apicheats.dev openai/llms.txt Raw .md
POST

POST /images/variations — OpenAI API

Deprecated

OpenAI API key (required); https://api.openai.com/v1

OpenAI API

Create image variation

Base URL
https://api.openai.com/v1
Auth
Authorization: Bearer <OPENAI_API_KEY>
Last verified
2026-10-20 · upstream hash matched
Actions Try in browser→
Agents: curl -H "Accept: text/markdown" this URL
→ 333 tokens · Vary: Accept

Critical gotchas

The Responses API is the primary interface for new text and tool workflows; Chat Completions remains a separate compatibility API.

Audio transcription uploads use multipart form data rather than a JSON request body.

cURL

curl -X POST 'https://api.openai.com/v1/images/variations' \  -H "Authorization: Bearer $OPENAI_API_KEY" \  -F '[email protected]'

Parameters

Name In Type Required Description
image body string Yes The image to use as the basis for the variation(s). Must be a valid PNG file, less than 4MB, and square.
model body string No The legacy model used by the retired image variations endpoint. This endpoint no longer accepts requests.
n body integer No The number of images to generate. Must be between 1 and 10.
response_format body string No 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.
size body string No The size of the generated images. Must be one of `256x256`, `512x512`, or `1024x1024`.
user body string No A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](https://developers.openai.com/api/docs/guides/safety-best-practices#implement-safety-identifiers).

Response 200 OK

{
  "safety_identifier": "string",
  "created": 0,
  "data": [
    {
      "b64_json": "string",
      "url": "https://example.com",
      "revised_prompt": "string"
    }
  ],
  "background": "transparent",
  "output_format": "png",
  "size": "string",
  "quality": "low",
  "usage": {
    "input_tokens": 0,
    "total_tokens": 0,
    "output_tokens": 0,
    "output_tokens_details": {
      "image_tokens": 0,
      "text_tokens": 0
    },
    "input_tokens_details": {
      "text_tokens": 0,
      "image_tokens": 0
    }
  }
}
Get a free OpenAI API key → sponsored

Affiliate link - we may earn a commission, at no extra cost to you.