whatmodel.sh / image / GPT-Image-2.6 Sunburst
GPT-Image-2.6 Sunburst
↗ share
+ contribute
GPT-Image-2.6 Sunburst is a closed-weights image model from OpenAI, released November 2026. Licence: proprietary.
Catalogue identity notes
OpenAI API changelog, Nov 4 2026: 'Released GPT-Image-2.6 Sunburst and GPT-Image-2.6 Flare for image generation and editing'. Model id gpt-image-2.6-sunburst (single snapshot), endpoints v1/images/generations and v1/images/edits, generally available. Successor to and distinct from gpt-image-2-5-sunburst. Arena's '(Medium)' suffix is OpenAI's quality parameter (Sunburst/Flare quality options: low, medium, high, xhigh, max; complexity is a separate parameter defaulting to high). Corresponds to Arena entries 'GPT-Image-2.6 Sunburst (Medium)' on text_to_image and image_edit. Price: No per-image price recorded. OpenAI publishes token prices only (model page and pricing table: image input $8.00, cached image input $2.00, image output $30.00, text input $5.00, cached text $1.25 per 1M tokens). Its per-image figure for 1024x1024 medium is produced by an interactive calculator in the image-generation guide and is not printed statically. fal.ai's endpoint openai/gpt-image-2.6/sunburst/text-to-image (published 2026-11-04) also shows only the token rates, with its per-size table not in the static page or llms.txt. models.dev has only OpenRouter and Vercel gateway tomls (aggregators). Observed 2026-11-12.
Model information sources
Score within the LMArena text-to-image comparison set only.
$ how it compares
The image models ranked either side of GPT-Image-2.6 Sunburst, out of 200 with a score, then more from OpenAI.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 1 | 91±2 | api $0.013/image | |||
| 2 | 87±2 | api $0.013/image | |||
| 3 | 87±2 | api price unknown | |||
| 4 | 85±2 | api price unknown | |||
| 5 | 83±1 | api $0.053/image | |||
| more from OpenAI | |||||
| 14 | 73±4 | api $0.034/image | |||
| 19 | 70±1 | api $0.034/image | |||
| 46 | 60±1 | api $0.042/image | |||
$ what it's good at
text to image▂▅▅▃▄▄█▃▂▁▁▃ #2 of 129 * · 73% of its score · 1 test
Beats GPT Image 2.5 Flare here, though they rank higher overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| LMArena text-to-image | 1405.6 ✎ | ▁▁▃▃▆█▄▂▂▂▁▃ beats 77/78 | 73% |
image to image / editing▁▁·▃▂▃█▆▃▆▂▃ #3 of 65 * · 25% of its score · 1 test
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Arena image edit | 1476.5 ✎ | ▂▁▁▃▆█▅▇█▄▃▃ beats 54/56 | 25% |
$ where to run it
Through an API
api · price unknown · developers.openai.com ↗
$ how the score was worked out · LMArena leaderboard dataset 98%
Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works
| source | results | share of the score |
|---|---|---|
| 2 | 98% | |
| prior · pull toward the middle | 2% | |
| weighted average | = 86.6 |
$ improve this page
Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.
data updated · sources and licences · json