Image API Reference

For the given prompt, the model generates a new image that matches the prompt description.

Create Image

Creates an image for the given text prompt.

Azure OpenAI

Request

POST https://api.core42.ai/openai//deployments/<deployment-id>/images/generations

OpenAI

Request

POST https://api.core42.ai/v1/images/generations

Request Parameters

Name	Required	Type	Description
model	true	string	ID of the model to use for this request. The available models are `dall-e-3`, `gpt-image-1`, and `sdxl-turbo`.
prompt	true	string	A text description of the desired image(s). The maximum supported length: `dall-e-3`: 4000 characters `gpt-image-1`: 32000 characters
background	false	string or null	Allows to set transparency for the background of the generated image(s). Must be one of `transparent`, `opaque` or `auto` (default value). When `auto` is used, the model will automatically determine the best background for the image. If `transparent`, the output format needs to support transparency, so it should be set to either `png` (default value) or `webp`. Note: This parameter applies only to the GPT Image 1 model.
moderation	false	string or null	Control the content-moderation level for images generated by `gpt-image-1`. Must be either `low` for less restrictive filtering or `auto` (default value). Note: This parameter applies only to the GPT Image 1 model.
n	false	integer or null	The number of images to generate. The value must be between 1 and 10. n=1 is the default and supported value for `DALL·E 3`.
quality	false	string	The quality of the image that will be generated. For `dall-e-3`: `standard` and `hd`. The default quality of the image is `standard`. For `gpt-image-1`: `high`, `medium` and `low` .
output_compression	false	integer or null	The compression level (0-100%) for the generated images. This parameter is only supported for GPT Image 1 model with the `webp`, or `jpeg` output formats and defaults to 100.
output_format	false	string or null	The format in which the generated images are returned. Must be one of `png`, `webp`, or `jpeg`. Note: This parameter applies only to the GPT Image 1 model.
response_format	false	string or null	The format in which the generated images are returned. Must be one of url or b64_json. URL validity after the image has been generated: OpenAI: One hour Azure OpenAI: 24 hours This parameter applies only to the DALL·E 3 model.
size	false	string or null	The size of the generated images. `dall-e-3`: Must be one of `1024x1024` (default value), `1792x1024`, or `1024x1792` `gpt-image-1`: Must be one of `1024x1024`, `1536x1024` (landscape), `1024x1536` (portrait), or `auto` (default value)
style	false	string or null	The style of the generated images. Must be one of `vivid` or `natural`. `Vivid` causes the model to lean towards generating hyper-real and dramatic images. `Natural` causes the model to produce more natural, less hyper-real-looking images. Note: This parameter applies only to the DALL·E 3 model.
user	false	string or null	A unique identifier represents your end-user.

For the DALL·E 3 model, the consumption for API requests is charged per unit per image. The usage can be monitored in the API request chart available on the Reports page.

Create Image Edit

Creates an edited or extended image given one or more source images and a prompt. This endpoint only supports gpt-image-1.

Azure OpenAI

Request

POST https://api.core42.ai/openai//deployments/<deployment-id>/images/edits

OpenAI

Request

POST https://api.core42.ai/v1/images/edits

Request Parameters

Name	Required	Type	Description
image	true	string or array	The image(s) to edit. Must be a supported image file or an array of images.. The available model is `gpt-image-1`. Each image should be a png, or jpg file less than 25MB. You can provide up to 16 images..
model	true	string	ID of the model to use for this request. The available models are `gpt-image-1`.
prompt	true	string	A text description of the desired image(s). The maximum supported length for `gpt-image-1` is 32000 characters.
background	false	string or null	Allows to set transparency for the background of the generated image(s). Must be one of `transparent`, `opaque`, or auto (default value). When auto is used, the model will automatically determine the best background for the image. If `transparent`, the output format needs to support transparency, so it should be set to either `png` (default value) or `webp`.
mask	false	file	An additional image whose fully transparent areas (e.g. where alpha is zero) indicate where image should be edited. If multiple images are provided, the mask will be applied on the first image. Must be a valid PNG file, less than 4MB, and have the same dimensions as image.
n	false	integer or null	The number of images to generate. The value must be between 1 and 10.
quality	false	string	The quality of the image that will be generated. For gpt-image-1: high, medium and low.
response_format	false	string or null	The format in which the generated images are returned. Must be one of url or b64_json. URL validity after the image has been generated: OpenAI: One hour Azure OpenAI: 24 hours
size	false	string or null	The size of the generated images. Must be one of `1024x1024`, `1536x1024 (landscape)`, `1024x1536(portrait)` or `auto` (default value)
user	false	string or null	A unique identifier represents your end-user.