Skip to main content
This API endpoint allows you to edit images using AI models. You can provide one or more base64-encoded images along with a text prompt describing the desired edit.
The Image Edits API supports both single and multiple image editing, with optional mask support for targeted edits.
Images stored via URL are only available for 1 hour after generation. Make sure to download and save important images locally.

​
Create Image Edit

To edit an image, use the following endpoint: POST /v1/images/edits

​
Request Body

​
images
array of string
required
Base64-encoded images (PNG format, < 4MB each)
​
mask
string
Base64-encoded mask image (PNG format, < 4MB) for targeted edits
​
prompt
string
required
Text description of the desired edit
​
model
string
Model to use for image editing
​
n
integer
Number of images to generate (1-10, default: 1)
​
size
string
Image size (options: “256x256”, “512x512”, “1024x1024”)
​
response_format
string
Response format (options: “url” or “b64_json”, default: “url”)
​
strength
number
Transformation strength (0.0-1.0)
​
guidance_scale
number
Guidance scale for the edit (0.0-20.0)
​
num_inference_steps
integer
Number of inference steps (1-100)
​
seed
integer
Random seed for reproducible results
​
kontext_max_mode
string
Kontext max mode configuration
import os
import base64
from openai import OpenAI

client = OpenAI(
    base_url="https://api.routeway.ai/v1",
    api_key=os.getenv("Routeway_API_KEY")
)

# Read and encode image
with open("input.png", "rb") as image_file:
    encoded_image = base64.b64encode(image_file.read()).decode('utf-8')

response = client.images.edit(
    images=[encoded_image],
    prompt="Add a sunset in the background",
    size="1024x1024",
    n=1
)

print(response.data[0].url)

​
Response

The response includes the edited image(s) with either a URL or base64-encoded data, depending on the response_format parameter. 
{
  "created": 1234567890,
  "data": [
    {
      "url": "https://example.com/image.png",
      "revised_prompt": "Add a sunset in the background"
    }
  ]
}
When response_format is set to b64_json, the response will include base64-encoded image data instead of a URL: 
{
  "created": 1234567890,
  "data": [
    {
      "b64_json": "iVBORw0KGgoAAAANSUhEUgAA...",
      "revised_prompt": "Add a sunset in the background"
    }
  ]
}

​
Error Response

{
  "error": {
    "message": "Invalid image format",
    "type": "invalid_request_error",
    "code": 400
  }
}