MaaS Image-1 Interface Documentation

Request Protocol

HTTP

Generate Images:

Header

Parameter Name	Value
Authorization	Bearer {YOUR AK}
Content-Type	application/json

Request URL

https://genaiapi.cloudsway.net/v1/ai/{YOUR ENDPOINT}/images/generations

Request Body:

Parameter Name	Type	Description
prompt	string	Text description of the desired image. The maximum length is 32,000 characters.
background	string	Allows setting the transparency of the generated image background. Must be one of transparent, opaque, or auto (default). When using auto, the model will automatically determine the best background for the image. If it is "transparent", the output format needs to support transparency, so it should be set to "png" (default) or "webp".
model	string	Model name
moderation	string	Controls the content review level of the generated images. Must be low (for less restrictive filtering) or auto (default).
n	int	Number of images to generate. Must be between 1 and 10.
output_compression	int	Compression level of the generated images (0 - 100%). This parameter only applies when the output format is webp or jpeg, and the default is 100.
output_format	string	Format of the returned generated images. Must be one of png, jpeg, or webp.
quality	string	Quality of the generated images. - auto (default) will automatically select the best quality for the given model. - Supports high, medium, and low.
size	string	Size of the generated images. Must be one of "1024x1024", "1536x1024" (landscape), "1024x1536" (portrait), or "auto" (default).
user	string	A unique identifier representing the end user

Request Example

curl --location 'https://genaiapi.cloudsway.net/v1/ai/{YOUR ENDPOINT}/images/generations' \
--header 'Authorization: Bearer {YOUR AK}' \
--header 'Content-Type: application/json' \
--data '{
    "prompt": "A photograph of a black fox in an autumn forest",
    "size": "1024x1024",
    "quality": "medium",
    "output_compression": 100,
    "output_format": "png",
    "n": 1
}
'

Response Results:

Parameter Name	Type	Description
created	int	Unix timestamp (in seconds) when the image was created.
data	List[Image]	List of generated images
usage	Usage	Token usage information for image generation.

Image:

Parameter Name	Type	Description
b64_json	string	Base64-encoded JSON of the generated image.

Usage:

Parameter Name	Type	Description
input_tokens	int	Number of tokens in the input prompt (images or text)
input_tokens_details	UsageInputTokensDetails	Details of the input tokens for image generation
output_tokens	int	Number of output image tokens
total_tokens	int	Total number of tokens for image generation

UsageInputTokensDetails:

Parameter Name	Type	Description
image_tokens	int	Number of input image tokens
text_tokens	int	Number of input text tokens

Example

{
    "created": 1747972711,
    "data": [
        {
            "b64_json": "iVBORw0KGgoAAAANSUhEU..."
        }
    ],
    "usage": {
        "input_tokens": 252,
        "output_tokens": 4160,
        "total_tokens": 4412,
        "input_tokens_details": {
            "image_tokens": 194,
            "text_tokens": 58
        }
    }
}

Edit Images:

Header

Parameter Name	Value
Authorization	Bearer {YOUR AK}
Content-Type	multipart/form-data

Request URL

https://genaiapi.cloudsway.net/v1/ai/{YOUR ENDPOINT}/images/edits

Request Body:

Parameter Name	Type	Description
image	File	Image to be edited. Must be a supported image file or an array of images. Each image should be a 'png', 'webp', or 'jpg' file smaller than 25MB, and you can provide up to 16 images at most.
prompt	string	Text description of the desired image. The maximum length is 32,000 characters.
background	string	Allows setting the transparency of the generated image background. Must be one of transparent, opaque, or auto (default). When using auto, the model will automatically determine the best background for the image. If it is "transparent", the output format needs to support transparency, so it should be set to "png" (default) or "webp".
mask	File	Additional image with fully transparent areas (e.g., alpha is zero) - Indicates where the 'image' should be edited. If multiple images are provided, the mask will be applied to the first image. Must be a valid PNG file, smaller than 4MB, and have the same dimensions as the 'image'.
model	string	Model name
n	int	Number of images to generate. Must be between 1 and 10.
quality	string	Quality of the generated images. - auto (default) will automatically select the best quality for the given model. - Supports high, medium, and low.
size	string	Size of the generated images. Must be one of "1024x1024", "1536x1024" (landscape), "1024x1536" (portrait), or "auto" (default).
user	string	A unique identifier representing the end user

Request Example

curl --location 'https://genaiapi.cloudsway.net/v1/ai/{YOUR ENDPOINT}/images/edits' \
--header 'Authorization: Bearer {YOUR AK}' \
--header 'Content-Type: multipart/form-data' \
--form 'image=@"/C:/Desktop/fox.png"' \
--form 'prompt="generate a mask delimiting the entire character in the picture, using white where the character is and black for the background. Return an image in the same size as the input image."'

Return Results

Parameter Name	Type	Description
created	int	Unix timestamp (in seconds) when the image was created.
data	List[Image]	List of generated images
usage	Usage	Token usage information for image generation.

Image:

Parameter Name	Type	Description
b64_json	string	Base64-encoded JSON of the generated image.

Usage:

Parameter Name	Type	Description
input_tokens	int	Number of tokens in the input prompt (images or text)
input_tokens_details	UsageInputTokensDetails	Details of the input tokens for image generation
output_tokens	int	Number of output image tokens
total_tokens	int	Total number of tokens for image generation

UsageInputTokensDetails:

Parameter Name	Type	Description
image_tokens	int	Number of input image tokens
text_tokens	int	Number of input text tokens

Example

{
    "created": 1748228315,
    "data": [
        {
            "b64_json": "iVBORw0KGgoAAA..."
        }
    ],
    "usage": {
        "input_tokens": 252,
        "output_tokens": 4160,
        "total_tokens": 4412,
        "input_tokens_details": {
            "image_tokens": 194,
            "text_tokens": 58
        }
    }
}