---
title: "Generate Image"
method: POST
path: "/v1/images/generations"
tags: ["router"]
---

# Generate Image

`POST /v1/images/generations`

## Request

- Base URL: `https://docs.sudoapp.dev` (the document declares no server; this is the origin it was published from)
- URL: `https://docs.sudoapp.dev/v1/images/generations`
- Auth: HTTP bearer

## Request body

- ImageGenerationRequest
  - `prompt` string, required: A text description of the desired image(s). The maximum length is 1000 characters for dall-e-2 and 4000 characters for dall-e-3.
  - `model` string, required: The model to use for image generation.
  - `n` integer, nullable: The number of images to generate. Must be between 1 and 10. For dall-e-3, only n=1 is supported.
  - `response_format` 'url' | 'b64_json', nullable: 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.
  - `quality` 'standard' | 'hd', nullable: The quality of the image that will be generated. hd creates images with finer details and greater consistency across the image. This param is only supported for dall-e-3.
  - `size` '256x256' | '512x512' | '1024x1024' | '1792x1024' | '1024x1792', nullable: The size of the generated images. Must be one of 256x256, 512x512, or 1024x1024 for dall-e-2. Must be one of 1024x1024, 1792x1024, or 1024x1792 for dall-e-3 models.
  - `style` 'vivid' | 'natural', nullable: The style of the generated images. 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. This param is only supported for dall-e-3.
  - `background` string, nullable: OpenAI only: Specify the background removal for the generated image.
  - `moderation` string, nullable: OpenAI only: Content moderation settings for the image generation.
  - `output_compression` integer, nullable: OpenAI only: Compression level for the output image, from 0 to 100.
  - `output_format` string, nullable: OpenAI only: The output format for the generated image.

## Response `200`

Image generated successfully

- ImageGeneration
  - `background` string, nullable: Background settings used in generation (OpenAI only)
  - `created` integer, nullable: The Unix timestamp (in seconds) of when the image was created.
  - `output_format` string, nullable: The output format of the generated image (OpenAI only)
  - `quality` string, nullable: The quality setting used for generation (OpenAI only)
  - `size` string, nullable: The size of the generated image (OpenAI only)
  - `usage` ImageUsage
    - `input_tokens` integer, required: Number of tokens in the input prompt.
    - `input_tokens_details` ImageInputTokens, required
      - `image_tokens` integer, required: Number of tokens used for image processing.
      - `text_tokens` integer, required: Number of tokens used for text processing.
    - `output_tokens` integer, required: Number of tokens used for the generated image.
    - `total_tokens` integer, required: Total number of tokens used in the request (input + output).
  - `data` ImageData[], required: The list of generated images.
    - `b64_json` string, nullable: The base64-encoded JSON of the generated image, if response_format is b64_json.
    - `revised_prompt` string, nullable: The prompt that was used to generate the image, if there was any revision to the prompt.
    - `url` string, nullable: The URL of the generated image, if response_format is url (default).

## Other responses

- `400`: Bad request
- `401`: Unauthorized
- `500`: Internal server error
- `502`: Bad gateway error

---

[API](https://skmtc.dev/sudoapp/apis/sudo-api.md) - [All operations](https://skmtc.dev/sudoapp/apis/sudo-api/llms.txt) - [OpenAPI document](https://skmtc.dev/sudoapp/apis/sudo-api/revisions/7d59684bf816?raw)