Image Editing

The OpenAI-style image editing endpoint uses application/json and passes reference images by URL. Prefer images[].image_url; image (a single URL string, URL array, or object) and image_urls (URL string array) are also accepted as compatibility fields.

curl -X POST "https://api.routescope.ai/v1/images/edits" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-image-2",
    "prompt": "Generate a new image based on these two reference images.",
    "images": [],
    "size": "1024x1024"
  }'

curl -X POST "https://api.routescope.ai/v1/images/edits" \  -H "Content-Type: application/json" \  -d '{    "model": "gpt-image-2",    "prompt": "Generate a new image based on these two reference images.",    "images": [],    "size": "1024x1024"  }'

{
  "created": 1,
  "data": {}
}

Authorization

BearerAuth

AuthorizationBearer <token>

Model relay endpoint authentication. Header: Authorization: Bearer .

In: header

Request Body

application/json

model*string

Model name. The Tencent TokenHub channel maps it inside the gateway to the upstream model name.

Default"gpt-image-2"

prompt*string

Image editing prompt.

images?

Recommended JSON URL image input. Each item is a single image URL object.

Default[]

image?string||

Compatibility field: accepts a single URL string, a URL array, or an object. Prefer images[].image_url.

image_urls?array<string>

Compatibility field: a URL string array. Prefer images[].image_url.

mask?string

Optional. Mask image URL; transparent areas mark the regions to edit.

Formaturi

n?integer

Number of images to generate.

Formatint32

Range1 <= value

size?string

Output image size.

Default"1024x1024"

quality?string

Image quality. Allowed values depend on the upstream model.

response_format?string

Response format. Supports url or b64_json; can be omitted by default and support varies across upstream channels.

Value in"url" | "b64_json"

background?string

Background fill mode. Support depends on the model.

Default"auto"

Value in"transparent" | "opaque" | "auto"

output_format?string

Output format. Allowed values depend on the upstream model.

output_compression?integer

Output compression level. Applies to jpeg and webp only.

Default90

Formatint32

Range0 <= value <= 100

moderation?string

Moderation strength. Support depends on the model.

Default"auto"

Value in"auto" | "low"

watermark?boolean

Whether to add a watermark. Support depends on the upstream channel.

Defaultfalse

user?string

End-user identifier; useful for abuse monitoring.

Response Body

application/json

Model Selection

Model ID	Capability	Description
`gpt-image-2`	Image editing	Example model for the OpenAI-style image editing endpoint. The Tencent TokenHub channel maps it inside the gateway to the upstream model name.

Common Parameters

Field	Type	Required	Description
`model`	string	Yes	Model name. The example uses `gpt-image-2`.
`prompt`	string	Yes	Editing prompt.
`images`	array<object>	No	Recommended JSON URL image input. Each item is a single image URL object (`image_url`).
`image`	string / string[] / object	No	Compatibility field: accepts a single URL string, a URL array, or an object. Prefer `images[].image_url`.
`image_urls`	string[]	No	Compatibility field: a URL string array. Prefer `images[].image_url`.
`mask`	string	No	Mask image URL marking the area to edit.
`size`	string	No	Image size. Defaults to `1024x1024`.
`n`	integer	No	Number of images to generate.

At least one of images / image / image_urls must be provided; images[].image_url is preferred.

Optional Parameters

Field	Type	Description
`quality`	string	Image quality.
`background`	string	Background setting.
`output_format`	string	Output format.
`output_compression`	integer	Output compression level.
`moderation`	string	Content moderation level.
`watermark`	boolean	Whether to add a watermark.
`response_format`	string	Response format. Supports `url` or `b64_json`.
`user`	string	End-user identifier.

Authorization

Request Body

Response Body

200application/json

Model Selection

Common Parameters

Optional Parameters

application/json