GPT-Image-2.6 Sunburst
Create detailed images and reference-based edits through an API with independent planning controls and vector output.
GPT-Image-2.6 Flare
developers.openai.com
Generate and edit images through OpenAI’s API with controls for visual complexity, guided edits and vector graphics.
Visit website
Pricing
Paid
Available on
API
Category
Ai Image Tools
What is GPT-Image-2.6 Flare?
GPT-Image-2.6 Flare is an OpenAI API model that creates and edits images from text and image inputs. It serves developers building visual tools where users generate a concept and then request changes to an existing image.
OpenAI positions Flare as the smaller option for workflows that prioritize response time. Developers can adjust planning complexity independently of rendering quality and choose output settings for their application.
Key features
Text and reference-image workflows
Generate images from descriptions or supply existing images for editing.
Separate planning and quality controls
Choose low, medium or high planning complexity independently of rendering quality.
Markup-guided edits
Guide changes with a transparent PNG overlay matching the first input image’s dimensions.
Vector output
Generate static SVG graphics for vector asset workflows.
Animated GIF preview
With access to the model’s GIF preview, create short animations with configurable frame count and timing.
Who is it for?
Designers exploring concepts
Compare visual directions before choosing a concept for further development.
Retail teams preparing image variations
Explore proposed changes to product imagery and review the results before use.
Developers building asset tools
Offer users image generation and editing inside a creative application.
How to use GPT-Image-2.6 Flare
- Create an OpenAI API key and configure an SDK or HTTP client. Organization verification may be required before using GPT Image models.
- Select gpt-image-2.6-flare in an image-generation or editing request.
- Provide a description and any reference images, then choose complexity, quality and output format.
- Inspect the returned asset and refine the request as needed.
GPT-Image-2.6 Flare pricing
Paid
Usage-based API pricing charges for text and image tokens. Consult OpenAI’s pricing page for current rates.
Check current pricing ↗What to know before you use it
- SVG generation returns one output and does not support image edits or streaming.
- GIF output requires access to the selected model’s GIF preview. It supports 2–16 frames within size limits and does not support streaming.
- Complex prompts can take up to two minutes. Exact lettering, placement and recurring visual consistency can require corrections.
- Organization verification may be required before accessing GPT Image models.
Frequently asked questions
Can Flare produce transparent images?
Yes. Transparent raster output supports PNG and WebP.
Does complexity change rendering quality?
Complexity controls computation spent planning the image. Rendering quality is a separate setting.
GPT-Image-2.6 Flare alternatives
GPT-Image-2.6 Sunburst
OpenAI positions Sunburst for workflows where demanding detail, layout or edit accuracy takes priority.