whatmodel.sh / image / GPT-Image-2.6 Sunburst

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

Release date ↗

86.6±2.1#3 of 147 image modelsfrom 2 benchmark results across 1 source* thinly tested, treat the rank as provisional

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.

#modelscorewhereRAMreleased
1GPT Image 2.5 Sunburst OpenAI91±2api $0.013/image2026-09
2GPT Image 2.5 Flare OpenAI87±2api $0.013/image2026-09
3GPT-Image-2.6 Sunburst OpenAI87±2api price unknown2026-11
4GPT-Image-2.6 Flare OpenAI85±2api price unknown2026-11
5GPT Image 2 OpenAI83±1api $0.053/image2026-04
more from OpenAI
14ChatGPT Image Latest (chatgpt-image-latest) OpenAI73±4api $0.034/image2025-12
19GPT Image 1.5 OpenAI70±1api $0.034/image2025-12
46GPT Image 1 OpenAI60±1api $0.042/image2025-04

see all image models · find the ones that fit your machine

$ 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.

testresultvs the others in its rundifficultycountswhy
LMArena text-to-image1405.6 ✎▁▁▃▃▆█▄▂▂▂▁▃ beats 77/78avg 1030▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 73%typical
image to image / editing▁▁·▃▂▃█▆▃▆▂▃ #3 of 65 * · 25% of its score · 1 test
testresultvs the others in its rundifficultycountswhy
Arena image edit1476.5 ✎▂▁▁▃▆█▅▇█▄▃▃ beats 54/56avg 1160▇▇▇▇▇▇▇▇▇▇ 25%typical

$ 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

sourceresultsshare of the scorelicence
LMArena leaderboard dataset2CC BY 4.0
prior · pull toward the middle
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