OpenAI's GPT Image 2 Edit enables image editing from natural-language instructions with one or more reference images. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
En attente

$0.07par exécution·~14 / $1

A high-end fashion editorial portrait of a blonde Western female model wearing the earrings shown in the image. The model is in her early 20s, with flawless, radiant skin and subtle freckles. She wears natural, dewy makeup with a soft blush and nude glossy lips. Her features are refined, with high cheekbones and a well-defined jawline. Her blonde hair is styled in a sleek low bun, neatly tucked behind her ears to fully showcase the earrings. She is posed in an elegant side profile, with her eyes gently closed, conveying a calm, graceful, and serene expression. The lighting is warm natural light, with soft botanical shadows cast across her face and shoulders, creating a soft yet high-contrast editorial atmosphere. The light enhances the texture of her skin as well as the reflective shine of the gold and pearl. The background is minimal, in warm beige tones, softly blurred, presenting a premium lifestyle aesthetic. Shot in an ultra-realistic style with fashion magazine quality, using an 85mm lens and shallow depth of field. The earrings are in sharp focus, with soft cinematic lighting, high detail, and a luxurious jewelry advertisement style, in 8K resolution.
OpenAI GPT Image 2 Edit transforms one or more reference images using natural-language instructions. Upload your image, describe the changes you want, and the model generates a polished edited result with strong prompt alignment and production-ready quality.
Natural-language image editing Edit images by simply describing the changes you want in plain language — no manual masking or complex editing workflow required.
Works with reference images Use one or more input images as the visual source for edits, transformations, or style adjustments.
Flexible aspect ratios Generate edited outputs in square, portrait, or landscape formats for different publishing and design needs.
Production-ready API Access the model through a ready-to-use REST inference API for easy integration into apps, tools, and creative pipelines.
Fast and affordable Get high-quality image edits with simple usage-based pricing and no cold-start friction.
| Parameter | Required | Description |
|---|---|---|
| images | Yes | Reference images to edit (up to 16) |
| prompt | Yes | Text description of the desired edit |
| aspect_ratio | No | Aspect ratio: 1:1, 3:2, 2:3, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9. Auto-detected from input image if not specified. |
| resolution | No | Output resolution: 1k (default), 2k, or 4k. |
| quality | No | Image quality: low, medium (default), or high. |
1:1 for square, 2:3 or 9:16 for portrait, 3:2 or 16:9 for landscape, etc. Auto-detected from input image if not specified.Turn this product photo into a premium studio advertisement with soft cinematic lighting, a clean beige background, subtle shadows, realistic reflections, and luxury brand aesthetics
Pricing varies by quality and resolution.
Prices below include one input image. Each additional input image adds $0.012.
| Quality | 1k | 2k | 4k |
|---|---|---|---|
| low | $0.02 | $0.03 | $0.04 |
| medium | $0.07 | $0.11 | $0.19 |
| high | $0.23 | $0.41 | $0.73 |
images and prompt are required fields.1:1, 3:2, 2:3, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, and 21:9. Auto-detected from input image if not specified.Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/openai/gpt-image-2/edit with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Gpt Image 2 Edit below.
set -euo pipefail
: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"
REQUEST_BODY=$(cat <<'JSON'
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"images": [
"https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
],
"aspect_ratio": "1:1",
"resolution": "1k",
"quality": "medium",
"output_format": "png"
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/openai/gpt-image-2/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=$(printf '%s' "$TASK" | jq -r '.urls.get // empty')
if [ -z "$RESULT_URL" ]; then
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"
fi
# 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' "$RESULT" | jq '.outputs'; break ;;
failed|cancelled|timeout) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
created|processing) sleep 2 ;;
*) printf 'Unexpected status: %s
' "$STATUS" >&2; exit 1 ;;
esac
doneconst submitUrl = "https://api.wavespeed.ai/api/v3/openai/gpt-image-2/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 ${apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"images": [
"https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
],
"aspect_ratio": "1:1",
"resolution": "1k",
"quality": "medium",
"output_format": "png"
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
`https://api.wavespeed.ai/api/v3/predictions/${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"].includes(result.status)) throw new Error(JSON.stringify(result));
if (!["created", "processing"].includes(result.status)) throw new Error("Unexpected status: " + result.status);
await new Promise(resolve => setTimeout(resolve, 2000));
}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"
],
"aspect_ratio": "1:1",
"resolution": "1k",
"quality": "medium",
"output_format": "png"
}
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/openai/gpt-image-2/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 = task.get("urls", {}).get("get") or 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"}:
raise RuntimeError(result)
if status not in {"created", "processing"}:
raise RuntimeError(f"Unexpected status: {status}")
time.sleep(2)Gpt Image 2 Edit is a OpenAI model for image editing, exposed as a REST API on WaveSpeedAI. OpenAI's GPT Image 2 Edit enables image editing from natural-language instructions with one or more reference 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.
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 production-oriented Python, JavaScript, and cURL examples with timeouts, transient-error handling, and safe GET retries. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/openai/openai-gpt-image-2-edit.
Gpt Image 2 Edit starts at $0.070 per run. 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.
Key inputs: `prompt`, `images`, `aspect_ratio`, `resolution`, `enable_base64_output`, `enable_sync_mode`. 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/openai/openai-gpt-image-2-edit.
Median end-to-end generation time on WaveSpeedAI is around 56 seconds per request, based on recent successful runs. Queue time varies with global demand; live status is visible in the prediction record.
Commercial usage rights depend on the model's license, set by its provider (OpenAI). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.