Skip to content
API Reference
Images

Create image

client.images.generate(ImageGenerateParamsbody, RequestOptionsoptions?): ImagesResponse { created, background, data, 4 more } | Stream<ImageGenStreamEvent>
POST/images/generations

Creates an image given a prompt. Learn more.

ParametersExpand Collapse
ImageGenerateParams = ImageGenerateParamsNonStreaming { stream } | ImageGenerateParamsStreaming { stream }
ImageGenerateParamsBase { prompt, background, model, 11 more }
prompt: string

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?: "transparent" | "opaque" | "auto" | null

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.

Accepts one of the following:
"transparent"
"opaque"
"auto"
model?: (string & {}) | 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). Defaults to dall-e-2 unless a parameter specific to the GPT image models is used.

Accepts one of the following:
(string & {})
ImageModel = "gpt-image-1.5" | "dall-e-2" | "dall-e-3" | 2 more
Accepts one of the following:
"gpt-image-1.5"
"dall-e-2"
"dall-e-3"
"gpt-image-1"
"gpt-image-1-mini"
moderation?: "low" | "auto" | null

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).

Accepts one of the following:
"low"
"auto"
n?: number | null

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

minimum1
maximum10
output_compression?: number | null

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?: "png" | "jpeg" | "webp" | null

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.

Accepts one of the following:
"png"
"jpeg"
"webp"
partial_images?: number | null

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.

maximum3
minimum0
quality?: "standard" | "hd" | "low" | 3 more | null

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.
Accepts one of the following:
"standard"
"hd"
"low"
"medium"
"high"
"auto"
response_format?: "url" | "b64_json" | null

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.

Accepts one of the following:
"url"
"b64_json"
size?: "auto" | "1024x1024" | "1536x1024" | 5 more | null

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.

Accepts one of the following:
"auto"
"1024x1024"
"1536x1024"
"1024x1536"
"256x256"
"512x512"
"1792x1024"
"1024x1792"
stream?: false | null

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?: "vivid" | "natural" | null

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.

Accepts one of the following:
"vivid"
"natural"
user?: string

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

ImageGenerateParamsNonStreaming extends ImageGenerateParamsBase { prompt, background, model, 11 more } { stream }
stream?: false | null

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.

ImageGenerateParamsNonStreaming extends ImageGenerateParamsBase { prompt, background, model, 11 more } { stream }
stream?: false | null

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.

ReturnsExpand Collapse
ImagesResponse { 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.

background?: "transparent" | "opaque"

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

Accepts one of the following:
"transparent"
"opaque"
data?: Array<Image { b64_json, revised_prompt, url } >

The list of generated images.

b64_json?: 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?: string

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

url?: 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.

output_format?: "png" | "webp" | "jpeg"

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

Accepts one of the following:
"png"
"webp"
"jpeg"
quality?: "low" | "medium" | "high"

The quality of the image generated. Either low, medium, or high.

Accepts one of the following:
"low"
"medium"
"high"
size?: "1024x1024" | "1024x1536" | "1536x1024"

The size of the image generated. Either 1024x1024, 1024x1536, or 1536x1024.

Accepts one of the following:
"1024x1024"
"1024x1536"
"1536x1024"
usage?: Usage { 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: InputTokensDetails { 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?: OutputTokensDetails { 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.

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

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

Accepts one of the following:
ImageGenPartialImageEvent { 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" | "opaque" | "auto"

The background setting for the requested image.

Accepts one of the following:
"transparent"
"opaque"
"auto"
created_at: number

The Unix timestamp when the event was created.

output_format: "png" | "webp" | "jpeg"

The output format for the requested image.

Accepts one of the following:
"png"
"webp"
"jpeg"
partial_image_index: number

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

quality: "low" | "medium" | "high" | "auto"

The quality setting for the requested image.

Accepts one of the following:
"low"
"medium"
"high"
"auto"
size: "1024x1024" | "1024x1536" | "1536x1024" | "auto"

The size of the requested image.

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

The type of the event. Always image_generation.partial_image.

ImageGenCompletedEvent { 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" | "opaque" | "auto"

The background setting for the generated image.

Accepts one of the following:
"transparent"
"opaque"
"auto"
created_at: number

The Unix timestamp when the event was created.

output_format: "png" | "webp" | "jpeg"

The output format for the generated image.

Accepts one of the following:
"png"
"webp"
"jpeg"
quality: "low" | "medium" | "high" | "auto"

The quality setting for the generated image.

Accepts one of the following:
"low"
"medium"
"high"
"auto"
size: "1024x1024" | "1024x1536" | "1536x1024" | "auto"

The size of the generated image.

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

The type of the event. Always image_generation.completed.

usage: Usage { 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: InputTokensDetails { 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.

Create image

import OpenAI from "openai";
import { writeFile } from "fs/promises";

const client = new OpenAI();

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

const imageBuffer = Buffer.from(img.data[0].b64_json, "base64");
await writeFile("output.png", imageBuffer);

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

Create image

import OpenAI from "openai";

const client = new OpenAI();

const stream = await client.images.generate({
  model: "gpt-image-1.5",
  prompt: "A cute baby sea otter",
  n: 1,
  size: "1024x1024",
  stream: true,
});

for await (const event of stream) {
  console.log(event);
}

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}}}
Returns Examples
{
  "created": 0,
  "background": "transparent",
  "data": [
    {
      "b64_json": "b64_json",
      "revised_prompt": "revised_prompt",
      "url": "url"
    }
  ],
  "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
    }
  }
}