# GPT Image 2.5: Flare vs. Sunburst — what's different and what OpenAI's new model can do

> GPT Image 2.5 is OpenAI's image model, released on September 8, 2026 alongside ChatGPT Images 2.5. In the API it's two models: the fast Flare, with up to 50% lower latency than GPT Image 2, and the precise Sunburst for detailed work and multi-step edits. Both offer six quality levels up to max, sizes up to 3840 px and transparent backgrounds. GPT Image 2.5 is available in the AI2Face generator.

Developer: OpenAI · Released: 2026-09-08 · Updated 2026-10-27
URL: https://ai2face.com/models/gpt-image-2-5

## Key facts

| | |
|---|---|
| Developer | OpenAI |
| Release date | September 8, 2026 (model snapshots dated 2026-09-08) |
| API models | gpt-image-2.5-flare and gpt-image-2.5-sunburst |
| What it does | Generates and edits images, including with masks and multiple references |
| Size | Multiples of 16 px, up to 3840 px per side, 0.66–8.3 MP, 1:3 to 3:1; above 2560 × 1440 is experimental |
| Quality | low, medium, high, xhigh, max or auto |
| Formats | PNG, JPEG, WebP; transparent background in PNG and WebP |
| API price | $30 per million image output tokens, $8 per million image input tokens |
| In AI2Face | Yes, in the generator |

## What is GPT Image 2.5

GPT Image 2.5 is OpenAI's set of image models released on September 8, 2026. In ChatGPT they power ChatGPT Images 2.5 — on every plan, on the web, in the apps and in Codex. In the API they're two separate models:

- **Flare** (`gpt-image-2.5-flare`) — a compact model optimized for speed, the default choice;
- **Sunburst** (`gpt-image-2.5-sunburst`) — the base model optimized for quality, for detailed work and edits.

The previous version, [GPT Image 2](/models/gpt-image-2), is still in the API. For the whole family, see the [GPT Image](/models/gpt-image) overview.

## What GPT Image 2.5 can do

**Sharp detail and natural light.** OpenAI lists the key improvements: sharpness, lighting, textures and a style that doesn't drift from frame to frame.

**Reference fidelity.** The model holds recognizable objects and people from uploaded photos more reliably — useful for series built around one character or product.

**Multi-step edits.** Each new step damages less of what already works. Sunburst is more precise here than Flare.

![Left: a fisherman in a yellow jacket on a pier; right: the same shot after an edit — a red jacket and light rain](https://ai2face.com/_astro/edit.CigYx_Fy_Z2uyjqs.jpg "A one-prompt edit in GPT Image 2.5 Sunburst: the jacket was replaced and rain added, while the face, cap, pier and light stayed the same")

**Six quality levels.** low, medium, high, xhigh, max and auto. xhigh and max are exclusive to 2.5 — OpenAI suggests turning them on when high doesn't meet the bar.

**Custom sizes.** The recommended sizes are 1024 × 1024, 1536 × 1024 and 1024 × 1536, but any multiple of 16 px up to 3840 px per side works. OpenAI considers anything above 2560 × 1440 experimental.

**Transparent backgrounds.** Officially supported in PNG and WebP, unlike GPT Image 2, where the feature is still in preview.

**Mask and multi-image editing.** The edit endpoint accepts several images, and the mask applies to the first one. The mask needs an alpha channel and must match the source in size and format.

**Partial previews.** With streaming, the model returns up to 3 draft frames before the final one — each costs an extra 100 tokens.

**Sketches and comments in ChatGPT.** ChatGPT's interface added sketching as a prompt, templates and editing through a comment pinned to a specific part of the image.

## Flare vs. Sunburst

| | Flare | Sunburst |
|---|---|---|
| Type | compact, optimized for speed | base, optimized for quality |
| Quality | comparable to GPT Image 2 | higher |
| Speed | up to 50% lower latency than GPT Image 2 | slower than Flare |
| Multi-step edits | more reliable than GPT Image 2 | the most precise |
| Best for | everyday generation, bulk jobs | ad campaigns, product shots, complex edits |
| Price per token | $30 per million output | $30 per million output |

OpenAI's announcement says Flare beats GPT Image 2 on quality, while its prompting guide calls the two comparable. OpenAI customer Manus rated Flare 2–4 times faster than GPT Image 2. Equal per-token pricing doesn't mean an equal price per image: the models spend a different number of tokens on each one.

![Two still lifes side by side: a glass of red wine by a candle on an oak table, bread and a bottle — Flare on the left, Sunburst on the right](https://ai2face.com/_astro/flare-vs-sunburst.B2wi3YJp_ZT5Bdh.jpg "One prompt in both versions: Flare on the left, Sunburst on the right. Sunburst shows more detail in the bread crumb and the wood grain and a brighter frame; Flare is darker and more contrasty")

OpenAI suggests choosing like this: for a demanding task, start with Sunburst and confirm it delivers. Then run the same prompts through Flare and switch only if the quality holds and latency drops.

## What GPT Image 2.5 is good for

- **Ad creative and product shots** with several rounds of edits — Sunburst.
- **Posters, covers and infographics** with lots of text.
- **Products and stickers on transparent backgrounds** for marketplaces and design.
- **Series with one character or product** built from references.
- **Bulk generation** — Flare is faster and suits hundreds of variations.

## GPT Image 2.5 vs. alternatives

| | GPT Image 2.5 | [GPT Image 2](/models/gpt-image-2) | [Nano Banana Pro](/models/nano-banana-pro) | [Seedream 5.0](/models/seedream-5-0) |
|---|---|---|---|---|
| Developer | OpenAI | OpenAI | Google DeepMind | ByteDance Seed |
| Released | Sep 8, 2026 | Apr 21, 2026 | Nov 20, 2025 | Pro Jul 8, 2026 |
| Max size | 3840 px | 3840 px | 4K | Lite — 4K, Pro — 2K |
| Quality levels | 6, up to max | 4, up to high | 1K, 2K, 4K | 1K–4K depending on version |
| Transparent background | yes | preview | no | Pro — layers with transparency |
| Editing | mask, comments | mask | by prompt | point, box, lasso, hex |
| In AI2Face | yes | yes | yes | yes |

GPT Image 2.5 is the most convenient model for text, UIs and PNGs without a background. Nano Banana Pro is stronger with complex people scenes and likeness across several photos, and Seedream 5.0 Pro with layered layouts.

## How to write prompts for GPT Image 2.5

1. **Structure:** scene → subject → details → constraints. Split long prompts into labeled sections.
2. **Purpose and format:** "a product photo for a listing, 1:1," "a vertical poster."
3. **Visible details:** materials, lighting, color, medium. If you want photorealism, say so.
4. **Quote text verbatim** with its position and typeface, plus "no other text." For small text, use medium or higher.
5. **Be exact about framing:** "full body, feet visible."
6. **In edits:** "change only X," then list what must stay and what's off-limits — logos, watermarks.
7. **Don't rely on the prompt for pixel-perfect areas:** if a region must stay identical, composite the approved edit into the original.

Compare Flare and Sunburst at the same quality level. If the result falls short, raise the quality; if it passes, try lower settings to save time.

## How to use GPT Image 2.5 in AI2Face

The AI2Face generator has both versions — GPT Image 2.5 Flare and GPT Image 2.5 Sunburst — alongside [Nano Banana Pro](/models/nano-banana-pro) and [Seedream 5.0](/models/seedream-5-0).

1. Sign up — new accounts get starter credits.
2. Open the generator and pick Flare or Sunburst.
3. Write a prompt, and upload references or an image to edit if needed.
4. The credit cost is shown before you start. Credits don't expire.

Every image on this page was made in AI2Face with GPT Image 2.5 Sunburst; the comparison diptych also used Flare.

## Limitations

- **Large images are experimental.** OpenAI doesn't officially guarantee anything above 2560 × 1440.
- **Masks are guidance.** The model can spill past the mask edges.
- **Sunburst speed.** Complex prompts can take up to 2 minutes.
- **Moderation.** Requests and results are filtered under OpenAI's policies.
- **Mixed messaging on Flare.** The announcement says it beats GPT Image 2 on quality, the guide says it's comparable. Test on your own tasks.

## Bottom line

GPT Image 2.5 is OpenAI's best image model: Flare handles everyday work quickly and cheaply, while Sunburst covers ads, product shots and multi-step edits. Transparent backgrounds and the xhigh and max levels make it better than GPT Image 2 in almost every way. For scenes with people and likeness across several photos, compare the result with [Nano Banana Pro](/models/nano-banana-pro); for layered layouts, with [Seedream 5.0](/models/seedream-5-0) — all in the same AI2Face generator.

## Generation examples

- Portrait of an older fisherman in a navy knit cap and a yellow oilskin jacket on a pier at dawn
  Prompt: `Editorial portrait photo of a 60-year-old fisherman with a weathered face, white stubble, a navy knit cap and a yellow oilskin jacket, standing on a wooden harbor pier at dawn, light mist, natural skin texture with pores and fine wrinkles, 85mm lens, shallow depth of field, photorealistic, no text, no logos`
- THE LAST LIGHTHOUSE movie poster: a lighthouse on a cliff in a storm and a figure with a lantern on the stairs
  Prompt: `Cinematic movie poster. Title at the top in large letters: 'THE LAST LIGHTHOUSE'. Tagline below the title: 'Some lights never go out.' Bottom line in small condensed type: 'IN CINEMAS NOVEMBER 14'. Image: a lone lighthouse on a cliff in a violent storm, a tiny figure with a lantern climbing the outside stairs, huge waves, teal and amber color grade. All text exactly as written, spelled correctly, no other text, no logos.`
- A terracotta pour-over dripper on a walnut stand above a glass carafe, coffee dripping
  Prompt: `Premium product photo of a matte terracotta ceramic pour-over coffee dripper on a walnut stand above a clear glass carafe, coffee dripping, a wisp of steam, soft directional side light, warm beige seamless background, subtle shadow, photorealistic, no text, no logos`
- A Coffee extraction infographic: an extraction scale, three tastes and a 1 : 16 brew ratio
  Prompt: `Clean editorial infographic titled 'Coffee extraction'. A horizontal gradient scale from 'Under-extracted' on the left to 'Over-extracted' on the right, with 'Sweet spot' marked in the middle. Under the scale three taste notes: 'Sour, thin', 'Balanced, sweet', 'Bitter, dry'. A small box in the corner: 'Brew ratio 1 : 16'. Simple icons of a coffee cup and beans, muted brown and cream palette. All text exactly as written, spelled correctly, no other text, no logos.`

## FAQ

### How is GPT Image 2.5 Flare different from Sunburst?

Flare is the fast model: OpenAI's announcement cites up to 50% lower latency than GPT Image 2, and the prompting guide calls its quality comparable to GPT Image 2. Sunburst is the base model optimized for quality: more precise in edits, but slower.

### What's new in GPT Image 2.5 compared with GPT Image 2?

Sharper detail, natural lighting and textures, better reference fidelity, dependable multi-step edits, the xhigh and max quality levels and official transparent backgrounds. ChatGPT also gained sketches, templates and comment-based editing on the image.

### What quality levels does GPT Image 2.5 offer?

Six: low, medium, high, xhigh, max and auto, with auto as the default. xhigh and max are new in 2.5.

### What's the maximum resolution of GPT Image 2.5?

Up to 3840 pixels per side and 8.3 megapixels. OpenAI considers anything larger than 2560 × 1440 experimental.

### How much does GPT Image 2.5 cost?

In the API, $30 per million image output tokens and $8 per million image input tokens — the same for Flare and Sunburst. The per-image cost depends on size, quality and the model.

### Is GPT Image 2.5 available in AI2Face?

Yes, the AI2Face generator has both versions — Flare and Sunburst — and you see the cost before you start a generation.

## Sources

- https://openai.com/index/introducing-chatgpt-images-2-5/
- https://developers.openai.com/api/docs/models/gpt-image-2.5-flare
- https://developers.openai.com/api/docs/models/gpt-image-2.5-sunburst
- https://developers.openai.com/api/docs/guides/image-generation
- https://developers.openai.com/api/docs/guides/image-prompting