MAI-Image-2.7 Edit API

microsoft/mai-image-2.7/edit

MAI-Image-2.7 Edit is Microsoft AI's image editor: change, remove or replace objects, update text and clean up flaws while the rest of the picture stays put, or combine up to 5 images. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Image Editing
Input

Drag & drop or click to upload

preview

Idle

Change the mug glaze to deep red, keep everything else the same

$0.035per run·~28 / $1

ExamplesView all

Change the mug glaze to deep red, keep everything else the same

Change the mug glaze to deep red, keep everything else the same

Related Models

README

MAI-Image-2.7 Edit

MAI-Image-2.7 Edit changes images from a text instruction: remove, replace or recolour objects, update text, clean up flaws, or combine up to 5 images. Microsoft AI's higher-quality MAI-Image-2.7 for final images.

Why Choose This?

  • Precise edits — Change what you ask for and keep the rest of the composition and layout.
  • Up to 5 images — Edit one image, or combine several into a new picture.
  • Text updates — Rewrite lettering on labels, signs and posters.

Parameters

ParameterDescription
promptThe edit, and what must stay the same (up to 20,000 characters).
images1-5 input images. One is edited; several are combined.

Pricing

Input imagesPrice per image
1$0.0432
3$0.0596
5$0.076

Output

  • One PNG of about 1 megapixel. Its shape follows your input images.
  • Input images larger than 1 megapixel are scaled down first.

Tips

  • Say what to change and what to preserve, for example layout, faces or product labels.
  • When combining images, say what each one contributes.
  • Edits that make realistic images of minors are declined.
Note:This website uses AI models provided by third parties. Documentation prices are for reference and may be outdated. The Generate button shows an estimate; the final task charge prevails.

Mai Image 2.7 Edit API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/microsoft/mai-image-2.7/edit with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Mai Image 2.7 Edit below.

HTTP example
set -euo pipefail

: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"

REQUEST_BODY=$(cat <<'JSON'
{
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "images": [
        "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
    ]
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/microsoft/mai-image-2.7/edit" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d "$REQUEST_BODY")

TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body "$RESULT_URL" \
    -H "Authorization: Bearer $WAVESPEED_API_KEY")
  RESULT=$(printf '%s' "$RESPONSE" | jq 'if has("data") then .data else . end')
  STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
  case "$STATUS" in
    completed) printf '%s\n' "$RESULT" | jq '.outputs'; break ;;
    failed|cancelled|timeout|deleted) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done
Node.js example
const submitUrl = "https://api.wavespeed.ai/api/v3/microsoft/mai-image-2.7/edit";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');

async function requestJson(url, options = {}) {
  const response = await fetch(url, options);
  if (!response.ok) throw new Error(await response.text());
  return response.json();
}

// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
  method: "POST",
  headers: {
    "Authorization": `Bearer ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "prompt": "A cinematic shot of a city at sunset, soft golden light",
        "images": [
                "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
        ]
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = `https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;

// 2. Poll until the prediction finishes.
while (true) {
  const resultBody = await requestJson(resultUrl, {
    headers: { "Authorization": `Bearer ${apiKey}` },
  });
  const result = resultBody.data ?? resultBody;
  if (result.status === "completed") {
    console.log(result.outputs);
    break;
  }
  if (["failed", "cancelled", "timeout", "deleted"].includes(result.status)) throw new Error(JSON.stringify(result));
  await new Promise(resolve => setTimeout(resolve, 2000));
}
Python example
import json
import os
import time
from urllib.request import Request, urlopen

api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "images": [
        "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
    ]
}

def request_json(url, data=None):
    request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
    with urlopen(request) as response:
        return json.load(response)

# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/microsoft/mai-image-2.7/edit", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
    raise RuntimeError("Submission response did not contain a prediction id")
result_url = f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"

# 2. Poll until the prediction finishes.
while True:
    result_body = request_json(result_url)
    result = result_body.get("data", result_body)
    status = result.get("status")
    if status == "completed":
        print(result.get("outputs", []))
        break
    if status in {"failed", "cancelled", "timeout", "deleted"}:
        raise RuntimeError(result)
    time.sleep(2)

Mai Image 2.7 Edit API — Frequently asked questions

What is the Mai Image 2.7 Edit API?

Mai Image 2.7 Edit is a Microsoft model for image editing, exposed as a REST API on WaveSpeedAI. MAI-Image-2.7 Edit is Microsoft AI's image editor: change, remove or replace objects, update text and clean up flaws while the rest of the picture stays put, or combine up to 5 images. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.

How do I call the Mai Image 2.7 Edit API?

POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID. Poll the result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates Python, JavaScript, and cURL examples for submitting requests and polling results. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/microsoft/mai-image-2.7/edit.

How much does Mai Image 2.7 Edit cost per run or per second?

Mai Image 2.7 Edit starts at $0.035 per run or per second. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.

What inputs does Mai Image 2.7 Edit accept?

Key inputs: `prompt`, `images`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/microsoft/mai-image-2.7/edit.

How do I get started with the Mai Image 2.7 Edit API?

Sign up for a free WaveSpeedAI account to claim starter credits, copy your API key from /accesskey, then call the endpoint shown in the API tab of the playground. The playground also auto-generates a code sample in Python, JavaScript, or cURL for the parameters you've set.

Can I use Mai Image 2.7 Edit outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (Microsoft). Check the provider's applicable terms and WaveSpeedAI's Terms of Service before commercial use.

llms.txt — microsoft/mai-image-2.7/edit for AI agents and LLMs