/images/edits

Edit images using AI models. Supports both single and multiple image editing.

Feature	Supported	Notes
Cost Tracking	✅	Works with all supported models
Logging	✅	Works across all integrations
Fallbacks	✅	Works between supported models
Loadbalancing	✅	Works between supported models
Supported Providers	OpenAI, Gemini (Google AI Studio), Vertex AI, Stability AI, AWS Bedrock (Stability)

Quick Start

Python

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.haimaker.ai/v1"
)

response = client.images.edit(
    model="openai/gpt-image-1",
    image=open("original_image.png", "rb"),
    prompt="Add a red hat to the person in the image",
    n=1,
    size="1024x1024"
)

print(response.data[0].url)

cURL

curl https://api.haimaker.ai/v1/images/edits \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F "model=openai/gpt-image-1" \
  -F "image=@original_image.png" \
  -F "prompt=Add a beautiful sunset in the background" \
  -F "n=1" \
  -F "size=1024x1024"

Image Edit with Mask

Use a mask to specify which areas of the image should be edited:

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.haimaker.ai/v1"
)

response = client.images.edit(
    model="openai/gpt-image-1",
    image=open("original_image.png", "rb"),
    mask=open("mask_image.png", "rb"),  # Transparent areas will be edited
    prompt="Replace the background with a beach scene",
    n=1,
    size="1024x1024"
)

print(response.data[0].url)

Using Different Models

OpenAI GPT-Image-1

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.haimaker.ai/v1"
)

response = client.images.edit(
    model="openai/gpt-image-1",
    image=open("portrait.png", "rb"),
    prompt="Add sunglasses and a smile",
    n=1,
    size="1024x1024"
)

print(response.data[0].url)

Gemini

import base64
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.haimaker.ai/v1"
)

response = client.images.edit(
    model="gemini/gemini-2.5-flash-image",
    image=open("original_image.png", "rb"),
    prompt="Add aurora borealis to the night sky",
    size="1792x1024"
)

# Gemini returns base64-encoded images
edited_image_bytes = base64.b64decode(response.data[0].b64_json)
with open("edited_image.png", "wb") as f:
    f.write(edited_image_bytes)

Vertex AI

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.haimaker.ai/v1"
)

response = client.images.edit(
    model="vertex_ai/imagen-3.0-capability-001",
    image=open("original_image.png", "rb"),
    mask=open("mask_image.png", "rb"),
    prompt="Turn this into watercolor style scenery",
    n=2,
    size="1024x1024"
)

for i, image_data in enumerate(response.data):
    print(f"Image {i+1}: {image_data.url}")

Input Parameters

Parameter	Type	Description	Required
image	file	The image to edit. Must be a valid PNG file, less than 4MB, and square.	Yes
prompt	string	A text description of the desired image edit.	Yes
model	string	The model to use for image editing.	No (defaults to dall-e-2)
mask	file	An additional image whose fully transparent areas indicate where the original image should be edited.	No
n	integer	The number of images to generate. Must be between 1 and 10.	No (defaults to 1)
size	string	The size of the generated images.	No (defaults to 1024x1024)
response_format	string	The format in which images are returned (url or b64_json).	No (defaults to url)
user	string	A unique identifier representing your end-user.	No

Response Format

{
    "created": 1677649800,
    "data": [
        {
            "url": "https://example.com/edited_image_1.png"
        }
    ]
}

For b64_json format:

{
    "created": 1677649800,
    "data": [
        {
            "b64_json": "iVBORw0KGgoAAAANSUhEUgAA..."
        }
    ]
}