Images

Create image

images.generate(ImageGenerateParams**kwargs) -> ImagesResponse

post /images/generations

Creates an image given a prompt. Learn more.

Parameters

prompt: str

A text description of the desired image(s). The maximum length is 32000 characters for the GPT image models, 1000 characters for dall-e-2 and 4000 characters for dall-e-3.
background: Optional[Literal["transparent", "opaque", "auto"]]

Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. 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.

gpt-image-2 and gpt-image-2-2026-04-21 do not support transparent backgrounds. Requests with background set to transparent will return an error for these models; use opaque or auto instead.

If transparent, the output format needs to support transparency, so it should be set to either png (default value) or webp.
- "transparent"
- "opaque"
- "auto"
model: Optional[Union[str, ImageModel, null]]

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, gpt-image-2, or gpt-image-2-2026-04-21). Defaults to dall-e-2 unless a parameter specific to the GPT image models is used.
- str
- Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 5 more]
  - "gpt-image-1"
  - "gpt-image-1-mini"
  - "gpt-image-2"
  - "gpt-image-2-2026-04-21"
  - "gpt-image-1.5"
  - "chatgpt-image-latest"
  - "dall-e-2"
  - "dall-e-3"
moderation: Optional[Literal["low", "auto"]]

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).
- "low"
- "auto"
n: Optional[int]

The number of images to generate. Must be between 1 and 10. For dall-e-3, only n=1 is supported.
output_compression: Optional[int]

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: Optional[Literal["png", "jpeg", "webp"]]

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.
- "png"
- "jpeg"
- "webp"
partial_images: Optional[int]

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: Optional[Literal["standard", "hd", "low", 3 more]]

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.
- "standard"
- "hd"
- "low"
- "medium"
- "high"
- "auto"
response_format: Optional[Literal["url", "b64_json"]]

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.
- "url"
- "b64_json"
size: Optional[Union[str, Literal["auto", "1024x1024", "1536x1024", 5 more], null]]

The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, arbitrary resolutions are supported as WIDTHxHEIGHT strings, for example 1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above 2560x1440 are experimental, and the maximum supported resolution is 3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes 1024x1024, 1536x1024, and 1024x1536 are supported by the GPT image models; auto is supported for models that allow automatic sizing. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
- str
- Literal["auto", "1024x1024", "1536x1024", 5 more]
  
  The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, arbitrary resolutions are supported as WIDTHxHEIGHT strings, for example 1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above 2560x1440 are experimental, and the maximum supported resolution is 3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes 1024x1024, 1536x1024, and 1024x1536 are supported by the GPT image models; auto is supported for models that allow automatic sizing. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
  - "auto"
  - "1024x1024"
  - "1536x1024"
  - "1024x1536"
  - "256x256"
  - "512x512"
  - "1792x1024"
  - "1024x1792"
stream: Optional[Literal[false]]

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.
- false
style: Optional[Literal["vivid", "natural"]]

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.
- "vivid"
- "natural"
user: Optional[str]

A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. Learn more.

Returns

class ImagesResponse: …

The response from the image generation endpoint.
- created: int
  
  The Unix timestamp (in seconds) of when the image was created.
- background: Optional[Literal["transparent", "opaque"]]
  
  The background parameter used for the image generation. Either transparent or opaque.
  - "transparent"
  - "opaque"
- data: Optional[List[Image]]
  
  The list of generated images.
  - b64_json: Optional[str]
    
    The base64-encoded JSON of the generated image. Returned by default for the GPT image models, and only present if response_format is set to b64_json for dall-e-2 and dall-e-3.
  - revised_prompt: Optional[str]
    
    For dall-e-3 only, the revised prompt that was used to generate the image.
  - url: Optional[str]
    
    When using dall-e-2 or dall-e-3, the URL of the generated image if response_format is set to url (default value). Unsupported for the GPT image models.
- output_format: Optional[Literal["png", "webp", "jpeg"]]
  
  The output format of the image generation. Either png, webp, or jpeg.
  - "png"
  - "webp"
  - "jpeg"
- quality: Optional[Literal["low", "medium", "high"]]
  
  The quality of the image generated. Either low, medium, or high.
  - "low"
  - "medium"
  - "high"
- size: Optional[Literal["1024x1024", "1024x1536", "1536x1024"]]
  
  The size of the image generated. Either 1024x1024, 1024x1536, or 1536x1024.
  - "1024x1024"
  - "1024x1536"
  - "1536x1024"
- usage: Optional[Usage]
  
  For gpt-image-1 only, the token usage information for the image generation.
  - input_tokens: int
    
    The number of tokens (images and text) in the input prompt.
  - input_tokens_details: UsageInputTokensDetails
    
    The input tokens detailed information for the image generation.
    - image_tokens: int
      
      The number of image tokens in the input prompt.
    - text_tokens: int
      
      The number of text tokens in the input prompt.
  - output_tokens: int
    
    The number of output tokens generated by the model.
  - total_tokens: int
    
    The total number of tokens (images and text) used for the image generation.
  - output_tokens_details: Optional[UsageOutputTokensDetails]
    
    The output token details for the image generation.
    - image_tokens: int
      
      The number of image output tokens generated by the model.
    - text_tokens: int
      
      The number of text output tokens generated by the model.

Example

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ.get("OPENAI_API_KEY"),  # This is the default and can be omitted
)
for image in client.images.generate(
    prompt="A cute baby sea otter",
):
  print(image)

Response

{
  "created": 0,
  "background": "transparent",
  "data": [
    {
      "b64_json": "b64_json",
      "revised_prompt": "revised_prompt",
      "url": "https://example.com"
    }
  ],
  "output_format": "png",
  "quality": "low",
  "size": "1024x1024",
  "usage": {
    "input_tokens": 0,
    "input_tokens_details": {
      "image_tokens": 0,
      "text_tokens": 0
    },
    "output_tokens": 0,
    "total_tokens": 0,
    "output_tokens_details": {
      "image_tokens": 0,
      "text_tokens": 0
    }
  }
}

Generate image

import base64
from openai import OpenAI
client = OpenAI()

img = client.images.generate(
    model="gpt-image-1.5",
    prompt="A cute baby sea otter",
    n=1,
    size="1024x1024"
)

image_bytes = base64.b64decode(img.data[0].b64_json)
with open("output.png", "wb") as f:
    f.write(image_bytes)

Response

{
  "created": 1713833628,
  "data": [
    {
      "b64_json": "..."
    }
  ],
  "usage": {
    "total_tokens": 100,
    "input_tokens": 50,
    "output_tokens": 50,
    "input_tokens_details": {
      "text_tokens": 10,
      "image_tokens": 40
    }
  }
}

Streaming

from openai import OpenAI

client = OpenAI()

stream = client.images.generate(
    model="gpt-image-1.5",
    prompt="A cute baby sea otter",
    n=1,
    size="1024x1024",
    stream=True
)

for event in stream:
    print(event)

Response

event: image_generation.partial_image
data: {"type":"image_generation.partial_image","b64_json":"...","partial_image_index":0}

event: image_generation.completed
data: {"type":"image_generation.completed","b64_json":"...","usage":{"total_tokens":100,"input_tokens":50,"output_tokens":50,"input_tokens_details":{"text_tokens":10,"image_tokens":40}}}

Create image edit

images.edit(ImageEditParams**kwargs) -> ImagesResponse

post /images/edits

Creates an edited or extended image given one or more source images and a prompt. This endpoint supports GPT Image models (gpt-image-1.5, gpt-image-1, gpt-image-1-mini, and chatgpt-image-latest) and dall-e-2.

Parameters

image: Union[FileTypes, Sequence[FileTypes]]

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, gpt-image-1.5, gpt-image-2, gpt-image-2-2026-04-21, and chatgpt-image-latest), 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, and it should be a square png file less than 4MB.
- FileTypes
- Sequence[FileTypes]
prompt: str

A text description of the desired image(s). The maximum length is 1000 characters for dall-e-2, and 32000 characters for the GPT image models.
background: Optional[Literal["transparent", "opaque", "auto"]]

Allows to set transparency for the background of the generated image(s). This parameter is only supported for GPT image models that support transparent backgrounds. 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.

gpt-image-2 and gpt-image-2-2026-04-21 do not support transparent backgrounds. Requests with background set to transparent will return an error for these models; use opaque or auto instead.

If transparent, the output format needs to support transparency, so it should be set to either png (default value) or webp.
- "transparent"
- "opaque"
- "auto"
input_fidelity: Optional[Literal["high", "low"]]

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 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.
- "high"
- "low"
mask: Optional[FileTypes]

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.
model: Optional[Union[str, ImageModel, null]]

The model to use for image generation. One of dall-e-2 or a GPT image model (gpt-image-1, gpt-image-1-mini, gpt-image-1.5, gpt-image-2, gpt-image-2-2026-04-21, or chatgpt-image-latest). Defaults to gpt-image-1.5.
- str
- Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 5 more]
  - "gpt-image-1"
  - "gpt-image-1-mini"
  - "gpt-image-2"
  - "gpt-image-2-2026-04-21"
  - "gpt-image-1.5"
  - "chatgpt-image-latest"
  - "dall-e-2"
  - "dall-e-3"
n: Optional[int]

The number of images to generate. Must be between 1 and 10.
output_compression: Optional[int]

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: Optional[Literal["png", "jpeg", "webp"]]

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. The default value is png.
- "png"
- "jpeg"
- "webp"
partial_images: Optional[int]

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: Optional[Literal["standard", "low", "medium", 2 more]]

The quality of the image that will be generated for GPT image models. Defaults to auto.
- "standard"
- "low"
- "medium"
- "high"
- "auto"
response_format: Optional[Literal["url", "b64_json"]]

The format in which the generated images 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 is only supported for dall-e-2 (default is url for dall-e-2), as GPT image models always return base64-encoded images.
- "url"
- "b64_json"
size: Optional[Union[str, Literal["256x256", "512x512", "1024x1024", 3 more], null]]

The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, arbitrary resolutions are supported as WIDTHxHEIGHT strings, for example 1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above 2560x1440 are experimental, and the maximum supported resolution is 3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes 1024x1024, 1536x1024, and 1024x1536 are supported by the GPT image models; auto is supported for models that allow automatic sizing. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
- str
- Literal["256x256", "512x512", "1024x1024", 3 more]
  
  The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, arbitrary resolutions are supported as WIDTHxHEIGHT strings, for example 1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above 2560x1440 are experimental, and the maximum supported resolution is 3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes 1024x1024, 1536x1024, and 1024x1536 are supported by the GPT image models; auto is supported for models that allow automatic sizing. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.
  - "256x256"
  - "512x512"
  - "1024x1024"
  - "1536x1024"
  - "1024x1536"
  - "auto"
stream: Optional[Literal[false]]

Edit the image in streaming mode. Defaults to false. See the Image generation guide for more information.
- false
user: Optional[str]

A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. Learn more.

Returns

class ImagesResponse: …

The response from the image generation endpoint.
- created: int
  
  The Unix timestamp (in seconds) of when the image was created.
- background: Optional[Literal["transparent", "opaque"]]
  
  The background parameter used for the image generation. Either transparent or opaque.
  - "transparent"
  - "opaque"
- data: Optional[List[Image]]
  
  The list of generated images.
  - b64_json: Optional[str]
    
    The base64-encoded JSON of the generated image. Returned by default for the GPT image models, and only present if response_format is set to b64_json for dall-e-2 and dall-e-3.
  - revised_prompt: Optional[str]
    
    For dall-e-3 only, the revised prompt that was used to generate the image.
  - url: Optional[str]
    
    When using dall-e-2 or dall-e-3, the URL of the generated image if response_format is set to url (default value). Unsupported for the GPT image models.
- output_format: Optional[Literal["png", "webp", "jpeg"]]
  
  The output format of the image generation. Either png, webp, or jpeg.
  - "png"
  - "webp"
  - "jpeg"
- quality: Optional[Literal["low", "medium", "high"]]
  
  The quality of the image generated. Either low, medium, or high.
  - "low"
  - "medium"
  - "high"
- size: Optional[Literal["1024x1024", "1024x1536", "1536x1024"]]
  
  The size of the image generated. Either 1024x1024, 1024x1536, or 1536x1024.
  - "1024x1024"
  - "1024x1536"
  - "1536x1024"
- usage: Optional[Usage]
  
  For gpt-image-1 only, the token usage information for the image generation.
  - input_tokens: int
    
    The number of tokens (images and text) in the input prompt.
  - input_tokens_details: UsageInputTokensDetails
    
    The input tokens detailed information for the image generation.
    - image_tokens: int
      
      The number of image tokens in the input prompt.
    - text_tokens: int
      
      The number of text tokens in the input prompt.
  - output_tokens: int
    
    The number of output tokens generated by the model.
  - total_tokens: int
    
    The total number of tokens (images and text) used for the image generation.
  - output_tokens_details: Optional[UsageOutputTokensDetails]
    
    The output token details for the image generation.
    - image_tokens: int
      
      The number of image output tokens generated by the model.
    - text_tokens: int
      
      The number of text output tokens generated by the model.

Example

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ.get("OPENAI_API_KEY"),  # This is the default and can be omitted
)
for image in client.images.edit(
    image=b"Example data",
    prompt="A cute baby sea otter wearing a beret",
):
  print(image)

Response

{
  "created": 0,
  "background": "transparent",
  "data": [
    {
      "b64_json": "b64_json",
      "revised_prompt": "revised_prompt",
      "url": "https://example.com"
    }
  ],
  "output_format": "png",
  "quality": "low",
  "size": "1024x1024",
  "usage": {
    "input_tokens": 0,
    "input_tokens_details": {
      "image_tokens": 0,
      "text_tokens": 0
    },
    "output_tokens": 0,
    "total_tokens": 0,
    "output_tokens_details": {
      "image_tokens": 0,
      "text_tokens": 0
    }
  }
}

Edit image

import base64
from openai import OpenAI
client = OpenAI()

prompt = """
Generate a photorealistic image of a gift basket on a white background
labeled 'Relax & Unwind' with a ribbon and handwriting-like font,
containing all the items in the reference pictures.
"""

result = client.images.edit(
    model="gpt-image-1.5",
    image=[
        open("body-lotion.png", "rb"),
        open("bath-bomb.png", "rb"),
        open("incense-kit.png", "rb"),
        open("soap.png", "rb"),
    ],
    prompt=prompt
)

image_base64 = result.data[0].b64_json
image_bytes = base64.b64decode(image_base64)

# Save the image to a file
with open("gift-basket.png", "wb") as f:
    f.write(image_bytes)

Streaming

from openai import OpenAI

client = OpenAI()

prompt = """
Generate a photorealistic image of a gift basket on a white background
labeled 'Relax & Unwind' with a ribbon and handwriting-like font,
containing all the items in the reference pictures.
"""

stream = client.images.edit(
    model="gpt-image-1.5",
    image=[
        open("body-lotion.png", "rb"),
        open("bath-bomb.png", "rb"),
        open("incense-kit.png", "rb"),
        open("soap.png", "rb"),
    ],
    prompt=prompt,
    stream=True
)

for event in stream:
    print(event)

Response

event: image_edit.partial_image
data: {"type":"image_edit.partial_image","b64_json":"...","partial_image_index":0}

event: image_edit.completed
data: {"type":"image_edit.completed","b64_json":"...","usage":{"total_tokens":100,"input_tokens":50,"output_tokens":50,"input_tokens_details":{"text_tokens":10,"image_tokens":40}}}

Create image variation

images.create_variation(ImageCreateVariationParams**kwargs) -> ImagesResponse

post /images/variations

Creates a variation of a given image. This endpoint only supports dall-e-2.

Parameters

image: FileTypes

The image to use as the basis for the variation(s). Must be a valid PNG file, less than 4MB, and square.
model: Optional[Union[str, ImageModel, null]]

The model to use for image generation. Only dall-e-2 is supported at this time.
- str
- Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 5 more]
  - "gpt-image-1"
  - "gpt-image-1-mini"
  - "gpt-image-2"
  - "gpt-image-2-2026-04-21"
  - "gpt-image-1.5"
  - "chatgpt-image-latest"
  - "dall-e-2"
  - "dall-e-3"
n: Optional[int]

The number of images to generate. Must be between 1 and 10.
response_format: Optional[Literal["url", "b64_json"]]

The format in which the generated images are returned. Must be one of url or b64_json. URLs are only valid for 60 minutes after the image has been generated.
- "url"
- "b64_json"
size: Optional[Literal["256x256", "512x512", "1024x1024"]]

The size of the generated images. Must be one of 256x256, 512x512, or 1024x1024.
- "256x256"
- "512x512"
- "1024x1024"
user: Optional[str]

A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. Learn more.

Returns

class ImagesResponse: …

The response from the image generation endpoint.
- created: int
  
  The Unix timestamp (in seconds) of when the image was created.
- background: Optional[Literal["transparent", "opaque"]]
  
  The background parameter used for the image generation. Either transparent or opaque.
  - "transparent"
  - "opaque"
- data: Optional[List[Image]]
  
  The list of generated images.
  - b64_json: Optional[str]
    
    The base64-encoded JSON of the generated image. Returned by default for the GPT image models, and only present if response_format is set to b64_json for dall-e-2 and dall-e-3.
  - revised_prompt: Optional[str]
    
    For dall-e-3 only, the revised prompt that was used to generate the image.
  - url: Optional[str]
    
    When using dall-e-2 or dall-e-3, the URL of the generated image if response_format is set to url (default value). Unsupported for the GPT image models.
- output_format: Optional[Literal["png", "webp", "jpeg"]]
  
  The output format of the image generation. Either png, webp, or jpeg.
  - "png"
  - "webp"
  - "jpeg"
- quality: Optional[Literal["low", "medium", "high"]]
  
  The quality of the image generated. Either low, medium, or high.
  - "low"
  - "medium"
  - "high"
- size: Optional[Literal["1024x1024", "1024x1536", "1536x1024"]]
  
  The size of the image generated. Either 1024x1024, 1024x1536, or 1536x1024.
  - "1024x1024"
  - "1024x1536"
  - "1536x1024"
- usage: Optional[Usage]
  
  For gpt-image-1 only, the token usage information for the image generation.
  - input_tokens: int
    
    The number of tokens (images and text) in the input prompt.
  - input_tokens_details: UsageInputTokensDetails
    
    The input tokens detailed information for the image generation.
    - image_tokens: int
      
      The number of image tokens in the input prompt.
    - text_tokens: int
      
      The number of text tokens in the input prompt.
  - output_tokens: int
    
    The number of output tokens generated by the model.
  - total_tokens: int
    
    The total number of tokens (images and text) used for the image generation.
  - output_tokens_details: Optional[UsageOutputTokensDetails]
    
    The output token details for the image generation.
    - image_tokens: int
      
      The number of image output tokens generated by the model.
    - text_tokens: int
      
      The number of text output tokens generated by the model.

Example

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ.get("OPENAI_API_KEY"),  # This is the default and can be omitted
)
images_response = client.images.create_variation(
    image=b"Example data",
)
print(images_response.created)

Response

{
  "created": 0,
  "background": "transparent",
  "data": [
    {
      "b64_json": "b64_json",
      "revised_prompt": "revised_prompt",
      "url": "https://example.com"
    }
  ],
  "output_format": "png",
  "quality": "low",
  "size": "1024x1024",
  "usage": {
    "input_tokens": 0,
    "input_tokens_details": {
      "image_tokens": 0,
      "text_tokens": 0
    },
    "output_tokens": 0,
    "total_tokens": 0,
    "output_tokens_details": {
      "image_tokens": 0,
      "text_tokens": 0
    }
  }
}

Example

from openai import OpenAI
client = OpenAI()

response = client.images.create_variation(
  image=open("image_edit_original.png", "rb"),
  n=2,
  size="1024x1024"
)

Response

{
  "created": 1589478378,
  "data": [
    {
      "url": "https://..."
    },
    {
      "url": "https://..."
    }
  ]
}

Domain Types

Image

class Image: …

Represents the content or the URL of an image generated by the OpenAI API.
- b64_json: Optional[str]
  
  The base64-encoded JSON of the generated image. Returned by default for the GPT image models, and only present if response_format is set to b64_json for dall-e-2 and dall-e-3.
- revised_prompt: Optional[str]
  
  For dall-e-3 only, the revised prompt that was used to generate the image.
- url: Optional[str]
  
  When using dall-e-2 or dall-e-3, the URL of the generated image if response_format is set to url (default value). Unsupported for the GPT image models.

Image Edit Completed Event

class ImageEditCompletedEvent: …

Emitted when image editing has completed and the final image is available.
- b64_json: str
  
  Base64-encoded final edited image data, suitable for rendering as an image.
- background: Literal["transparent", "opaque", "auto"]
  
  The background setting for the edited image.
  - "transparent"
  - "opaque"
  - "auto"
- created_at: int
  
  The Unix timestamp when the event was created.
- output_format: Literal["png", "webp", "jpeg"]
  
  The output format for the edited image.
  - "png"
  - "webp"
  - "jpeg"
- quality: Literal["low", "medium", "high", "auto"]
  
  The quality setting for the edited image.
  - "low"
  - "medium"
  - "high"
  - "auto"
- size: Literal["1024x1024", "1024x1536", "1536x1024", "auto"]
  
  The size of the edited image.
  - "1024x1024"
  - "1024x1536"
  - "1536x1024"
  - "auto"
- type: Literal["image_edit.completed"]
  
  The type of the event. Always image_edit.completed.
  - "image_edit.completed"
- usage: Usage
  
  For the GPT image models only, the token usage information for the image generation.
  - input_tokens: int
    
    The number of tokens (images and text) in the input prompt.
  - input_tokens_details: UsageInputTokensDetails
    
    The input tokens detailed information for the image generation.
    - image_tokens: int
      
      The number of image tokens in the input prompt.
    - text_tokens: int
      
      The number of text tokens in the input prompt.
  - output_tokens: int
    
    The number of image tokens in the output image.
  - total_tokens: int
    
    The total number of tokens (images and text) used for the image generation.

Image Edit Partial Image Event

class ImageEditPartialImageEvent: …

Emitted when a partial image is available during image editing streaming.
- b64_json: str
  
  Base64-encoded partial image data, suitable for rendering as an image.
- background: Literal["transparent", "opaque", "auto"]
  
  The background setting for the requested edited image.
  - "transparent"
  - "opaque"
  - "auto"
- created_at: int
  
  The Unix timestamp when the event was created.
- output_format: Literal["png", "webp", "jpeg"]
  
  The output format for the requested edited image.
  - "png"
  - "webp"
  - "jpeg"
- partial_image_index: int
  
  0-based index for the partial image (streaming).
- quality: Literal["low", "medium", "high", "auto"]
  
  The quality setting for the requested edited image.
  - "low"
  - "medium"
  - "high"
  - "auto"
- size: Literal["1024x1024", "1024x1536", "1536x1024", "auto"]
  
  The size of the requested edited image.
  - "1024x1024"
  - "1024x1536"
  - "1536x1024"
  - "auto"
- type: Literal["image_edit.partial_image"]
  
  The type of the event. Always image_edit.partial_image.
  - "image_edit.partial_image"

Image Edit Stream Event

ImageEditStreamEvent

Emitted when a partial image is available during image editing streaming.
- class ImageEditPartialImageEvent: …
  
  Emitted when a partial image is available during image editing streaming.
  - b64_json: str
    
    Base64-encoded partial image data, suitable for rendering as an image.
  - background: Literal["transparent", "opaque", "auto"]
    
    The background setting for the requested edited image.
    - "transparent"
    - "opaque"
    - "auto"
  - created_at: int
    
    The Unix timestamp when the event was created.
  - output_format: Literal["png", "webp", "jpeg"]
    
    The output format for the requested edited image.
    - "png"
    - "webp"
    - "jpeg"
  - partial_image_index: int
    
    0-based index for the partial image (streaming).
  - quality: Literal["low", "medium", "high", "auto"]
    
    The quality setting for the requested edited image.
    - "low"
    - "medium"
    - "high"
    - "auto"
  - size: Literal["1024x1024", "1024x1536", "1536x1024", "auto"]
    
    The size of the requested edited image.
    - "1024x1024"
    - "1024x1536"
    - "1536x1024"
    - "auto"
  - type: Literal["image_edit.partial_image"]
    
    The type of the event. Always image_edit.partial_image.
    - "image_edit.partial_image"
- class ImageEditCompletedEvent: …
  
  Emitted when image editing has completed and the final image is available.
  - b64_json: str
    
    Base64-encoded final edited image data, suitable for rendering as an image.
  - background: Literal["transparent", "opaque", "auto"]
    
    The background setting for the edited image.
    - "transparent"
    - "opaque"
    - "auto"
  - created_at: int
    
    The Unix timestamp when the event was created.
  - output_format: Literal["png", "webp", "jpeg"]
    
    The output format for the edited image.
    - "png"
    - "webp"
    - "jpeg"
  - quality: Literal["low", "medium", "high", "auto"]
    
    The quality setting for the edited image.
    - "low"
    - "medium"
    - "high"
    - "auto"
  - size: Literal["1024x1024", "1024x1536", "1536x1024", "auto"]
    
    The size of the edited image.
    - "1024x1024"
    - "1024x1536"
    - "1536x1024"
    - "auto"
  - type: Literal["image_edit.completed"]
    
    The type of the event. Always image_edit.completed.
    - "image_edit.completed"
  - usage: Usage
    
    For the GPT image models only, the token usage information for the image generation.
    - input_tokens: int
      
      The number of tokens (images and text) in the input prompt.
    - input_tokens_details: UsageInputTokensDetails
      
      The input tokens detailed information for the image generation.
      - image_tokens: int
        
        The number of image tokens in the input prompt.
      - text_tokens: int
        
        The number of text tokens in the input prompt.
    - output_tokens: int
      
      The number of image tokens in the output image.
    - total_tokens: int
      
      The total number of tokens (images and text) used for the image generation.

Image Gen Completed Event

class ImageGenCompletedEvent: …

Emitted when image generation has completed and the final image is available.
- b64_json: str
  
  Base64-encoded image data, suitable for rendering as an image.
- background: Literal["transparent", "opaque", "auto"]
  
  The background setting for the generated image.
  - "transparent"
  - "opaque"
  - "auto"
- created_at: int
  
  The Unix timestamp when the event was created.
- output_format: Literal["png", "webp", "jpeg"]
  
  The output format for the generated image.
  - "png"
  - "webp"
  - "jpeg"
- quality: Literal["low", "medium", "high", "auto"]
  
  The quality setting for the generated image.
  - "low"
  - "medium"
  - "high"
  - "auto"
- size: Literal["1024x1024", "1024x1536", "1536x1024", "auto"]
  
  The size of the generated image.
  - "1024x1024"
  - "1024x1536"
  - "1536x1024"
  - "auto"
- type: Literal["image_generation.completed"]
  
  The type of the event. Always image_generation.completed.
  - "image_generation.completed"
- usage: Usage
  
  For the GPT image models only, the token usage information for the image generation.
  - input_tokens: int
    
    The number of tokens (images and text) in the input prompt.
  - input_tokens_details: UsageInputTokensDetails
    
    The input tokens detailed information for the image generation.
    - image_tokens: int
      
      The number of image tokens in the input prompt.
    - text_tokens: int
      
      The number of text tokens in the input prompt.
  - output_tokens: int
    
    The number of image tokens in the output image.
  - total_tokens: int
    
    The total number of tokens (images and text) used for the image generation.

Image Gen Partial Image Event

class ImageGenPartialImageEvent: …

Emitted when a partial image is available during image generation streaming.
- b64_json: str
  
  Base64-encoded partial image data, suitable for rendering as an image.
- background: Literal["transparent", "opaque", "auto"]
  
  The background setting for the requested image.
  - "transparent"
  - "opaque"
  - "auto"
- created_at: int
  
  The Unix timestamp when the event was created.
- output_format: Literal["png", "webp", "jpeg"]
  
  The output format for the requested image.
  - "png"
  - "webp"
  - "jpeg"
- partial_image_index: int
  
  0-based index for the partial image (streaming).
- quality: Literal["low", "medium", "high", "auto"]
  
  The quality setting for the requested image.
  - "low"
  - "medium"
  - "high"
  - "auto"
- size: Literal["1024x1024", "1024x1536", "1536x1024", "auto"]
  
  The size of the requested image.
  - "1024x1024"
  - "1024x1536"
  - "1536x1024"
  - "auto"
- type: Literal["image_generation.partial_image"]
  
  The type of the event. Always image_generation.partial_image.
  - "image_generation.partial_image"

Image Gen Stream Event

ImageGenStreamEvent

Emitted when a partial image is available during image generation streaming.
- class ImageGenPartialImageEvent: …
  
  Emitted when a partial image is available during image generation streaming.
  - b64_json: str
    
    Base64-encoded partial image data, suitable for rendering as an image.
  - background: Literal["transparent", "opaque", "auto"]
    
    The background setting for the requested image.
    - "transparent"
    - "opaque"
    - "auto"
  - created_at: int
    
    The Unix timestamp when the event was created.
  - output_format: Literal["png", "webp", "jpeg"]
    
    The output format for the requested image.
    - "png"
    - "webp"
    - "jpeg"
  - partial_image_index: int
    
    0-based index for the partial image (streaming).
  - quality: Literal["low", "medium", "high", "auto"]
    
    The quality setting for the requested image.
    - "low"
    - "medium"
    - "high"
    - "auto"
  - size: Literal["1024x1024", "1024x1536", "1536x1024", "auto"]
    
    The size of the requested image.
    - "1024x1024"
    - "1024x1536"
    - "1536x1024"
    - "auto"
  - type: Literal["image_generation.partial_image"]
    
    The type of the event. Always image_generation.partial_image.
    - "image_generation.partial_image"
- class ImageGenCompletedEvent: …
  
  Emitted when image generation has completed and the final image is available.
  - b64_json: str
    
    Base64-encoded image data, suitable for rendering as an image.
  - background: Literal["transparent", "opaque", "auto"]
    
    The background setting for the generated image.
    - "transparent"
    - "opaque"
    - "auto"
  - created_at: int
    
    The Unix timestamp when the event was created.
  - output_format: Literal["png", "webp", "jpeg"]
    
    The output format for the generated image.
    - "png"
    - "webp"
    - "jpeg"
  - quality: Literal["low", "medium", "high", "auto"]
    
    The quality setting for the generated image.
    - "low"
    - "medium"
    - "high"
    - "auto"
  - size: Literal["1024x1024", "1024x1536", "1536x1024", "auto"]
    
    The size of the generated image.
    - "1024x1024"
    - "1024x1536"
    - "1536x1024"
    - "auto"
  - type: Literal["image_generation.completed"]
    
    The type of the event. Always image_generation.completed.
    - "image_generation.completed"
  - usage: Usage
    
    For the GPT image models only, the token usage information for the image generation.
    - input_tokens: int
      
      The number of tokens (images and text) in the input prompt.
    - input_tokens_details: UsageInputTokensDetails
      
      The input tokens detailed information for the image generation.
      - image_tokens: int
        
        The number of image tokens in the input prompt.
      - text_tokens: int
        
        The number of text tokens in the input prompt.
    - output_tokens: int
      
      The number of image tokens in the output image.
    - total_tokens: int
      
      The total number of tokens (images and text) used for the image generation.

Image Model

Literal["gpt-image-1", "gpt-image-1-mini", "gpt-image-2", 5 more]
- "gpt-image-1"
- "gpt-image-1-mini"
- "gpt-image-2"
- "gpt-image-2-2026-04-21"
- "gpt-image-1.5"
- "chatgpt-image-latest"
- "dall-e-2"
- "dall-e-3"

Images Response

class ImagesResponse: …

The response from the image generation endpoint.
- created: int
  
  The Unix timestamp (in seconds) of when the image was created.
- background: Optional[Literal["transparent", "opaque"]]
  
  The background parameter used for the image generation. Either transparent or opaque.
  - "transparent"
  - "opaque"
- data: Optional[List[Image]]
  
  The list of generated images.
  - b64_json: Optional[str]
    
    The base64-encoded JSON of the generated image. Returned by default for the GPT image models, and only present if response_format is set to b64_json for dall-e-2 and dall-e-3.
  - revised_prompt: Optional[str]
    
    For dall-e-3 only, the revised prompt that was used to generate the image.
  - url: Optional[str]
    
    When using dall-e-2 or dall-e-3, the URL of the generated image if response_format is set to url (default value). Unsupported for the GPT image models.
- output_format: Optional[Literal["png", "webp", "jpeg"]]
  
  The output format of the image generation. Either png, webp, or jpeg.
  - "png"
  - "webp"
  - "jpeg"
- quality: Optional[Literal["low", "medium", "high"]]
  
  The quality of the image generated. Either low, medium, or high.
  - "low"
  - "medium"
  - "high"
- size: Optional[Literal["1024x1024", "1024x1536", "1536x1024"]]
  
  The size of the image generated. Either 1024x1024, 1024x1536, or 1536x1024.
  - "1024x1024"
  - "1024x1536"
  - "1536x1024"
- usage: Optional[Usage]
  
  For gpt-image-1 only, the token usage information for the image generation.
  - input_tokens: int
    
    The number of tokens (images and text) in the input prompt.
  - input_tokens_details: UsageInputTokensDetails
    
    The input tokens detailed information for the image generation.
    - image_tokens: int
      
      The number of image tokens in the input prompt.
    - text_tokens: int
      
      The number of text tokens in the input prompt.
  - output_tokens: int
    
    The number of output tokens generated by the model.
  - total_tokens: int
    
    The total number of tokens (images and text) used for the image generation.
  - output_tokens_details: Optional[UsageOutputTokensDetails]
    
    The output token details for the image generation.
    - image_tokens: int
      
      The number of image output tokens generated by the model.
    - text_tokens: int
      
      The number of text output tokens generated by the model.

python/resources/images/index.md +42 −2

124 124

125 - `"b64_json"`125 - `"b64_json"`

126 126

127- `size: Optional[str]`127- `size: Optional[Union[str, Literal["auto", "1024x1024", "1536x1024", 5 more], null]]`

128 128

129 The size of the generated images. For `gpt-image-2` and `gpt-image-2-2026-04-21`, arbitrary resolutions are supported as `WIDTHxHEIGHT` strings, for example `1536x864`. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above `2560x1440` are experimental, and the maximum supported resolution is `3840x2160`. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes `1024x1024`, `1536x1024`, and `1024x1536` are supported by the GPT image models; `auto` is supported for models that allow automatic sizing. For `dall-e-2`, use one of `256x256`, `512x512`, or `1024x1024`. For `dall-e-3`, use one of `1024x1024`, `1792x1024`, or `1024x1792`.129 The size of the generated images. For `gpt-image-2` and `gpt-image-2-2026-04-21`, arbitrary resolutions are supported as `WIDTHxHEIGHT` strings, for example `1536x864`. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above `2560x1440` are experimental, and the maximum supported resolution is `3840x2160`. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes `1024x1024`, `1536x1024`, and `1024x1536` are supported by the GPT image models; `auto` is supported for models that allow automatic sizing. For `dall-e-2`, use one of `256x256`, `512x512`, or `1024x1024`. For `dall-e-3`, use one of `1024x1024`, `1792x1024`, or `1024x1792`.

130 130

131 - `str`

132

133 - `Literal["auto", "1024x1024", "1536x1024", 5 more]`

134

135 The size of the generated images. For `gpt-image-2` and `gpt-image-2-2026-04-21`, arbitrary resolutions are supported as `WIDTHxHEIGHT` strings, for example `1536x864`. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above `2560x1440` are experimental, and the maximum supported resolution is `3840x2160`. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes `1024x1024`, `1536x1024`, and `1024x1536` are supported by the GPT image models; `auto` is supported for models that allow automatic sizing. For `dall-e-2`, use one of `256x256`, `512x512`, or `1024x1024`. For `dall-e-3`, use one of `1024x1024`, `1792x1024`, or `1024x1792`.

136

137 - `"auto"`

138

139 - `"1024x1024"`

140

141 - `"1536x1024"`

142

143 - `"1024x1536"`

144

145 - `"256x256"`

146

147 - `"512x512"`

148

149 - `"1792x1024"`

150

151 - `"1024x1792"`

152

131- `stream: Optional[Literal[false]]`153- `stream: Optional[Literal[false]]`

132 154

133 Generate the image in streaming mode. Defaults to `false`. See the155 Generate the image in streaming mode. Defaults to `false`. See the

510 532

511 - `"b64_json"`533 - `"b64_json"`

512 534

513- `size: Optional[str]`535- `size: Optional[Union[str, Literal["256x256", "512x512", "1024x1024", 3 more], null]]`

514 536

515 The size of the generated images. For `gpt-image-2` and `gpt-image-2-2026-04-21`, arbitrary resolutions are supported as `WIDTHxHEIGHT` strings, for example `1536x864`. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above `2560x1440` are experimental, and the maximum supported resolution is `3840x2160`. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes `1024x1024`, `1536x1024`, and `1024x1536` are supported by the GPT image models; `auto` is supported for models that allow automatic sizing. For `dall-e-2`, use one of `256x256`, `512x512`, or `1024x1024`. For `dall-e-3`, use one of `1024x1024`, `1792x1024`, or `1024x1792`.537 The size of the generated images. For `gpt-image-2` and `gpt-image-2-2026-04-21`, arbitrary resolutions are supported as `WIDTHxHEIGHT` strings, for example `1536x864`. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above `2560x1440` are experimental, and the maximum supported resolution is `3840x2160`. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes `1024x1024`, `1536x1024`, and `1024x1536` are supported by the GPT image models; `auto` is supported for models that allow automatic sizing. For `dall-e-2`, use one of `256x256`, `512x512`, or `1024x1024`. For `dall-e-3`, use one of `1024x1024`, `1792x1024`, or `1024x1792`.

516 538

539 - `str`

540

541 - `Literal["256x256", "512x512", "1024x1024", 3 more]`

542

543 The size of the generated images. For `gpt-image-2` and `gpt-image-2-2026-04-21`, arbitrary resolutions are supported as `WIDTHxHEIGHT` strings, for example `1536x864`. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above `2560x1440` are experimental, and the maximum supported resolution is `3840x2160`. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes `1024x1024`, `1536x1024`, and `1024x1536` are supported by the GPT image models; `auto` is supported for models that allow automatic sizing. For `dall-e-2`, use one of `256x256`, `512x512`, or `1024x1024`. For `dall-e-3`, use one of `1024x1024`, `1792x1024`, or `1024x1792`.

544

545 - `"256x256"`

546

547 - `"512x512"`

548

549 - `"1024x1024"`

550

551 - `"1536x1024"`

552

553 - `"1024x1536"`

554

555 - `"auto"`

556

517- `stream: Optional[Literal[false]]`557- `stream: Optional[Literal[false]]`

518 558

519 Edit the image in streaming mode. Defaults to `false`. See the559 Edit the image in streaming mode. Defaults to `false`. See the

python/resources/images/index.md 2026-05-05 23:00 UTC to 2026-05-07 21:57 UTC

Images

Create image

Parameters

Returns

Example

Response

Generate image

Response

Streaming

Response

Create image edit

Parameters

Returns

Example

Response

Edit image

Streaming

Response

Create image variation

Parameters

Returns

Example

Response

Example

Response

Domain Types

Image

Image Edit Completed Event

Image Edit Partial Image Event

Image Edit Stream Event

Image Gen Completed Event

Image Gen Partial Image Event

Image Gen Stream Event

Image Model

Images Response