Image Edit API

FastRouter’s Image Edit API lets you send an image and a natural-language instruction to generate an AI-edited version using the openai/gpt-image-1 model.

Image Edit API

Use FastRouter.ai to edit and transform images using the openai/gpt-image-1 model. Provide an input image along with a natural-language instruction, and FastRouter will generate an edited version of the image.

---

Endpoint

POST https://go.fastrouter.ai/api/v1/images/edits

Base URL

https://go.fastrouter.ai/api/v1

---

Required Parameters

Parameter	Type	Description
image	file or file[]	The image(s) to edit. Must be PNG, WEBP, or JPG and smaller than 50MB each. Supports up to 16 images.
prompt	string	Text description of the desired modification. Max length: 32,000 characters for gpt-image-1.
model	string	Must be "openai/gpt-image-1"

---

Optional Parameters

Parameter	Type	Default	Description
n	integer	1	Number of images to generate (1–10).
size	string	1024x1024	Output size: 1024x1024, 1536x1024, 1024x1536, or auto.
output_compression	integer	100	Compression (0–100) for JPEG or WEBP outputs.
output_format	string	png	Output format: png, jpeg, or webp.
mask	file	—	PNG mask file (< 4MB). Transparent areas indicate regions to edit. Must match dimensions of the first input image.
background	string	auto	Controls background transparency: transparent, opaque, or auto. If transparent, output format must be png or webp.

---

cURL Example

curl --location 'https://go.fastrouter.ai/api/v1/images/edits' \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer API_KEY' \
--form 'model="openai/gpt-image-1"' \
--form 'prompt="Change the color of the cycle to blue"' \
--form 'image[]=@"yellow-cycle.png"' \
--form 'size="1024x1024"'

---

Python Example (OpenAI SDK)

import openai
import base64
from openai import OpenAI

client = OpenAI(
    api_key="API_KEY",
    base_url="https://go.fastrouter.ai/api/v1"
)

prompt = """
Change the color of the cycle to blue
"""

result = client.images.edit(
    model="openai/gpt-image-1",
    image=[
        open("yellow-cycle.png", "rb")
    ],
    prompt=prompt
)

image_base64 = result.data[0].b64_json
image_bytes = base64.b64decode(image_base64)

# Save the output image
with open("blue.png", "wb") as f:
    f.write(image_bytes)

---

Image Edit via Chat Completions (Nano Banana)

FastRouter also supports image editing through the Chat Completions API using Google Gemini Nano Banana, accessible as google/gemini-2.5-flash-image.

Instead of calling the /images/edits endpoint, you send a chat completion request to /chat/completions with:

• model set to "google/gemini-2.5-flash-image"

• A messages array where the user message content contains:

  • An image_url block pointing to the input image. FastRouter supports both direct URLs and base64-encoded data for images.

  • A text block describing the desired edit in natural language

cURL Example (Nano Banana Chat Completion)

curl --location 'https://go.fastrouter.ai/api/v1/chat/completions' \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer API-KEY' \
--data '{
  "model": "google/gemini-2.5-flash-image",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "image_url",
          "image_url": {
            "url": "https://example.com/storage/yellow-cycle.jpg"
          }
        },
        {
          "type": "text",
          "text": "Change the picture of the bicycle to red"
        }
      ]
    }
  ]
}'

This call will return a response from Nano Banana where the model has applied the requested visual edit to the provided image via the Chat Completions API.