images

Create image

Generate images from text prompts

Request

POST /images/generations

Request Body

Field	Type	Required	Description
prompt	string	Yes	A text description of the desired image(s). - Maximum length is 32000 characters for the GPT image models - Maximum length is 1000 characters for dall-e-2 - Maximum length is 4000 characters for dall-e-3
background	object	No	Allows to set transparency for the background of the generated image(s). This parameter is only supported for the GPT image models. 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.
model	string	No	The model to use for image generation. One of dall-e-2, dall-e-3, or a GPT image model (gpt-image-1, gpt-image-1-mini, gpt-image-1.5). Defaults to dall-e-2 unless a parameter specific to the GPT image models is used.
moderation	object	No	Control the content-moderation level for images generated by the GPT image models. Must be either low for less restrictive filtering or auto (default value).
n	object	No	The number of images to generate. Must be between 1 and 10. For dall-e-3, only n=1 is supported.
output_compression	object	No	The compression level (0-100%) for the generated images. This parameter is only supported for the GPT image models with the webp or jpeg output formats, and defaults to 100.
output_format	object	No	The format in which the generated images are returned. This parameter is only supported for the GPT image models. Must be one of png, jpeg, or webp.
partial_images	integer	No	The number of partial images to generate. This parameter is used for streaming responses that return partial images. Value must be between 0 and 3. When set to 0, the response will be a single image sent in one streaming event. Note that the final image may be sent before the full number of partial images are generated if the full image is generated more quickly.
quality	object	No	The quality of the image that will be generated. - auto (default value) will automatically select the best quality for the given model. - high, medium and low are supported for the GPT image models. - hd and standard are supported for dall-e-3. - standard is the only option for dall-e-2.
response_format	object	No	The format in which generated images with dall-e-2 and dall-e-3 are returned. Must be one of url or b64_json. URLs are only valid for 60 minutes after the image has been generated. This parameter isn’t supported for the GPT image models, which always return base64-encoded images.
size	object	No	The size of the generated images. Must be one of 1024x1024, 1536x1024 (landscape), 1024x1536 (portrait), or auto (default value) for the GPT image models, one of 256x256, 512x512, or 1024x1024 for dall-e-2, and one of 1024x1024, 1792x1024, or 1024x1792 for dall-e-3.
stream	object	No	Generate the image in streaming mode. Defaults to false. See the Image generation guide for more information. This parameter is only supported for the GPT image models.
style	object	No	The style of the generated images. This parameter is only supported for dall-e-3. 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.
user	string	No	A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse.

Request Examples

Simple image generation

{
  "model": "gpt-4o-mini",
  "prompt": "A cute cat sitting on a windowsill",
  "n": 1,
  "size": "1024x1024"
}

Image generation with detailed parameters

{
  "model": "gpt-4o-mini",
  "prompt": "A futuristic city with flying cars at sunset",
  "n": 1,
  "quality": "hd",
  "size": "1792x1024",
  "style": "vivid"
}

Base64 output

{
  "model": "gpt-4o-mini",
  "prompt": "Minimalist logo of a cloud with a lightning bolt",
  "n": 1,
  "response_format": "b64_json",
  "size": "512x512"
}

Successful response

Response Schema

Field	Type	Required	Description
created	integer	Yes	-
data	Array<ImageObject>	Yes	-
usage	object	No	Usage information for image generation (provider-dependent)

Response Example

{
  "created": 1677652288,
  "data": [
    {
      "url": "https://example.com/image.png",
      "revised_prompt": "A cute orange tabby cat sitting on a white windowsill, looking outside"
    }
  ]
}

Code Examples

JavaScript (Fetch)

const response = await fetch('https://api.r9s.ai/v1/images/generations', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
  "model": "gpt-4o-mini",
  "prompt": "A cute cat sitting on a windowsill",
  "n": 1,
  "size": "1024x1024"
})
});

const data = await response.json();
console.log(data);

Python (requests)

import requests

url = "https://api.r9s.ai/v1/images/generations"
headers = {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json"
}

response = requests.post(url, json={
  "model": "gpt-4o-mini",
  "prompt": "A cute cat sitting on a windowsill",
  "n": 1,
  "size": "1024x1024"
}, headers=headers)
data = response.json()
print(data)

cURL

curl -X POST "https://api.r9s.ai/v1/images/generations" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"gpt-4o-mini","prompt":"A cute cat sitting on a windowsill","n":1,"size":"1024x1024"}'

Edit image

Create an edited or extended image given an original and prompt

Request

POST /images/edits

Request Body

Field	Type	Required	Description
image	string	Yes	The image(s) to edit. Must be a supported image file or an array of images. For the GPT image models (gpt-image-1, gpt-image-1-mini, and gpt-image-1.5): - Each image should be a png, webp, or jpg file less than 50MB - You can provide up to 16 images For dall-e-2: - You can only provide one image - It should be a square png file less than 4MB
prompt	string	Yes	A text description of the desired image(s). - Maximum length is 32000 characters for GPT image models - Maximum length is 1000 characters for dall-e-2 - Maximum length is 4000 characters for dall-e-3
mask	string	No	An additional image whose fully transparent areas (e.g. where alpha is zero) indicate where image should be edited. If there are multiple images 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.
background	object	No	Allows to set transparency for the background of the generated image(s). This parameter is only supported for the GPT image models. 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.
input_fidelity	string (high, low)	No	Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1. Unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
model	string	No	The model to use for image generation. One of dall-e-2, dall-e-3, or a GPT image model (gpt-image-1, gpt-image-1-mini, gpt-image-1.5). Defaults to dall-e-2 unless a parameter specific to the GPT image models is used.
moderation	object	No	Control the content-moderation level for images generated by the GPT image models. Must be either low for less restrictive filtering or auto (default value).
n	object	No	The number of images to generate. Must be between 1 and 10. For dall-e-3, only n=1 is supported.
output_compression	object	No	The compression level (0-100%) for the generated images. This parameter is only supported for the GPT image models with the webp or jpeg output formats, and defaults to 100.
output_format	object	No	The format in which the generated images are returned. This parameter is only supported for the GPT image models. Must be one of png, jpeg, or webp.
partial_images	integer	No	The number of partial images to generate. This parameter is used for streaming responses that return partial images. Value must be between 0 and 3. When set to 0, the response will be a single image sent in one streaming event. Note that the final image may be sent before the full number of partial images are generated if the full image is generated more quickly.
quality	object	No	The quality of the image that will be generated. - auto (default value) will automatically select the best quality for the given model. - high, medium and low are supported for the GPT image models. - hd and standard are supported for dall-e-3. - standard is the only option for dall-e-2.
response_format	object	No	The format in which generated images with dall-e-2 and dall-e-3 are returned. Must be one of url or b64_json. URLs are only valid for 60 minutes after the image has been generated. This parameter isn’t supported for the GPT image models, which always return base64-encoded images.
size	object	No	The size of the generated images. Must be one of 1024x1024, 1536x1024 (landscape), 1024x1536 (portrait), or auto (default value) for the GPT image models, one of 256x256, 512x512, or 1024x1024 for dall-e-2, and one of 1024x1024, 1792x1024, or 1024x1792 for dall-e-3.
stream	object	No	Generate the image in streaming mode. Defaults to false. See the Image generation guide for more information. This parameter is only supported for the GPT image models.
style	object	No	The style of the generated images. This parameter is only supported for dall-e-3. 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.
user	string	No	A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse.

Request Examples

Simple edit with dall-e-2

{
  "image": "data:image/png;base64,<BASE64_IMAGE>",
  "prompt": "Add a red bow tie to the cat",
  "model": "dall-e-2",
  "n": 1,
  "size": "1024x1024",
  "response_format": "url"
}

Edit using a mask (dall-e-2)

{
  "image": "data:image/png;base64,<BASE64_IMAGE>",
  "mask": "data:image/png;base64,<BASE64_MASK>",
  "prompt": "Replace the sky with a sunset",
  "model": "dall-e-2",
  "size": "512x512"
}

Edit with GPT image model

{
  "image": "data:image/png;base64,<BASE64_IMAGE>",
  "prompt": "Make the background transparent and add autumn colors",
  "model": "gpt-image-1",
  "background": "transparent",
  "output_format": "png",
  "quality": "high",
  "input_fidelity": "high",
  "n": 2
}

Streaming edit with GPT image model

{
  "image": "data:image/png;base64,<BASE64_IMAGE>",
  "prompt": "Convert to watercolor painting style",
  "model": "gpt-image-1.5",
  "stream": true,
  "partial_images": 2,
  "output_format": "webp",
  "output_compression": 85
}

Edit multiple images (GPT image models)

{
  "image": [
    "data:image/png;base64,<BASE64_IMAGE1>",
    "data:image/png;base64,<BASE64_IMAGE2>"
  ],
  "prompt": "Apply vintage filter to all images",
  "model": "gpt-image-1",
  "n": 1,
  "size": "1536x1024"
}

Successful response

Response Schema

Field	Type	Required	Description
created	integer	Yes	-
data	Array<ImageObject>	Yes	-
usage	object	No	Usage information for image generation (provider-dependent)

Response Example

{
  "created": 1677652288,
  "data": [
    {
      "url": "https://example.com/edited-image.png"
    }
  ]
}

Code Examples

JavaScript (Fetch)

const response = await fetch('https://api.r9s.ai/v1/images/edits', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({})
});

const data = await response.json();
console.log(data);

Python (requests)

import requests

url = "https://api.r9s.ai/v1/images/edits"
headers = {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json"
}

response = requests.post(url, json={}, headers=headers)
data = response.json()
print(data)

cURL

curl -X POST "https://api.r9s.ai/v1/images/edits" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{}'

Schema Reference

ImageGenerationRequest

Field	Type	Required	Description
prompt	string	Yes	A text description of the desired image(s). - Maximum length is 32000 characters for the GPT image models - Maximum length is 1000 characters for dall-e-2 - Maximum length is 4000 characters for dall-e-3
background	object	No	Allows to set transparency for the background of the generated image(s). This parameter is only supported for the GPT image models. 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.
model	string	No	The model to use for image generation. One of dall-e-2, dall-e-3, or a GPT image model (gpt-image-1, gpt-image-1-mini, gpt-image-1.5). Defaults to dall-e-2 unless a parameter specific to the GPT image models is used.
moderation	object	No	Control the content-moderation level for images generated by the GPT image models. Must be either low for less restrictive filtering or auto (default value).
n	object	No	The number of images to generate. Must be between 1 and 10. For dall-e-3, only n=1 is supported.
output_compression	object	No	The compression level (0-100%) for the generated images. This parameter is only supported for the GPT image models with the webp or jpeg output formats, and defaults to 100.
output_format	object	No	The format in which the generated images are returned. This parameter is only supported for the GPT image models. Must be one of png, jpeg, or webp.
partial_images	integer	No	The number of partial images to generate. This parameter is used for streaming responses that return partial images. Value must be between 0 and 3. When set to 0, the response will be a single image sent in one streaming event. Note that the final image may be sent before the full number of partial images are generated if the full image is generated more quickly.
quality	object	No	The quality of the image that will be generated. - auto (default value) will automatically select the best quality for the given model. - high, medium and low are supported for the GPT image models. - hd and standard are supported for dall-e-3. - standard is the only option for dall-e-2.
response_format	object	No	The format in which generated images with dall-e-2 and dall-e-3 are returned. Must be one of url or b64_json. URLs are only valid for 60 minutes after the image has been generated. This parameter isn’t supported for the GPT image models, which always return base64-encoded images.
size	object	No	The size of the generated images. Must be one of 1024x1024, 1536x1024 (landscape), 1024x1536 (portrait), or auto (default value) for the GPT image models, one of 256x256, 512x512, or 1024x1024 for dall-e-2, and one of 1024x1024, 1792x1024, or 1024x1792 for dall-e-3.
stream	object	No	Generate the image in streaming mode. Defaults to false. See the Image generation guide for more information. This parameter is only supported for the GPT image models.
style	object	No	The style of the generated images. This parameter is only supported for dall-e-3. 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.
user	string	No	A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse.

ImageGenerationResponse

Field	Type	Required	Description
created	integer	Yes	-
data	Array<ImageObject>	Yes	-
usage	object	No	Usage information for image generation (provider-dependent)

ImageObject

Field	Type	Required	Description
url	string	No	Image URL
b64_json	string	No	Base64-encoded JSON
revised_prompt	string	No	Revised prompt

ImageUsage

Field	Type	Required	Description
prompt_tokens	integer	No	Token count for the prompt
image_tokens	integer	No	Token count for the generated image (GPT-Image-1/1.5)
input_text_tokens	integer	No	Input text token count (Qwen)
output_image_tokens	integer	No	Output image token count (Qwen)
width	integer	No	Generated image width (Qwen)
height	integer	No	Generated image height (Qwen)
image_count	integer	No	Number of images generated (Qwen)

API Overview - Learn about authentication and basic information
models - View models related APIs
chat - View chat related APIs
responses - View responses related APIs
messages - View messages related APIs
completions - View completions related APIs
edits - View edits related APIs
embeddings - View embeddings related APIs
engine-embeddings - View engine-embeddings related APIs
moderations - View moderations related APIs
audio - View audio related APIs
search - View search related APIs
proxy - View proxy related APIs

images

Create image

Request

Request Body

Request Examples

Simple image generation

Image generation with detailed parameters

Base64 output

Response Schema

Response Example

Code Examples

JavaScript (Fetch)

Python (requests)

cURL

Edit image

Request

Request Body

Request Examples

Simple edit with dall-e-2

Edit using a mask (dall-e-2)

Edit with GPT image model

Streaming edit with GPT image model

Edit multiple images (GPT image models)

Response Schema

Response Example

Code Examples

JavaScript (Fetch)

Python (requests)

cURL

Schema Reference

ImageGenerationRequest

ImageGenerationResponse

ImageObject

ImageUsage

Related APIs