curl --request POST \
  --url https://api.modellix.ai/api/v1/openai/gpt-image-1.5-edit \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "images": [
    {
      "image_url": "https://example.com/input.png"
    }
  ],
  "prompt": "Convert to vintage style"
}
'

{
  "code": 0,
  "message": "success",
  "data": {
    "status": "pending",
    "task_id": "task_abc123xyz",
    "model_id": "gpt-image-2-edit"
  }
}

{
  "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 1.5 Edit

[Core Function] GPT Image 1.5 Edit is a versatile image-to-image editing and merging model. [Strengths] It excels at complex utility editing tasks, including multi-image merging (up to 16 images), transparent background support, and precise control over how strictly the model adheres to the input image (fidelity control). [Best For] Highly recommended for: merging reference images, editing UI assets, generating variations with strict shape preservation, and creating transparent cutouts. [Limitations] Do NOT use this model if you require 2K or 4K high-resolution outputs, as it is limited to standard resolutions. [Routing] Use this model specifically when the user provides multiple images to combine, requires transparency, or explicitly asks to ‘keep the exact shape’ of the original image (fidelity control). Otherwise, use GPT Image 2 Edit.

POST

openai

gpt-image-1.5-edit

curl --request POST \
  --url https://api.modellix.ai/api/v1/openai/gpt-image-1.5-edit \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "images": [
    {
      "image_url": "https://example.com/input.png"
    }
  ],
  "prompt": "Convert to vintage style"
}
'

{
  "code": 0,
  "message": "success",
  "data": {
    "status": "pending",
    "task_id": "task_abc123xyz",
    "model_id": "gpt-image-2-edit"
  }
}

{
  "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

Authorization

string

header

required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json

Request payload for standard GPT Image Edit models.

prompt

string

required

Description of the desired edits, supports up to 32,000 characters

Required string length: 1 - 32000

Example:

"Add a watercolor effect to this image"

images

string[]

required

Input image URL(s) to edit. Direct HTTPS URLs as string array. Supports up to 16 images for GPT Image models

Required array length: 1 - 16 elements

Direct image URL (https only)

Example:

["https://example.com/input.png"]

size

enum<string>

default:1024x1024

Output image size. Preset resolutions only

Available options:

1024x1024,

1536x1024,

1024x1536

Example:

"1024x1024"

quality

enum<string>

default:low

Output quality level. 'low': fast draft (default), 'medium': balanced, 'high': best quality

Available options:

low,

medium,

high

Example:

"high"

background

enum<string>

default:auto

Background transparency. 'transparent': transparent background (requires png or webp format), 'opaque': solid background, 'auto': model decides

Available options:

transparent,

opaque,

auto

Example:

"transparent"

input_fidelity

enum<string>

Control fidelity to original input image. 'high': preserve original details, 'low': more creative freedom

Available options:

high,

low

Example:

"high"

mask

string

Optional mask URL. Must be PNG with alpha channel; dimensions must match the input image exactly. Transparent areas are edited, opaque areas locked, semi-transparent areas blend with the original.

Example:

"https://example.com/mask.png"

Response

Task submitted successfully

Response object for asynchronous task submission.

code

integer

required

Response code, 0 indicates success

Example:

0

message

string

required

Response message

Example:

"success"

data

object

required

Detailed data about the submitted asynchronous task.

Show child attributes

Gpt image 1 5 Gpt image 2