# gpt-image-2.5-sunburst decision evidence

GPT Image 2.5 Sunburst is OpenAI's closed-weight image generation and editing model for workflows where editing precision matters most, released on 2026-09-08 alongside Flare, which OpenAI positions for fast everyday generation. It takes text and up to 16 reference images and outputs images up to 3840x2160; OpenAI still cautions that repeated edits can change details you meant to keep, and the reviewed stress test held up through five chained edits.

Verified: 2026-09-24; snapshot: 2026-09-25.

## Published model card

As the vendor publishes it for the model and its weights; these are not the limits of a hosted endpoint.

- Context window: Not published; prompts are limited to 32,000 characters
- Maximum output: 1 to 10 images per request, up to 3840x2160 each (sizes above 2560x1440 are experimental)
- Modalities: Text and image input (up to 16 reference images when editing); image output
- Parameter count: Not disclosed

## Open weights and deployment

Status: Unavailable. OpenAI publishes no GPT Image 2.5 weights. Sunburst is served through the Image API (generations and edits) and the Responses API image generation tool.

## Real-task reports

### [Repeated edits to one image with GPT Image 2.5 Sunburst](https://x.com/alecwilcock/status/2100555617941307601)

By [Alec Wilcock](https://x.com/alecwilcock) (@alecwilcock). AI educator and content creator whose profile lists a social-media role at ElevenLabs

Published: 2026-09-17; retrieved: 2026-09-24; verified: 2026-09-24.

- Task: Change the t-shirt in a photo, then feed each output back in as the next input
- Method: Chained edits of the same image with one prompt per round, shown in a video.
- Finding: The image still held up at round five; the author says the video does not flatter the model, but that other models rarely get past round three before breaking down.
- Limitation: One chain of edits judged by eye; the comparison with other models is asserted, not shown; the author works in social media at ElevenLabs.
- Rounds shown: 5

## Public leaderboard coverage

A board missing from this list has no figure for this model in this snapshot; missing coverage is not a zero.

- LMArena Text-to-Image Arena — Arena score (Elo): 1424 ±8 (retrieved 2026-10-05) [source](https://arena.ai/leaderboard/text-to-image)
- LMArena Image Edit Arena — Arena score (Elo): 1522 ±5 (retrieved 2026-10-05) [source](https://arena.ai/leaderboard/image-edit)
- Artificial Analysis Text To Image — Elo: 1179 -11/11 (retrieved 2026-09-13) [source](https://artificialanalysis.ai/image/leaderboard/text-to-image)
- Artificial Analysis Editing — Elo: 1167 -10/10 (retrieved 2026-09-13) [source](https://artificialanalysis.ai/image/leaderboard/editing)

## Official sources

- [Introducing ChatGPT Images 2.5](https://openai.com/index/introducing-chatgpt-images-2-5/) — OpenAI, retrieved 2026-09-24
- [GPT-Image-2.5 Sunburst model documentation](https://developers.openai.com/api/docs/models/gpt-image-2.5-sunburst) — OpenAI, retrieved 2026-09-24
- [Image prompting guide](https://developers.openai.com/api/docs/guides/image-prompting) — OpenAI, retrieved 2026-09-24
- [ChatGPT Images 2.5 System Card](https://deploymentsafety.openai.com/chatgpt-images-2-5) — OpenAI, retrieved 2026-09-24