---
title: "Creates an image given a prompt"
method: POST
path: "/images/generations"
tags: ["inference-proxy-api-new_ImagesGenerations"]
---

# Creates an image given a prompt

`POST /images/generations`

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.

## Request body

- CreateImageRequest
  - `prompt` string, 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.
  - `model` string — The model to use for image generation. GPT-IMAGE-1 is the latest model offering the best quality with automatic optimization and enhanced capabilities.
  - `moderation` string, nullable — The moderation setting for the image generation. GPT-IMAGE-1 supports: low, auto.
  - `background` string, nullable — The background setting for the image generation. GPT-IMAGE-1 supports: transparent, opaque, auto.
  - `output_format` string, nullable — The output format for the image generation. GPT-IMAGE-1 supports: png, webp, jpeg.
  - `output_compression` integer, nullable — The output compression for the image generation. GPT-IMAGE-1 supports: 0-100.
  - `n` integer, nullable — The number of images to generate. GPT-IMAGE-1 only supports n=1.
  - `quality` string, nullable — The quality of the image that will be generated. GPT-IMAGE-1 supports: auto (automatically select best quality), high, medium, low.
  - `size` string, nullable — The size of the generated images. GPT-IMAGE-1 supports: auto (automatically select best size), 1536x1024 (landscape), 1024x1536 (portrait).
  - `stream` boolean, 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_images` integer, 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.
  - `user` string, nullable — A unique identifier representing your end-user, which can help DigitalOcean to monitor and detect abuse.

## Response `200`

OK

- ImagesResponse — The response from the image generation endpoint
  - `created` integer, required — The Unix timestamp (in seconds) of when the images were created
  - `data` GeneratedImage[], required — The list of generated images
    - `b64_json` string, required — The base64-encoded JSON of the generated image. GPT-IMAGE-1 returns images in b64_json format only.
    - `revised_prompt` string — The optimized prompt that was used to generate the image. GPT-IMAGE-1 automatically optimizes prompts for best results.
  - `background` string, nullable — The background setting used for the image generation
  - `output_format` string, nullable — The output format of the generated image
  - `quality` string, nullable — The quality setting used for the image generation
  - `size` string, nullable — The size of the generated image
  - `usage` object, nullable — Usage statistics for the image generation request
    - `input_tokens` integer, required — Number of tokens in the input prompt
    - `input_tokens_details` object, nullable — Detailed breakdown of input tokens
      - `text_tokens` integer — Number of text tokens in the input
    - `output_tokens` integer — Number of tokens in the generated output
    - `total_tokens` integer, required — Total number of tokens used (input + output)

---

[API](https://skmtc.net/digitalocean/apis/digitalocean-api.md) · [All operations](https://skmtc.net/digitalocean/apis/digitalocean-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/digitalocean/digitalocean-api/revisions/cb3bf9b21459/schema)