Skip to main content
POST

Authorizations

string
required
All endpoints require authentication using a Bearer TokenGet an API Key:Visit the API Key Management Page to get your API KeyAdd to the request headers when using:

Body

string
required
Model nameFixed value: "gpt_image_1_5"
object
required
Model parameters object
string
required
Caller task IDUser-defined task identifier, required

Instructions

  • Automatic Text-to-Image / Image-to-Image Switching: Omitting image_url defaults to text-to-image; passing 1–16 reference images switches to image-to-image, which can be used for partial editing, outfit changes, background replacement, style transfer, and multi-image composition.
  • Consistent Parameters for Both Modes: Text-to-image and image-to-image use the same set of parameters and are billed according to the quality tier.
  • Output Dimensions: Determined jointly by aspect_ratio and quality, with actual pixel dimensions subject to the returned image; if you need 1K / 2K / 4K or more aspect ratios, please use GPT-Image-2.
  • No Deduction on Failure: Credits will not be deducted if the task fails.

Response

string
Initiator task ID, can be used to query results
string
Initial status, fixed to "pending"
number
Estimated credit consumption, varies with quality tier
string
Creation time (ISO format)