Skip to main content
POST
/
gpt-image-1.5-edit
/
async
curl --request POST \
  --url https://api.modellix.ai/api/v1/openai/gpt-image-1.5-edit/async \
  --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"
  }
}

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

​
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.

Request payload for standard GPT Image Edit models.

​
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"]
​
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"

​
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"

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.