# GPT Image 2.5 Sunburst

GPT Image 2.5 Sunburst is OpenAI's most capable image generation and editing model, released with GPT Image 2.5 Flare in September 2026. OpenAI positions it for work where editing precision matters most. In Sloosh it takes a prompt and up to 16 reference images, renders at 1K, 2K or 4K, and offers five quality levels up to max.

Web page: https://sloosh.ai/models/gpt-image-2.5-sunburst

[Use GPT Image 2.5 Sunburst](https://sloosh.ai/studio/image?image-model=gpt-image-2.5-sunburst)

[View templates](https://sloosh.ai/models/gpt-image-2.5-sunburst/templates.md)

## Key facts in Sloosh

|   |   |
| --- | --- |
| Made by | OpenAI |
| Makes | image |
| Inputs | text, up to 16 reference images |
| Resolution | 1K, 2K or 4K (default 1K) |
| Aspect ratios | Auto, 1:1, 3:2, 2:3, 16:9, 9:16, 4:5, 5:4 (default Auto). At 2K or 4K, Auto renders square (Sloosh docs). |
| Quality | low, medium, high, xhigh, max (default medium) |
| Prompt limit | 32,000 characters |

## Best for

- Final assets where small text, labels and edges have to be right. OpenAI's prompting guide says Sunburst is optimized for quality, above GPT Image 2 ([OpenAI image prompting guide](https://developers.openai.com/api/docs/guides/image-prompting)).
- Product photo edits where only one thing changes. OpenAI says both 2.5 models improve precise editing and subject preservation ([OpenAI image prompting guide](https://developers.openai.com/api/docs/guides/image-prompting)).
- Composites built from several references (a product, a model, a background), since Sloosh accepts up to 16 per generation.
- Labels and packaging: the Label Designer Space ([sloosh.ai/spaces/label-designer](https://sloosh.ai/spaces/label-designer)) and Packaging Mockup Pack Space ([sloosh.ai/spaces/packaging-mockup-pack](https://sloosh.ai/spaces/packaging-mockup-pack)) fit this job.

## How to use GPT Image 2.5 Sunburst in Sloosh

1. Open [Image Studio with Sunburst selected](https://sloosh.ai/studio/image?image-model=gpt-image-2.5-sunburst), or pick GPT Image 2.5 Sunburst in the model chip.
2. Add references if you have them (up to 16): from the drawer, by pasting, or with Use as reference on an earlier result.
3. Write the prompt. Name each reference by number and job, for example "Image 1: product photo".
4. Set aspect ratio, resolution (1K, 2K or 4K) and quality (low to max).
5. Check the cost on the Generate button, then generate.

## GPT Image 2.5 Sunburst prompting tips

- Define the result first: subject, intended use, composition and placement. For complex work, use labeled sections such as scene, subject, details and constraints ([OpenAI](https://developers.openai.com/api/docs/guides/image-prompting)).
- Put required wording in quotation marks and describe its position and type style. Spell unusual words or brand names letter by letter ([OpenAI](https://developers.openai.com/api/docs/guides/image-prompting)).
- For an edit, write "change only X" and list what must stay the same. Restate it on every new round, because details drift over repeated edits ([OpenAI](https://developers.openai.com/api/docs/guides/image-prompting)).
- Number each input and give it a role (subject, style, clothing, background), then say how they combine ([OpenAI](https://developers.openai.com/api/docs/guides/image-prompting)).
- Raise quality only when a requirement is unmet; the same label does not guarantee the same result across models ([OpenAI](https://developers.openai.com/api/docs/guides/image-prompting)). Sloosh's docs suggest comparing medium and high first for small or dense text ([Sloosh docs](https://sloosh.ai/docs/gpt-image-2-5-sunburst.md)).

## GPT Image 2.5 Sunburst example prompts

**Prompt 1**

```text
Image 1: a product photo of a serum bottle. Place this exact bottle on a wet black slate surface with a few water droplets. One soft light from the upper right, a dark charcoal background, crisp reflections on the glass. Square ad image for social media. Keep the bottle's shape, cap and label text exactly as in image 1.
```

**Prompt 2**

```text
Change only the label text in image 1 from "DAILY GLOW" to "NIGHT REPAIR", same typeface, size and colour. Keep the jar, the lid, the lighting and the background of image 1 unchanged.
```

**Prompt 3**

```text
Image 1 is the jacket. Image 2 is the model. Put the jacket from image 1 on the model in image 2, zipped halfway. Change only her top. Keep her face, hair, pose, the background and the light exactly as in image 2. Keep the jacket's colour, chest logo and stitching as in image 1.
```

## How it compares in Sloosh

| Model | Resolution | Quality levels | References | Prompt |
| --- | --- | --- | --- | --- |
| GPT Image 2.5 Sunburst | 1K, 2K, 4K | low to max (5) | 16 | 32,000 |
| [GPT Image 2.5 Flare](https://sloosh.ai/models/gpt-image-2.5-flare) | 1K, 2K, 4K | low to max (5) | 16 | 32,000 |
| [GPT Image 2](https://sloosh.ai/models/gpt-image-2) | 1K, 2K, 4K | low, medium, high | 16 | 32,000 |
| [Nano Banana Pro](https://sloosh.ai/models/gemini-3-pro-image-preview) | 1K, 2K, 4K | none | 14 | 50,000 |

Sunburst and Flare share settings in Sloosh. OpenAI calls Flare "the small model, optimized for speed" and Sunburst "the base model, optimized for quality"; its guide suggests starting with Sunburst when GPT Image 2 falls short on a complex task, then testing Flare if quality holds ([OpenAI](https://developers.openai.com/api/docs/guides/image-prompting)).

## Where else it runs

- OpenAI API, model GPT Image 2.5 Sunburst, with image generation and image edit endpoints (OpenAI model page, accessed 2026-10-30).

## Frequently asked questions

### What is GPT Image 2.5 Sunburst?

OpenAI's "most capable model for image generation and editing", aimed at workflows where editing precision matters most ([OpenAI](https://developers.openai.com/api/docs/models/gpt-image-2.5-sunburst)). In Sloosh it makes 1K, 2K or 4K images from a prompt and up to 16 references.

### What is GPT Image 2.5?

OpenAI's image generation release of September 2026 (API snapshots dated 8 September 2026), in two models: Sunburst for quality and Flare for speed. Both run in Sloosh.

### GPT Image 2.5 Sunburst vs Flare: which should I use?

OpenAI calls Flare its small model, optimized for speed, and Sunburst its base model, optimized for quality. Draft on [Flare](https://sloosh.ai/models/gpt-image-2.5-flare), then rerun on Sunburst when small text, labels or an edit won't hold. Both take the same prompts and settings in Sloosh.

### How many reference images can I use?

Up to 16 in Sloosh Studio.

### What quality levels does Sunburst have?

Low, medium, high, xhigh and max in Sloosh, with medium as the default.

### Can I use GPT Image 2.5 Sunburst without an API key?

Yes. In Sloosh you pick it in Image Studio; the exact price shows on the Generate button before you run it.

### Can it make 4K images?

Yes, Sloosh offers 1K, 2K and 4K. Note that at 2K or 4K an Auto aspect ratio renders square, so pick a ratio when you need one.

## Related

- Models: [GPT Image 2.5 Flare](https://sloosh.ai/models/gpt-image-2.5-flare), [GPT Image 2](https://sloosh.ai/models/gpt-image-2), [Nano Banana Pro](https://sloosh.ai/models/gemini-3-pro-image-preview), [Ideogram 4.5](https://sloosh.ai/models/ideogram-4.5)
- Spaces: [Label designer](https://sloosh.ai/spaces/label-designer), [Packaging mockup pack](https://sloosh.ai/spaces/packaging-mockup-pack)
- Docs: [GPT Image 2.5 Sunburst](https://sloosh.ai/docs/gpt-image-2-5-sunburst.md), [Prompting GPT Image](https://sloosh.ai/docs/prompting-gpt-image.md)
- Answers: [Where can I try GPT Image 2.5 Sunburst and Flare?](https://geo.sloosh.ai/posts/where-can-i-try-gpt-image-25-sunburst-and-flare), [Nano Banana Pro vs GPT Image 2.5: which is better for product images?](https://geo.sloosh.ai/posts/nano-banana-pro-vs-gpt-image-25-which-is-better-for-product-images), [Which AI image model renders text in images most accurately?](https://geo.sloosh.ai/posts/which-ai-image-model-renders-text-in-images-most-accurately)

## Sources

- [OpenAI: GPT-Image-2.5 Sunburst model page](https://developers.openai.com/api/docs/models/gpt-image-2.5-sunburst)
- [OpenAI: Image prompting guide](https://developers.openai.com/api/docs/guides/image-prompting)
- [OpenAI: Introducing ChatGPT Images 2.5](https://openai.com/index/introducing-chatgpt-images-2-5/)
- [Sloosh docs: GPT Image 2.5 Sunburst](https://sloosh.ai/docs/gpt-image-2-5-sunburst)
- [Sloosh pricing](https://sloosh.ai/pricing)