Image model vs image model
GPT Image 2.6 Flare vs GPT Image 2.6 Sunburst
Neither has an arena score yet and they cost about the same (≈$0.21 against ≈$0.21 an image), so judge them on the samples below.
Where they sit among all 59 image models
Up and to the left is better pictures for less money. Hover or tap a dot for its numbers, then click it to compare that model with GPT Image 2.6 Flare. Models the arena hasn’t rated yet sit in the grey lane at the bottom.
The specs
| Spec | GPT Image 2.6 Flare | GPT Image 2.6 Sunburst |
|---|---|---|
| Price per image | ≈$0.21 (estimated, high quality) | ≈$0.21 (estimated, high quality) |
| 100 images | $21.05 | $21.05 |
| Text-to-image Elo | Not scored yet | Not scored yet |
| Editing Elo | Not scored yet | Not scored yet |
| Edits uploaded pictures | No | No |
| Largest size | — | — |
| Open weights | No | No |
| Zero data retention | No | No |
| Lab | OpenAI | OpenAI |
| Official name | GPT Image 2.6 Flare | GPT Image 2.6 Sunburst |
| Released | November 2026 | November 2026 |
Elo ± is the 95% margin. Prices are for one 1024×1024 image from the Vercel AI Gateway.
Questions
Which is better, GPT Image 2.6 Flare or GPT Image 2.6 Sunburst?
Neither has an arena score yet and they cost about the same (≈$0.21 against ≈$0.21 an image), so judge them on the samples below.
Which is cheaper, GPT Image 2.6 Flare or GPT Image 2.6 Sunburst?
They cost about the same: GPT Image 2.6 Flare ≈$0.21 and GPT Image 2.6 Sunburst ≈$0.21 for a 1024×1024 image. GPT Image 2.6 Flare is billed per token, so its price is an estimate at high quality. GPT Image 2.6 Sunburst is billed per token, so its price is an estimate at high quality.
Can GPT Image 2.6 Flare and GPT Image 2.6 Sunburst edit images?
Not on ModelCompare: both only make new pictures from a prompt here.
How can I compare GPT Image 2.6 Flare and GPT Image 2.6 Sunburst myself?
Open the comparison, type one prompt and both models draw it side by side, each with what it cost and how long it took. You sign up with Google before your first run, and new accounts start with free credit.
Related comparisons
Where the numbers come from
Quality scores are Elo ratings from the Artificial Analysis image arenas, where people vote between two pictures made from the same prompt without knowing which model made which. The vote split comes from the Elo gap. Prices are for one 1024×1024 image from the Vercel AI Gateway; models billed per token are estimated at the quality the arena scored. The sample pictures are our own runs. Updated November 5, 2026.