AI Image Editor API

A production AI Image Editor API that applies a natural-language instruction to a photo and returns the edited frame. JSON in, image out. $0.03 per image (30 credits). 5,000 free credits (24-hour trial), no credit card.

Quick start — AI Image Editor API

This is the instruction-based image editor: you describe the change in a sentence, not with a brush. The route is POST /v1/image/edit with JSON. Image may be a public URL or a base64 data URI.

curl -X POST https://api.pixelapi.dev/v1/image/edit \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"image":"https://example.com/portrait.jpg","prompt":"make the background a sunset beach scene"}'

curl https://api.pixelapi.dev/v1/image/GENERATION_ID \
  -H "Authorization: Bearer YOUR_API_KEY"

import requests
r = requests.post(
    "https://api.pixelapi.dev/v1/image/edit",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    json={
        "image": "https://example.com/portrait.jpg",
        "prompt": "make the background a sunset beach scene",
    },
)
job = r.json()

const res = await fetch("https://api.pixelapi.dev/v1/image/edit", {
  method: "POST",
  headers: {
    Authorization: "Bearer " + process.env.PIXELAPI_KEY,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    image: "https://example.com/portrait.jpg",
    prompt: "make the background a sunset beach scene",
  }),
});
const job = await res.json();

require "net/http"
require "json"
uri = URI("https://api.pixelapi.dev/v1/image/edit")
req = Net::HTTP::Post.new(uri)
req["Authorization"] = "Bearer YOUR_API_KEY"
req["Content-Type"] = "application/json"
req.body = {image: "https://example.com/portrait.jpg",
            prompt: "make the background a sunset beach scene"}.to_json
job = JSON.parse(Net::HTTP.start(uri.host, uri.port, use_ssl: true){|h| h.request(req)}.body)

What the AI Image Editor API is for

Most “edit this photo” products still mean sliders and layers. This endpoint is a developer Image Editor API: a REST call that applies a natural-language instruction while keeping the person or product recognizable. Typical prompts: “change the hair color to blonde”, “add dramatic studio lighting”, “make the person wear a red dress”, “restore the old photo to high quality”, “make the background a sunset beach scene”.

Use dedicated tools when the job is mechanical. Transparent cutouts go to the Background Removal API. Erasing a person or a cable goes to the Remove Object API. Date stamps and watermarks go to the Remove Text API. Print resolution goes to the Upscale API. The editor is for semantic change — lighting, wardrobe, setting, color — not for punching a hole in a layer.

Pricing comparison

Live charge is $0.03 per image (30 credits) from /v1/pricing/live. That is the instruction-based editor meter, not the cheaper erase/upscale meters.

5,000 free credits (24-hour trial), no card. After that, prepaid credits. Do not hard-code a price in your app — read /v1/pricing/live so a rate change cannot silently under-charge or over-charge a customer.

Production notes

• Content-Type must be application/json. Multipart file uploads belong on the other image routes.
• Optional seed pins a result for tests. Optional negative_prompt steers away from artifacts you keep seeing.
• Do not send internal flags meant for PixelAPI operators. Documented fields for integrators are image, prompt, reference_image, seed, negative_prompt, and webhook_url if you prefer a callback over polling.
• Poll GET /v1/image/{generation_id}. The OpenAPI text that mentions a jobs path is not the public poll you should ship.
• Identity-sensitive edits (face, body, garment) should be QC’d against the input before you show the file to an end user.

Use cases and related pages

Agencies batch seasonal color on product stills. Portrait apps restyle lighting. Marketplaces apply a studio look to phone photos. Fashion tools drape a reference garment when you pass reference_image.

Industry: ecommerce, fashion, photography, social, real estate. How-tos: modify background, modify clothing, change color, retouch portrait, add an element. Alternatives: Adobe Firefly, Clipdrop, Leonardo. Index hubs: use cases, alternatives, howto.

Frequently asked questions