Edit image

Edits an existing image from a prompt, optionally with an inpainting mask. Compatible with the OpenAI /v1/images/edits API — send multipart/form-data (not JSON).

Only image models flagged edit-capable work here: call /v2/models/all and use a model whose supports_edits is true. Each such model also reports an edit block with supports_mask and max_input_images. A mask is accepted only by models whose edit.supports_mask is true (OpenAI GPT-Image, FLUX inpaint/fill, Ideogram); natural-language and multi-reference edit models (Gemini Flash Image, FLUX.2, Seedream, Nano Banana) reject a mask with 400. Images are returned as base64-encoded data (b64_json).

Provider-specific knobs (e.g. OpenAI input_fidelity/background, fal strength/guidance_scale) can be sent in the parameters JSON field; OpenAI background, input_fidelity and output_format may also be sent as their own form fields.

curl https://api.deutschlandgpt.de/v2/images/edits \
  -X POST \
  -H "Authorization: Bearer $DGPT_API_KEY"

curl https://api.deutschlandgpt.de/v2/images/edits \
  -X POST \
  -H "Authorization: Bearer $DGPT_API_KEY"

import os, requests

response = requests.post(
    "https://api.deutschlandgpt.de/v2/images/edits",
    headers={"Authorization": f"Bearer {os.environ['DGPT_API_KEY']}"},
)

print(response.json())

import os, requests

response = requests.post(
    "https://api.deutschlandgpt.de/v2/images/edits",
    headers={"Authorization": f"Bearer {os.environ['DGPT_API_KEY']}"},
)

print(response.json())

const response = await fetch('https://api.deutschlandgpt.de/v2/images/edits', {
  method: 'POST',
  headers: {
    Authorization: `Bearer ${process.env.DGPT_API_KEY}`,
  },
});

console.log(await response.json());

const response = await fetch('https://api.deutschlandgpt.de/v2/images/edits', {
  method: 'POST',
  headers: {
    Authorization: `Bearer ${process.env.DGPT_API_KEY}`,
  },
});

console.log(await response.json());

{
  "created": 0,
  "data": [
    {
      "b64_json": "string",
      "revised_prompt": "string"
    }
  ],
  "usage": {
    "imageCount": 0,
    "quality": "string",
    "dimension": "string",
    "costInEuro": 0
  }
}

{
  "created": 0,
  "data": [
    {
      "b64_json": "string",
      "revised_prompt": "string"
    }
  ],
  "usage": {
    "imageCount": 0,
    "quality": "string",
    "dimension": "string",
    "costInEuro": 0
  }
}