Openai Gpt Image 2.5 Sunburst Edit API Documentation

Openai Gpt Image 2.5 Sunburst Edit API Documentation

Playground

OpenAI’s GPT Image 2.5 Sunburst Edit edits one or more reference images from natural-language instructions, with five quality tiers up to 4K. Sunburst is the precision-focused GPT Image 2.5 tier that spends more time per image for extra fidelity on intricate detail. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

OpenAI GPT Image 2.5 Sunburst Edit transforms one or more reference images using natural-language instructions. Sunburst is the precision-focused GPT Image 2.5 tier that spends more time per image for extra fidelity on intricate detail.

• Need to generate a new image from scratch instead? Try OpenAI GPT Image 2.5 Sunburst Text-to-Image.
• Need a faster, lower-latency tier? Try OpenAI GPT Image 2.5 Flare Edit.

Why Choose This?

• Natural-language image editing Edit images by describing the changes you want in plain language — no manual masking or complex editing workflow required.

• Works with reference images Use up to 16 input images as the visual source for edits, transformations, or style adjustments.

• Five quality tiers Choose from low drafts to max fidelity and pay only for the detail you need.

• Up to 4K output and flexible aspect ratios Square, portrait, landscape, and panoramic outputs at 1k, 2k, or 4k.

• Production-ready API Access the model through a ready-to-use REST inference API for fast integration into applications and workflows.

Parameters

Quality Tiers

GPT Image 2.5 exposes five quality tiers. Pick the lowest tier that meets your need; every step up adds detail, latency, and cost.

How to Use

1. Upload reference images — add up to 16 images you want to edit.
2. Write your prompt — clearly describe the changes, style adjustments, or composition edits you want.
3. Pick quality and resolution (optional) — medium / 1k is the default; raise quality for more detail or resolution for larger output.
4. Choose aspect ratio (optional) — auto-detected from the first input image if not specified.
5. Submit — run the model and download your edited image.

Example Prompt

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

Pricing varies by quality and resolution. Prices below include one input image. Each additional input image adds $0.015.

Best Use Cases

• Product photo enhancement — Upgrade basic product shots into premium marketing visuals.
• Creative retouching — Change backgrounds, lighting, styling, or composition with natural-language instructions.
• Marketing adaptation — Rework existing brand assets into new campaign visuals.
• Social media content — Edit images into platform-ready formats for posts, ads, and promos.
• Design iteration — Explore multiple visual directions from the same base image.

Pro Tips

• Be specific about what should stay unchanged and what should be modified.
• Mention visual style clearly, such as photorealistic, luxury editorial, minimal, cinematic, or flat lay.
• Start at medium quality and 1k; move up a tier only if a specific detail is missing.
• If using multiple reference images, make sure they are visually clear and relevant to the intended output.

Notes

• Both images and prompt are required fields.
• Up to 16 reference images per request; the output aspect ratio follows the first image unless aspect_ratio is set.
• Requests containing sexual content are rejected before generation and are not charged.

Related Models

• OpenAI GPT Image 2.5 Sunburst Text-to-Image — Generate new images directly from natural-language prompts.
• OpenAI GPT Image 2.5 Flare Edit — The Flare tier of the same model: faster and lower latency.
• OpenAI GPT Image 2 Edit — The previous generation.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-api-key"

REQUEST_BODY=$(cat <<'JSON'
{
  "prompt": "A cinematic ocean wave at sunrise, highly detailed",
  "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-2.5-sunburst/edit" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}")

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

  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

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters