GPT Image 2.5 Sunburst API

Introduction

GPT Image 2.5 Sunburst Edit runs OpenAI's gpt-image-2.5-sunburst on images you already have. It takes one to sixteen sources, an optional PNG mask and a transparent-background option, and it is the model OpenAI recommends when editing precision matters most.

Choose a mode by starting material

Key features

Masks, fidelity and transparency

A mask limits the repaint to its transparent pixels; input fidelity high keeps faces and fabric closer to the sources; background transparent returns a real alpha channel in PNG or WebP.

Up to sixteen sources

Combine people, settings and products from up to sixteen images in one request, each referred to by its order in the prompt.

Precision is the point

In our crimson-gown edit only the fabric changed: the lace sleeves, the face, the chair and the single key light stayed where they were.

Request parameters

Pricing

Prices are in credits, the same credits you use on the website (1 credit = $0.01). The hold is taken when the task is accepted and settled to the actual charge when it finishes; failed tasks are refunded.

Each task is rounded up to whole credits, so one run at the lowest tier costs 1 credit per image ($0.01).

For an exact number before you run, send the same body to POST /jobs/quote.

Use cases

Retouch approved photographs

Change a garment, a colour or the light in a signed-off photograph without touching the rest of the frame, masked or unmasked.

Cut-outs for layouts

People and products returned on a transparent background, ready for a layout, a slide or a product page without a separate removal step.

Product recolours

One product photograph in several finishes or colours, masked to the product so the set and the light stay identical.

Prompt guide & pro tips

Build the mask to match the source

Same pixel size as the first source, saved as PNG, transparent only where the repaint should happen. Everything opaque is protected.

Write the protected list out

After the change, name what must stay: face, hair, pose, chair, light. The model follows a written list more reliably than an implied one.

For cut-outs, name what to keep

Say which subject stays and that the background should be fully transparent, and set output_format to png or webp.

Check the alpha before layout

Open the returned PNG or WebP in your layout tool: the empty area is a real alpha channel, so no extra keying or masking step is needed.

API quick start

Call the GPT Image 2.5 Sunburst API in three steps

1. Create an API key. Sign in to PopNow and create a key in the API console. Keys start with sk-popnow- and use the same credits as the website.
2. Send the request. POST /jobs/createTask with model openai/gpt-image-2.5-sunburst/edit and an input object that follows the parameter table. The response returns a task ID straight away.
3. Get the result. Poll GET /jobs/recordInfo with the task ID, or pass a callBackUrl and we post the result to it. Download the output links when the task succeeds.

# 1. Create the task. Keep the Idempotency-Key if you retry after a network error.
export IDEMPOTENCY_KEY="$(uuidgen)"
curl -X POST https://api.popnow.ai/api/v1/jobs/createTask \
  -H "Authorization: Bearer $POPNOW_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $IDEMPOTENCY_KEY" \
  -d '{
  "model": "openai/gpt-image-2.5-sunburst/edit",
  "input": {
    "prompt": "A ceramic teapot on a linen cloth, soft window light, muted palette",
    "image_urls": [
      "https://media.popnow.ai/influencer/examples/marco.webp"
    ],
    "aspect_ratio": "1:1",
    "resolution": "1k",
    "quality": "high",
    "num_outputs": 1,
    "input_fidelity": "low"
  }
}'

# 2. Copy data.taskId from the response, then poll until state is succeeded, failed, canceled or expired.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
  -H "Authorization: Bearer $POPNOW_API_KEY"

Replace the prompt and any links with your own. The API tab has the response, polling and callback reference.

GPT Image 2.5 Sunburst API questions

All GPT Image models

GPT Image 2.5 Flare has the same options and price per image but is tuned for speed and usually finishes sooner. Sunburst is the one for final images and precise edits.

• GPT Image 2.5 Sunburst APIOpenAI's quality-first model, up to 4K with clean textFrom 1 credit per image
• GPT Image 2.5 Flare APIOpenAI's speed-first model with masked edits and cut-outsFrom 1 credit per image
• GPT Image 2 APILegible in-image text and precise masked editsFrom 1 credit per image

Other image APIs

• Nano Banana 2.1 APIGoogle's newest Nano Banana, sharp text and 4K outputFrom 8 credits per image
• Nano Banana Pro APIPlans the layout first: dense text, diagrams and 4K editsFrom 17 credits per image
• Seedream 5.0 Pro APIHigh-detail images and edits from up to ten referencesFrom 6 credits per image
• FLUX.2 Max APITop-tier FLUX: photoreal light and exact brand colorsFrom 11 credits per image
• Qwen Image 2.1 Pro APIUp to six detailed 2K images from one promptFrom 6 credits per image
• Qwen Image 2.1 Turbo APIFast 8-step renders, up to six per promptFrom 3 credits per image

More about GPT Image 2.5 Sunburst

Try it

GPT Image 2.5 Sunburst AI Image Generator onlineCreate images with GPT Image 2.5 Sunburst in PopNow

Compare

Nano Banana 2.1 vs GPT Image 2.5 Sunburst

Docs

GPT Image 2.5 Sunburst model ID and input schema in the API docsPopNow API quickstart: your first request in five minutesImage generation guide for the PopNow APIWebhooks: get GPT Image 2.5 Sunburst results without polling