when speed is the priority; use GPT Image 2.5 Sunburst Edit when image quality is the priority.
curl --request POST \
--url https://api.modellix.ai/api/v1/openai/gpt-image-2.5-flare-edit \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"images": [
"https://example.com/input.png"
],
"prompt": "Add a watercolor effect to this image"
}
'{
"code": 0,
"message": "success",
"data": {
"status": "pending",
"task_id": "12345678-1234-4234-8234-123456789abc",
"model_id": "openai/gpt-image-2.5-flare-edit",
"get_result": {
"method": "GET",
"url": "https://api.modellix.ai/api/v1/tasks/12345678-1234-4234-8234-123456789abc"
}
}
}{
"code": 400,
"message": "Invalid request parameters",
"details": {}
}{
"code": 400,
"message": "Invalid request parameters",
"details": {}
}{
"code": 400,
"message": "Invalid request parameters",
"details": {}
}{
"code": 400,
"message": "Invalid request parameters",
"details": {}
}Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Body
Request payload for GPT Image 2.5 Flare Edit.
Request payload shared by GPT Image 2.5 Sunburst Edit and Flare Edit.
Description of the desired edits, from 1 to 32,000 Unicode characters.
1 - 32000"Replace the red square with a green circle"
Input image URLs as a string array, with 1 to 16 images.
1 - 16 elements1["https://example.com/input.png"]
Optional PNG mask URL for local editing. The mask must have an alpha channel and match the first input image's dimensions. Transparent areas indicate the area to edit.
1"https://example.com/mask.png"
Output aspect ratio. Can be set independently of resolution; omitting it uses 1:1.
1:1, 3:2, 2:3, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9 "16:9"
Output resolution tier. Can be set independently of aspect_ratio; omitting it uses 1K. Pixel dimensions depend on both parameters: 1:1 + 1K gives 1024x1024, 1:1 + 4K gives 2880x2880, and 16:9 + 4K gives 3840x2160.
1K, 2K, 4K "4K"
Output quality level. Defaults to low.
low, medium, high, xhigh, max "high"
Background mode: auto lets the model choose, opaque requests an opaque background, and transparent requests a transparent background with PNG output.
auto, opaque, transparent "transparent"
Response
Task submitted successfully. Poll the URL in data.get_result.url using Query Task Result to retrieve the generated image.