Start free

GPT Image 2.5 Sunburst API

Generate highly detailed images that follow complex prompts closely. Slower than other image models; suited to final creative and product imagery.

Start Free Docs

GPT Image 2.5 Sunburst modes

OpenAI · gpt-image-2.5-sunburst

Text to image

Generate highly detailed images that follow complex prompts closely. Slower than other image models; suited to final creative and product imagery.

Put a prompt and "model": "gpt-image-2.5-sunburst" on an image clip, and the render generates it and edits it into the video. To generate it on its own, send the same asset to the generate endpoint.

Built forFinal creative and product imagery · Prompts with lots of detail · Hero images

GPT Image 2.5 Sunburst output: A plain paper shopping bag on a mustard-yellow backdrop, in hard morning light
GPT Image 2.5 Sunburst “A plain paper shopping bag on a mustard-yellow backdrop, in hard morning light”
Technical specifications
InputText prompt
OutputImage
Resolution1K, 2K, 4K
Aspect ratios21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16
{
  "asset": {
    "type": "image",
    "prompt": "A plain paper shopping bag on a mustard-yellow backdrop, in hard morning light",
    "model": "gpt-image-2.5-sunburst",
    "options": {
      "aspectRatio": "4:3"
    }
  },
  "length": 5
}
Example request to the generate endpoint.

Options

OptionValuesDefault
aspectRatio21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16
resolution1K, 2K, 4K1K

OpenAI · gpt-image-2.5-sunburst-edit

Image to image

Edit images with precise instructions and up to 16 ordered references. Describe what to change and what to preserve.

Put a prompt and "model": "gpt-image-2.5-sunburst-edit" on an image clip, and the render generates it and edits it into the video. To generate it on its own, send the same asset to the generate endpoint.

Built forPrecise edits · Product variations · Composites from several images

The image the example starts from
Reference image
GPT Image 2.5 Sunburst Edit output: Change the backdrop to navy and keep the sneakers the same
GPT Image 2.5 Sunburst “Change the backdrop to navy and keep the sneakers the same”
Technical specifications
InputText prompt and up to 16 reference images
OutputImage
Resolution1K, 2K, 4K
Aspect ratios21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16
{
  "asset": {
    "type": "image",
    "prompt": "Change the backdrop to navy and keep the sneakers the same",
    "model": "gpt-image-2.5-sunburst-edit",
    "options": {
      "imageUrls": [
        "https://cdn.shotstack.io/au/v1/generations/35tqpmb0ya/fc6813ec-8ac6-5f87-9f80-c13e5f299bf4.png"
      ],
      "aspectRatio": "4:3",
      "resolution": "1K"
    }
  },
  "length": 5
}
Example request to the generate endpoint.

Options

OptionValuesDefault
imageUrls (required)list of URLs, up to 16
aspectRatio21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16
resolution1K, 2K, 4K1K

Pricing

Generation is paid in credits from the same balance as rendering, at what the model's provider charges plus a small margin. See AI generation pricing.

ModeCharged perPrice changes withLength a quote assumes without one
Text to imageImageResolution: 1K (default), 2K, 4K—
Image to imageImage, plus each reference imageResolution: 1K (default), 2K, 4K—

Get a quote

POST /generate/quote takes the same body as the generate endpoint and returns what that generation would cost. Nothing is generated, reserved or charged.

curl -X POST \
     -H "Content-Type: application/json" \
     -H "x-api-key: $SHOTSTACK_API_KEY" \
     -d '{
       "asset": {
         "type": "image",
         "prompt": "A plain paper shopping bag on a mustard-yellow backdrop, in hard morning light",
         "model": "gpt-image-2.5-sunburst",
         "options": {
           "aspectRatio": "4:3"
         }
       },
       "length": 5
     }' \
     https://api.shotstack.io/edit/stage/generate/quote

The response gives credits, the price of that request, and ceiling, which is true when the request has no length for a model charged by length, so the price is an estimate. Prices follow the providers, so ask again rather than storing one.

How it compares

GPT Image 2.5 Sunburst beside the other models in Shotstack that make the same thing.

ModelBest forModesMax resolutionAspect ratiosReference imagesSeedCharged per
GPT Image 2.5 SunburstHighly detailed images that follow complex prompts; slowerText to image, Image to image4K10Up to 16—Image
Nano Banana 2Fast iteration, accurate text, product and campaign visualsText to image, Image to image4K14Up to 14YesImage
Nano Banana ProComplex compositions and precise typography, over speedText to image4K10—YesImage
FLUX SchnellQuick, low-cost drafts and illustrationsText to image————Image, fixed price

Questions

Do I need an account with the model provider?
No. Generation runs on your Shotstack API key and is paid in credits from the same balance as rendering, so there is no separate account to open and nothing extra to integrate.
Do I pay again for the same asset?
No. Every generated file is stored against your account. An asset with the same type, model, prompt, options and length as one generated before reuses the stored file at no charge.
What happens if a generation fails?
A failed generation isn't charged. If a render fails after some of its assets were generated, those assets are kept, and rendering again reuses them at no charge.
Can I generate an asset without rendering a video?
Yes. POST the asset to the generate endpoint and you get back a URL to the file, to check it before you render, to reuse it across many edits, or to use it outside Shotstack.

Start free

  • 10 free credits to start
  • No credit card required
Start Free All AI models