gpt-image-1

This documentation is valid for the following list of our models:

openai/gpt-image-1

Model Overview

A powerful multimodal model capable of generating new images, combining existing ones, and applying image masks — all guided by a text prompt.

Setup your API Key

If you don’t have an API key for the AI/ML API yet, feel free to use our Quickstart guide.

API Schemas

Note that by default, the quality parameter is set to 'medium'. The output image will still look great, but for even more detailed results, consider setting this parameter to 'high'.

Generate image

post

Body

modelstring · enumRequiredPossible values:

promptstring · max: 32000Required

The text prompt describing the content, style, or composition of the image to be generated.

sizestring · enumOptional

The size of the generated image.

Default: 1024x1024Possible values:

qualitystring · enumOptional

The quality of the image that will be generated.

Default: mediumPossible values:

output_formatstring · enumOptional

The format of the generated image.

Default: pngPossible values:

backgroundstring · enumOptional

Allows to set transparency for the background of the generated image(s). When auto is used, the model will automatically determine the best background for the image. If transparent, the output format needs to support transparency, so it should be set to either png (default value) or webp.

Default: autoPossible values:

moderationstring · enumOptional

Control the content-moderation level for images.

Default: autoPossible values:

nnumber · enumOptional

The number of images to generate.

Default: 1Possible values:

output_compressioninteger · max: 100Optional

Compression level (0-100%), applies to JPEG and WebP only.

Default: 100

response_formatstring · enumOptional

The format in which the generated images are returned.

Default: urlPossible values:

Responses

200Success

application/json

post

/v1/images/generations

curl -L \
  --request POST \
  --url 'https://api.aimlapi.com/v1/images/generations' \
  --header 'Authorization: Bearer <YOUR_AIMLAPI_KEY>' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "openai/gpt-image-1",
    "prompt": "A T-Rex relaxing on a beach, lying on a sun lounger and wearing sunglasses."
  }'

200Success

{
  "data": [
    {
      "url": "https://cdn.aimlapi.com/generations/hedgehog/1749730923700-29fe35d2-4aef-4bc5-a911-6c39884d16a8.png",
      "b64_json": null
    }
  ],
  "meta": {
    "usage": {
      "credits_used": 120000,
      "usd_spent": 0.06
    }
  }
}

Edit image

Unfortunately, this model only accepts local files specified by their file paths. It does not support image input via URLs or base64 encoding.

post

Body

modelstring · enumRequiredPossible values:

promptstring · max: 32000Required

The text prompt describing the content, style, or composition of the image to be generated.

imageany ofRequired

One or multiple images to edit. Each must be a local file (png, webp, or jpg), up to 50MB. Maximum 16 images.

objectOptional

object[] · max: 16Optional

sizestring · enumOptional

The size of the generated image.

Default: 1024x1024Possible values:

qualitystring · enumOptional

The quality of the image that will be generated.

Default: mediumPossible values:

output_formatstring · enumOptional

The format of the generated image.

Default: pngPossible values:

maskobjectOptional

A local PNG file used as a mask. Transparent areas define where the image will be edited. Must be under 4MB and match the image dimensions.

backgroundstring · enumOptional

Default: autoPossible values:

nnumber · min: 1 · max: 10Optional

The number of images to generate.

Default: 1

output_compressioninteger · max: 100Optional

Compression level (0-100%), applies to JPEG and WebP only.

Default: 100

response_formatstring · enumOptional

The format in which the generated images are returned.

Default: urlPossible values:

Responses

200Success

application/json

200Success

{
  "data": [
    {
      "url": "https://cdn.aimlapi.com/generations/hedgehog/1749730923700-29fe35d2-4aef-4bc5-a911-6c39884d16a8.png",
      "b64_json": null
    }
  ],
  "meta": {
    "usage": {
      "credits_used": 120000,
      "usd_spent": 0.06
    }
  }
}

Quick Examples

Generate image

Let's generate an image of the specified size using a simple prompt.

import requests
import json

def main():
    response = requests.post(
        "https://api.aimlapi.com/v1/images/generations",
        headers={
            # Insert your AIML API Key instead of <YOUR_AIMLAPI_KEY>:
            "Authorization": "Bearer <YOUR_AIMLAPI_KEY>",
            "Content-Type": "application/json",
        },
        json={
            "model": "openai/gpt-image-1",
            "prompt": "A T-Rex relaxing on a beach, lying on a sun lounger and wearing sunglasses. Realistic photo.",
            "size": "1024x1024"
        }
    )

    data = response.json()
    print(json.dumps(data, indent=2, ensure_ascii=False))

if __name__ == "__main__":
    main()

async function main() {
  const response = await fetch('https://api.aimlapi.com/v1/images/generations', {
    method: 'POST',
    headers: {
      // Insert your AIML API Key instead of <YOUR_AIMLAPI_KEY>:
      'Authorization': 'Bearer <YOUR_AIMLAPI_KEY>',
      'Content-Type': 'application/json',
    },
    body: JSON.stringify({
      model: 'openai/gpt-image-1',
      prompt: 'A T-Rex relaxing on a beach, lying on a sun lounger and wearing sunglasses. Realistic photo.',
      size: '1536x1024'
    }),
  });

  const data = await response.json();
  console.log(data);
}

main();

Response

{
  "created": 1749730922,
  "background": "opaque",
  "data": [
    {
      "url": "https://cdn.aimlapi.com/generations/hedgehog/1749730923700-29fe35d2-4aef-4bc5-a911-6c39884d16a8.png"
    }
  ],
  "output_format": "png",
  "quality": "medium",
  "size": "1536x1024",
  "usage": {
    "input_tokens": 29,
    "input_tokens_details": {
      "image_tokens": 0,
      "text_tokens": 29
    },
    "output_tokens": 1568,
    "total_tokens": 1597
  }
}

We obtained the following 1536x1024 image by running this code example (~ 26 s):

More images

Edit image: Combine images

Let's generate an image using two input images and a prompt that defines how they should be edited.

Our input images

from openai import OpenAI

def main():
    client = OpenAI(
        api_key="<YOUR_AIMLAPI_KEY>",
        base_url="https://api.aimlapi.com/v1",
    )

    result = client.images.edit(
        model="openai/gpt-image-1",
        image=[
            open("t-rex.png", "rb"),
            open("crown.png", "rb"),
        ],
        prompt="Put the crown on the T-rex's head"
    )

    print("Generation:", result)

if __name__ == "__main__":
    main()

import fs from 'fs';
import OpenAI, { toFile } from 'openai';

const main = async () => {
  const client = new OpenAI({
    baseURL: 'https://api.aimlapi.com/v1',
    apiKey: '<YOUR_API_KEY>',
  });

  const imageFiles = ['t-rex.png', 'crown.png'];

  const images = await Promise.all(
    imageFiles.map(
      async (file) =>
        await toFile(fs.createReadStream(file), null, {
          type: 'image/png',
        }),
    ),
  );

  const result = await client.images.edit({
    model: 'openai/gpt-image-1',
    image: images,
    prompt: "Put the crown on the T-rex's head",
  });

  console.log('Generation', result);
};

main();

Response

Generation: ImagesResponse(created=1750278299, data=[Image(b64_json=None, revised_prompt=None, url='https://cdn.aimlapi.com/generations/hedgehog/1750278300281-023df523-e986-431c-bb61-5b9e43301cef.png')], usage=Usage(input_tokens=574, input_tokens_details=UsageInputTokensDetails(image_tokens=517, text_tokens=57), output_tokens=1056, total_tokens=1630), background='opaque', output_format='png', quality='medium', size='1024x1024')

We obtained the following 1024x1024 image by running this code example (~ 34 s):

Edit image: Use an image mask

In this example, we’ll provide the model with our previously generated image of a T-rex on a beach, along with a same-sized mask where the area occupied by the dinosaur is transparent (alpha = 0). In the prompt, we’ll ask the model to remove the masked object from the image and see how well it handles the task.

Image & Mask

from openai import OpenAI

def main():
    client = OpenAI(
        api_key="<YOUR_AIMLAPI_KEY>",
        base_url="https://api.aimlapi.com/v1",
    )

    result = client.images.edit(
        model="openai/gpt-image-1",
        image=open("t-rex.png", "rb"),
        mask=open('t-rex-alpha_mask.png', 'rb'),
        prompt="Remove this from the picture"
    )
    print("Generation:", result)


if __name__ == "__main__":
    main()

import fs from 'fs';
import OpenAI, { toFile } from 'openai';

const main = async () => {
  const client = new OpenAI({
    baseURL: 'https://api.aimlapi.com/v1',
    apiKey: '<YOUR_AIMLAPI_KEY>',
  });

  const image = await toFile(
    fs.createReadStream('t-rex.png'),
    null,
    {
      type: 'image/png',
    },
  );
  
  const mask = await toFile(
    fs.createReadStream('t-rex-alpha_mask.png'),
    null,
    {
      type: 'image/png',
    },
  );

  const result = await client.images.edit({
    model: 'openai/gpt-image-1',
    image: image,
    mask: mask,
    prompt: 'Remove this from the picture',
  });

  console.log('Generation', result);
};

main();

Response

Generation: ImagesResponse(created=1750275775, data=[Image(b64_json=None, revised_prompt=None, url='https://cdn.aimlapi.com/generations/hedgehog/1750275776080-3fbcf9fc-b8ec-47f1-bb77-4a7e370a3a0c.png')], usage=Usage(input_tokens=360, input_tokens_details=UsageInputTokensDetails(image_tokens=323, text_tokens=37), output_tokens=1056, total_tokens=1416), background='opaque', output_format='png', quality='medium', size='1024x1024')

We obtained the following 1024x1024 image by running this code example (~ 32 s).

PreviousDALL·E 3 Nextgpt-image-1-mini

Last updated 27 days ago

Was this helpful?