curl --request POST \
--url https://api.modellix.ai/api/v1/openai/gpt-image-2-edit/async \
--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": "task_abc123xyz",
"model_id": "gpt-image-2-edit"
}
}GPT Image 2 Edit is the state-of-the-art image editing model supporting high-resolution outputs including 2K (2048x2048, 2048x1152) and 4K (3840x2160, 2160x3840). Uses the size parameter for output dimensions. Default quality is low when omitted. Does not support transparent backgrounds or input fidelity control.
curl --request POST \
--url https://api.modellix.ai/api/v1/openai/gpt-image-2-edit/async \
--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": "task_abc123xyz",
"model_id": "gpt-image-2-edit"
}
}Documentation Index
Fetch the complete documentation index at: https://docs.modellix.ai/llms.txt
Use this file to discover all available pages before exploring further.
Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Body
Request payload for GPT Image 2 Edit model.
Request payload for GPT Image 2 Edit model.
Input image URL(s) to edit. Direct HTTPS URLs as string array. Supports up to 16 images for GPT Image models
1 - 16 elementsDirect image URL (https only)
["https://example.com/input.png"]Description of the desired edits, supports up to 32,000 characters
1 - 32000"Add a watercolor effect to this image"
Output image size in pixels (width x height). Includes standard and 2K/4K presets
1024x1024, 1536x1024, 1024x1536, 2048x2048, 2048x1152, 3840x2160, 2160x3840 "1024x1024"
Output quality level. 'low': fast draft (default), 'medium': balanced, 'high': best quality
low, medium, high "high"