Sign in

v8

latestOpenAPI 3.0.0Apache 2.0raw.githubusercontent.com2025-10-165266542.4 MB
inference-proxy-api-new_ImagesGenerations

Creates an image given a prompt

Creates a high-quality image from a text prompt using GPT-IMAGE-1, the latest image generation model with automatic prompt optimization and enhanced visual capabilities.

post/images/generations

Request body

promptstring required

A text description of the desired image(s). GPT-IMAGE-1 supports up to 32,000 characters and provides automatic prompt optimization for best results.

modelstring

The model to use for image generation. GPT-IMAGE-1 is the latest model offering the best quality with automatic optimization and enhanced capabilities.

moderationstring nullable

The moderation setting for the image generation. GPT-IMAGE-1 supports: low, auto.

backgroundstring nullable

The background setting for the image generation. GPT-IMAGE-1 supports: transparent, opaque, auto.

output_formatstring nullable

The output format for the image generation. GPT-IMAGE-1 supports: png, webp, jpeg.

output_compressioninteger nullable

The output compression for the image generation. GPT-IMAGE-1 supports: 0-100.

ninteger nullable

The number of images to generate. GPT-IMAGE-1 only supports n=1.

qualitystring nullable

The quality of the image that will be generated. GPT-IMAGE-1 supports: auto (automatically select best quality), high, medium, low.

sizestring nullable

The size of the generated images. GPT-IMAGE-1 supports: auto (automatically select best size), 1536x1024 (landscape), 1024x1536 (portrait).

streamboolean nullable

If set to true, partial image data will be streamed as the image is being generated. When streaming, the response will be sent as server-sent events with partial image chunks. When stream is true, partial_images must be greater than 0.

partial_imagesinteger nullable

The number of partial image chunks to return during streaming generation. This parameter is optional with a default of 0. When stream=true, this must be greater than 0 to receive progressive updates of the image as it's being generated. Higher values provide more frequent updates but may increase response overhead.

userstring nullable

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

Example request

{
  "prompt": "A cute baby sea otter floating on its back in calm blue water",
  "model": "openai-gpt-image-1",
  "moderation": "auto",
  "background": "auto",
  "output_format": "png",
  "output_compression": 100,
  "n": 1,
  "quality": "auto",
  "size": "auto",
  "partial_images": 1,
  "user": "user-1234"
}

Response

OK

createdinteger required

The Unix timestamp (in seconds) of when the images were created

backgroundstring nullable

The background setting used for the image generation

output_formatstring nullable

The output format of the generated image

qualitystring nullable

The quality setting used for the image generation

sizestring nullable

The size of the generated image

Example response

{
  "created": 1677649456,
  "data": [
    {
      "b64_json": "iVBORw0KGgoAAAANSUhEUgAAAQAAAAEAAQMAAABmvDolAAAAA1BMVEX...",
      "revised_prompt": "A cute baby sea otter floating on its back in calm blue water, captured with professional photography lighting and composition"
    }
  ],
  "background": "opaque",
  "output_format": "png",
  "quality": "high",
  "size": "1024x1024",
  "usage": {
    "input_tokens": 12,
    "input_tokens_details": {
      "text_tokens": 12
    },
    "output_tokens": 4160,
    "total_tokens": 4172
  }
}