OpenAI Edits

/v1/images/edits is the OpenAI Images API compatible synchronous image editing endpoint. General API keys use the synchronous image gateway. Task API keys use Task API models and pricing, and wait synchronously for the edit result.

Interface

Item	Value
Method	POST
Path	/v1/images/edits, also supports /images/edits
Content-Type	multipart/form-data or application/json
Authentication	Authorization: Bearer YOUR_API_KEY
General API key	Requires an OpenAI platform group with image generation enabled
Task API key	Uses Task API model and billing configuration

With a Task API key, this endpoint waits for up to 120 seconds. If the wait times out and the response includes task_id, use the Task API to query the final status.

Multipart Parameters

Parameter	Type	Required	Description
model	string	No	Image model. Defaults to gpt-image-2. General API keys must use an OpenAI Images compatible model; Task API keys may use any available Task API image model.
prompt	string	Yes	Edit instruction.
image	file	Yes	Input image. Multiple images can use repeated image fields or image[].
mask	file	No	Mask image.
size	string	No	Output size.
n	integer	No	Number of images.
response_format	string	No	Response format.
input_fidelity	string	No	OpenAI Images API edit parameter. Availability depends on the selected model.

JSON Parameters

Parameter	Type	Required	Description
model	string	No	Image model. Defaults to gpt-image-2. General API keys must use an OpenAI Images compatible model; Task API keys may use any available Task API image model.
prompt	string	Yes	Edit instruction.
images	array	Yes	Items support { "image_url": "https://..." }. file_id is not supported.
mask.image_url	string	No	Mask image URL. mask.file_id is not supported.
size	string	No	Output size.
n	integer	No	Number of images.

For JSON requests, image URLs must be accessible by the service. Use multipart upload when the source image is local to the client.

Multipart Example

curl https://api.llmapi.site/v1/images/edits \
  -H 'Authorization: Bearer YOUR_API_KEY' \
  -F 'model=gpt-image-2' \
  -F 'image=@input.png' \
  -F 'prompt=change the background to a clean studio setting' \
  -F 'size=1024x1024'

JSON Example

curl https://api.llmapi.site/v1/images/edits \
  -H 'Authorization: Bearer YOUR_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "gpt-image-2",
    "prompt": "replace the background with a bright studio",
    "images": [
      { "image_url": "https://example.com/input.png" }
    ],
    "size": "1024x1024"
  }'

Response — 200 OK

{
  "created": 1779912000,
  "data": [
    {
      "b64_json": "..."
    }
  ]
}

Field	Description
created	Unix timestamp when the response was created.
data[].b64_json	Base64 edited image payload when response_format is b64_json.
data[].url	Edited image URL when URL responses are available.

Errors

Status	Cause
400	Request body is invalid, an image file or images[].image_url is missing, or unsupported fields such as file_id are used.
401	API key is missing or invalid.
403	Balance, quota, or group permission check failed.
404	Current API key group cannot call the OpenAI Images API.
429	Rate limit or concurrency limit was reached.
504	Task API key synchronous wait timed out. The response includes task_id when the final status can be queried later.
500 / 502 / 503	Gateway or upstream provider failed.