GPT Image 2.6 Flare
imageOpenAI's faster GPT Image 2.6 model. More frame sizes, a quality choice from Low through Max, and edits of up to four pictures.
Other versions
What it supports
- Aspect ratios
- auto, 1:1, 3:2, 2:3, 4:3, 3:4, 5:4, 4:5, 16:9, 9:16, 2:1, 1:2, 21:9, 9:21, 3:1, 1:3
- Resolutions
- 1K, 2K, 4K
- Quality
- low, medium, high, xhigh, max
- Per request
- up to 4
What it costs
- low · 1K
- 3 credits
- medium · 1K
- 6 credits
- high · 1K
- 7 credits
- xhigh · 1K
- 11 credits
- max · 1K
- 25 credits
- low · 2K
- 6 credits
- medium · 2K
- 11 credits
- high · 2K
- 13 credits
- xhigh · 2K
- 22 credits
- max · 2K
- 50 credits
- low · 4K
- 10 credits
- medium · 4K
- 17 credits
- high · 4K
- 20 credits
- xhigh · 4K
- 35 credits
- max · 4K
- 79 credits
Credits come with a Generator plan. The exact cost is shown on the Generate button before anything is spent.
GPT Image 2.6 Flare is OpenAI's faster GPT Image 2.6 model. kie describes it as the one for faster iteration, with more sizes than Economy.
What it is good at
Trying a picture or an edit quickly, at 1K, 2K, or 4K, with a quality you choose. OpenAI's 2.6 prompting guide shows Flare and Sunburst as the two tiers that can combine reference pictures.
How to use it on Visxy
Write the picture in the prompt. Pick a frame, a resolution (1K, 2K, or 4K), and a quality: Low, Medium, High, xhigh, or max.
To edit or combine pictures, attach one to four of them and name them image 1, image 2, image 3, and image 4 in the prompt.
Where it differs
GPT Image 2.6 Sunburst is the tier kie describes for more detail and tighter consistency across edits. GPT Image 2.6 Economy is 1K only, with no quality switch. GPT Image 2.5 Flare is the previous generation.
FAQ
Should I start on Flare?
Flare is the fast 2.6 model. Move to Sunburst when the edit has to hold more detail. Economy is the 1K model without a quality choice.
Can I edit several pictures?
Yes. One to four, named image 1 onward.
Is there a quality switch?
Yes. Low, Medium, High, xhigh, and max. The price follows the resolution and the quality.
Is this a video model?
No. It makes still pictures.
Official sources
More image models
All image modelsSeedream 5.5
ByteDance's Seedream 5.5. A still at 1K, 1.5K, or 2K, or an edit of up to four pictures. The edit's price follows the size and how many pictures you attach.
Seedream 5 Pro
ByteDance's Seedream model for designed pictures: dense layouts, readable type, and realistic materials. Attach up to four pictures and name them.
Flux 2 Pro
Black Forest Labs' production FLUX.2 stills model. Photoreal product, material, and light, or an edit of up to four pictures you name.
Qwen Image 3 Pro
Alibaba's Qwen Image 3 Pro. The Pro model beside Qwen Image 3: a dense picture from a prompt, or an edit of one picture.
Seedream 5 Flash
ByteDance's fast Seedream 5 image model. A picture from a prompt, or an edit of one to four pictures, without @ tags.
Qwen Image 3
Alibaba's Qwen Image 3. A dense picture from a prompt, or an edit of one picture. Enhance expands the prompt only if you turn it on.