Skip to content
For the complete documentation index, see llms.txt. Markdown versions of documentation pages are available by appending .md to the page URL.
Primary navigation

Suggested
Overview Models Agents Tools Audio & voice Production API reference
API Reference

Images

Given a prompt and/or an input image, the model will generate a new image.

Create image variation
POST/images/variations
Create image edit
POST/images/edits
Create image
POST/images/generations
ModelsExpand Collapse
Image object { b64_json, revised_prompt, url }

Represents the content or the URL of an image generated by the OpenAI API.

b64_json: optional string

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 string

For dall-e-3 only, the revised prompt that was used to generate the image.

url: optional string

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.

formaturi
ImageEditCompletedEvent object { b64_json, background, created_at, 5 more }

Emitted when image editing has completed and the final image is available.

b64_json: string

Base64-encoded final edited image data, suitable for rendering as an image.

background: "transparent" or "opaque" or "auto"

The background setting for the edited image.

One of the following:
"transparent"
"opaque"
"auto"
created_at: number

The Unix timestamp when the event was created.

formatunixtime
output_format: "png" or "webp" or "jpeg"

The output format for the edited image.

One of the following:
"png"
"webp"
"jpeg"
quality: "low" or "medium" or "high" or 3 more

The quality setting for the edited image.

One of the following:
"low"
"medium"
"high"
"xhigh"
"max"
"auto"
size: string or "1024x1024" or "1024x1536" or "1536x1024" or "auto"

The image dimensions as a WIDTHxHEIGHT string, for example 1536x864.

One of the following:
string
"1024x1024" or "1024x1536" or "1536x1024" or "auto"

The image dimensions as a WIDTHxHEIGHT string, for example 1536x864.

One of the following:
"1024x1024"
"1024x1536"
"1536x1024"
"auto"
type: "image_edit.completed"

The type of the event. Always image_edit.completed.

usage: object { input_tokens, input_tokens_details, output_tokens, total_tokens }

For the GPT image models only, the token usage information for the image generation.

input_tokens: number

The number of tokens (images and text) in the input prompt.

input_tokens_details: object { image_tokens, text_tokens }

The input tokens detailed information for the image generation.

image_tokens: number

The number of image tokens in the input prompt.

text_tokens: number

The number of text tokens in the input prompt.

output_tokens: number

The number of image tokens in the output image.

total_tokens: number

The total number of tokens (images and text) used for the image generation.

ImageEditPartialImageEvent object { b64_json, background, created_at, 5 more }

Emitted when a partial image is available during image editing streaming.

b64_json: string

Base64-encoded partial image data, suitable for rendering as an image.

background: "transparent" or "opaque" or "auto"

The background setting for the requested edited image.

One of the following:
"transparent"
"opaque"
"auto"
created_at: number

The Unix timestamp when the event was created.

formatunixtime
output_format: "png" or "webp" or "jpeg"

The output format for the requested edited image.

One of the following:
"png"
"webp"
"jpeg"
partial_image_index: number

0-based index for the partial image (streaming).

quality: "low" or "medium" or "high" or 3 more

The quality setting for the requested edited image.

One of the following:
"low"
"medium"
"high"
"xhigh"
"max"
"auto"
size: string or "1024x1024" or "1024x1536" or "1536x1024" or "auto"

The image dimensions as a WIDTHxHEIGHT string, for example 1536x864.

One of the following:
string
"1024x1024" or "1024x1536" or "1536x1024" or "auto"

The image dimensions as a WIDTHxHEIGHT string, for example 1536x864.

One of the following:
"1024x1024"
"1024x1536"
"1536x1024"
"auto"
type: "image_edit.partial_image"

The type of the event. Always image_edit.partial_image.

ImageEditStreamEvent = ImageEditPartialImageEvent { b64_json, background, created_at, 5 more } or ImageEditCompletedEvent { b64_json, background, created_at, 5 more }

Emitted when a partial image is available during image editing streaming.

One of the following:
ImageEditPartialImageEvent object { b64_json, background, created_at, 5 more }

Emitted when a partial image is available during image editing streaming.

b64_json: string

Base64-encoded partial image data, suitable for rendering as an image.

background: "transparent" or "opaque" or "auto"

The background setting for the requested edited image.

One of the following:
"transparent"
"opaque"
"auto"
created_at: number

The Unix timestamp when the event was created.

formatunixtime
output_format: "png" or "webp" or "jpeg"

The output format for the requested edited image.

One of the following:
"png"
"webp"
"jpeg"
partial_image_index: number

0-based index for the partial image (streaming).

quality: "low" or "medium" or "high" or 3 more

The quality setting for the requested edited image.

One of the following:
"low"
"medium"
"high"
"xhigh"
"max"
"auto"
size: string or "1024x1024" or "1024x1536" or "1536x1024" or "auto"

The image dimensions as a WIDTHxHEIGHT string, for example 1536x864.

One of the following:
string
"1024x1024" or "1024x1536" or "1536x1024" or "auto"

The image dimensions as a WIDTHxHEIGHT string, for example 1536x864.

One of the following:
"1024x1024"
"1024x1536"
"1536x1024"
"auto"
type: "image_edit.partial_image"

The type of the event. Always image_edit.partial_image.

ImageEditCompletedEvent object { b64_json, background, created_at, 5 more }

Emitted when image editing has completed and the final image is available.

b64_json: string

Base64-encoded final edited image data, suitable for rendering as an image.

background: "transparent" or "opaque" or "auto"

The background setting for the edited image.

One of the following:
"transparent"
"opaque"
"auto"
created_at: number

The Unix timestamp when the event was created.

formatunixtime
output_format: "png" or "webp" or "jpeg"

The output format for the edited image.

One of the following:
"png"
"webp"
"jpeg"
quality: "low" or "medium" or "high" or 3 more

The quality setting for the edited image.

One of the following:
"low"
"medium"
"high"
"xhigh"
"max"
"auto"
size: string or "1024x1024" or "1024x1536" or "1536x1024" or "auto"

The image dimensions as a WIDTHxHEIGHT string, for example 1536x864.

One of the following:
string
"1024x1024" or "1024x1536" or "1536x1024" or "auto"

The image dimensions as a WIDTHxHEIGHT string, for example 1536x864.

One of the following:
"1024x1024"
"1024x1536"
"1536x1024"
"auto"
type: "image_edit.completed"

The type of the event. Always image_edit.completed.

usage: object { input_tokens, input_tokens_details, output_tokens, total_tokens }

For the GPT image models only, the token usage information for the image generation.

input_tokens: number

The number of tokens (images and text) in the input prompt.

input_tokens_details: object { image_tokens, text_tokens }

The input tokens detailed information for the image generation.

image_tokens: number

The number of image tokens in the input prompt.

text_tokens: number

The number of text tokens in the input prompt.

output_tokens: number

The number of image tokens in the output image.

total_tokens: number

The total number of tokens (images and text) used for the image generation.

ImageGenCompletedEvent object { b64_json, background, created_at, 5 more }

Emitted when image generation has completed and the final image is available.

b64_json: string

Base64-encoded image data, suitable for rendering as an image.

background: "transparent" or "opaque" or "auto"

The background setting for the generated image.

One of the following:
"transparent"
"opaque"
"auto"
created_at: number

The Unix timestamp when the event was created.

formatunixtime
output_format: "png" or "webp" or "jpeg"

The output format for the generated image.

One of the following:
"png"
"webp"
"jpeg"
quality: "low" or "medium" or "high" or 3 more

The quality setting for the generated image.

One of the following:
"low"
"medium"
"high"
"xhigh"
"max"
"auto"
size: string or "1024x1024" or "1024x1536" or "1536x1024" or "auto"

The image dimensions as a WIDTHxHEIGHT string, for example 1536x864.

One of the following:
string
"1024x1024" or "1024x1536" or "1536x1024" or "auto"

The image dimensions as a WIDTHxHEIGHT string, for example 1536x864.

One of the following:
"1024x1024"
"1024x1536"
"1536x1024"
"auto"
type: "image_generation.completed"

The type of the event. Always image_generation.completed.

usage: object { input_tokens, input_tokens_details, output_tokens, total_tokens }

For the GPT image models only, the token usage information for the image generation.

input_tokens: number

The number of tokens (images and text) in the input prompt.

input_tokens_details: object { image_tokens, text_tokens }

The input tokens detailed information for the image generation.

image_tokens: number

The number of image tokens in the input prompt.

text_tokens: number

The number of text tokens in the input prompt.

output_tokens: number

The number of image tokens in the output image.

total_tokens: number

The total number of tokens (images and text) used for the image generation.

ImageGenPartialImageEvent object { b64_json, background, created_at, 5 more }

Emitted when a partial image is available during image generation streaming.

b64_json: string

Base64-encoded partial image data, suitable for rendering as an image.

background: "transparent" or "opaque" or "auto"

The background setting for the requested image.

One of the following:
"transparent"
"opaque"
"auto"
created_at: number

The Unix timestamp when the event was created.

formatunixtime
output_format: "png" or "webp" or "jpeg"

The output format for the requested image.

One of the following:
"png"
"webp"
"jpeg"
partial_image_index: number

0-based index for the partial image (streaming).

quality: "low" or "medium" or "high" or 3 more

The quality setting for the requested image.

One of the following:
"low"
"medium"
"high"
"xhigh"
"max"
"auto"
size: string or "1024x1024" or "1024x1536" or "1536x1024" or "auto"

The image dimensions as a WIDTHxHEIGHT string, for example 1536x864.

One of the following:
string
"1024x1024" or "1024x1536" or "1536x1024" or "auto"

The image dimensions as a WIDTHxHEIGHT string, for example 1536x864.

One of the following:
"1024x1024"
"1024x1536"
"1536x1024"
"auto"
type: "image_generation.partial_image"

The type of the event. Always image_generation.partial_image.

ImageGenStreamEvent = ImageGenPartialImageEvent { b64_json, background, created_at, 5 more } or ImageGenCompletedEvent { b64_json, background, created_at, 5 more }

Emitted when a partial image is available during image generation streaming.

One of the following:
ImageGenPartialImageEvent object { b64_json, background, created_at, 5 more }

Emitted when a partial image is available during image generation streaming.

b64_json: string

Base64-encoded partial image data, suitable for rendering as an image.

background: "transparent" or "opaque" or "auto"

The background setting for the requested image.

One of the following:
"transparent"
"opaque"
"auto"
created_at: number

The Unix timestamp when the event was created.

formatunixtime
output_format: "png" or "webp" or "jpeg"

The output format for the requested image.

One of the following:
"png"
"webp"
"jpeg"
partial_image_index: number

0-based index for the partial image (streaming).

quality: "low" or "medium" or "high" or 3 more

The quality setting for the requested image.

One of the following:
"low"
"medium"
"high"
"xhigh"
"max"
"auto"
size: string or "1024x1024" or "1024x1536" or "1536x1024" or "auto"

The image dimensions as a WIDTHxHEIGHT string, for example 1536x864.

One of the following:
string
"1024x1024" or "1024x1536" or "1536x1024" or "auto"

The image dimensions as a WIDTHxHEIGHT string, for example 1536x864.

One of the following:
"1024x1024"
"1024x1536"
"1536x1024"
"auto"
type: "image_generation.partial_image"

The type of the event. Always image_generation.partial_image.

ImageGenCompletedEvent object { b64_json, background, created_at, 5 more }

Emitted when image generation has completed and the final image is available.

b64_json: string

Base64-encoded image data, suitable for rendering as an image.

background: "transparent" or "opaque" or "auto"

The background setting for the generated image.

One of the following:
"transparent"
"opaque"
"auto"
created_at: number

The Unix timestamp when the event was created.

formatunixtime
output_format: "png" or "webp" or "jpeg"

The output format for the generated image.

One of the following:
"png"
"webp"
"jpeg"
quality: "low" or "medium" or "high" or 3 more

The quality setting for the generated image.

One of the following:
"low"
"medium"
"high"
"xhigh"
"max"
"auto"
size: string or "1024x1024" or "1024x1536" or "1536x1024" or "auto"

The image dimensions as a WIDTHxHEIGHT string, for example 1536x864.

One of the following:
string
"1024x1024" or "1024x1536" or "1536x1024" or "auto"

The image dimensions as a WIDTHxHEIGHT string, for example 1536x864.

One of the following:
"1024x1024"
"1024x1536"
"1536x1024"
"auto"
type: "image_generation.completed"

The type of the event. Always image_generation.completed.

usage: object { input_tokens, input_tokens_details, output_tokens, total_tokens }

For the GPT image models only, the token usage information for the image generation.

input_tokens: number

The number of tokens (images and text) in the input prompt.

input_tokens_details: object { image_tokens, text_tokens }

The input tokens detailed information for the image generation.

image_tokens: number

The number of image tokens in the input prompt.

text_tokens: number

The number of text tokens in the input prompt.

output_tokens: number

The number of image tokens in the output image.

total_tokens: number

The total number of tokens (images and text) used for the image generation.

ImageModel = "gpt-image-1.5" or "gpt-image-2" or "gpt-image-2-2026-04-21" or 8 more
One of the following:
"gpt-image-1.5"
"gpt-image-2"
"gpt-image-2-2026-04-21"
"gpt-image-2.5-sunburst"
"gpt-image-2.5-sunburst-2026-09-08"
"gpt-image-2.5-flare"
"gpt-image-2.5-flare-2026-09-08"
"dall-e-2"
"dall-e-3"
"gpt-image-1"
"gpt-image-1-mini"
ImagesResponse object { created, background, data, 4 more }

The response from the image generation endpoint.

created: number

The Unix timestamp (in seconds) of when the image was created.

formatunixtime
background: optional "transparent" or "opaque"

The background parameter used for the image generation. Either transparent or opaque.

One of the following:
"transparent"
"opaque"
data: optional array of Image { b64_json, revised_prompt, url }

The list of generated images.

b64_json: optional string

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 string

For dall-e-3 only, the revised prompt that was used to generate the image.

url: optional string

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.

formaturi
output_format: optional "png" or "webp" or "jpeg"

The output format of the image generation. Either png, webp, or jpeg.

One of the following:
"png"
"webp"
"jpeg"
quality: optional "low" or "medium" or "high" or 2 more

The quality of the image generated. One of low, medium, high, xhigh, or max.

One of the following:
"low"
"medium"
"high"
"xhigh"
"max"
size: optional string or "1024x1024" or "1024x1536" or "1536x1024"

The image dimensions as a WIDTHxHEIGHT string, for example 1536x864.

One of the following:
string
"1024x1024" or "1024x1536" or "1536x1024"

The image dimensions as a WIDTHxHEIGHT string, for example 1536x864.

One of the following:
"1024x1024"
"1024x1536"
"1536x1024"
usage: optional object { input_tokens, input_tokens_details, output_tokens, 2 more }

For gpt-image-1 only, the token usage information for the image generation.

input_tokens: number

The number of tokens (images and text) in the input prompt.

input_tokens_details: object { image_tokens, text_tokens }

The input tokens detailed information for the image generation.

image_tokens: number

The number of image tokens in the input prompt.

text_tokens: number

The number of text tokens in the input prompt.

output_tokens: number

The number of output tokens generated by the model.

total_tokens: number

The total number of tokens (images and text) used for the image generation.

output_tokens_details: optional object { image_tokens, text_tokens }

The output token details for the image generation.

image_tokens: number

The number of image output tokens generated by the model.

text_tokens: number

The number of text output tokens generated by the model.