SparkleTripImagination, made real.Credits & billing
All guides
Image model guides

GPT Image 2.6: how to choose the 2.6 variants

GPT Image 2.6 variants are available in Sparkles Editor, with gpt-image-2.6-sunburst as the system default. The current 2.6 entries are gpt-image-2.6-sunburst and gpt-image-2.6-flare. They share the same image-generation entry point. You can choose another fixed model or enable automatic routing, which prioritizes the 2.5 family.

Learn how gpt-image-2.6-sunburst and gpt-image-2.6-flare are used in SparkleTrip, then choose automatic routing or a fixed model for your next image.
View full-size image
A reusable scene illustration for the GPT Image 2.6 guide. It shows a visual direction, not a provider benchmark or a promise that every prompt will produce the same result.

1. What is in the GPT Image 2.6 family?

The current catalog exposes two GPT Image 2.6 variants. gpt-image-2.6-sunburst is the preferred 2.6 choice for a person, several references, a detailed scene or visual continuity. gpt-image-2.6-flare is the preferred 2.6 choice for posters, packaging, menus, diagrams and dense in-image text. New requests default to gpt-image-2.6-sunburst; optional automatic routing prioritizes the 2.5 variants and falls back to 2.6 when the task or live catalog calls for it. These are Sparkles routing roles based on current observations, not a guarantee for every prompt.

2. Use the model roles as a decision aid

Start with the goal rather than the model name.

If the request is mainly… Start with… Why
One subject, a clean scene or a quick exploration gpt-image-2.5-sunburst A balanced general-purpose choice
A person, product identity, several references or a complex relationship between objects gpt-image-2.6-sunburst A useful starting point for continuity and detail
A poster, label, menu, infographic or information-heavy layout gpt-image-2.6-flare A useful starting point when lettering and hierarchy matter

The automatic mode uses these signals and falls back to an available catalog model. If the first result is not stable enough, switch to a fixed model and repeat the same request so you can compare like with like.

3. Parameters that are available today

Sparkles exposes the image controls that are currently validated by the production catalog: low, medium, high and auto quality; aspect-ratio choices; auto, opaque or transparent backgrounds; and PNG, JPEG, WebP or (for eligible 2.6 requests) GIF output. Native GIF availability still depends on the upstream channel entitlement. You can attach reference images, ask for a particular number of images and keep a series of related results in one workflow. Mention the words that must appear in the picture, then inspect them at full size. These controls describe the current product contract and may change when the catalog changes.

4. Automatic or fixed?

Choose automatic when you want the assistant to route a changing task while keeping the stable 2.5 family first. Choose a fixed model when you are testing a prompt, comparing revisions, building a series or need to reproduce a known direction. The selected preference applies to new work. A submitted task keeps the model and parameters that were frozen when it started.

5. References and text still need a check

A reference image supplies visual evidence; it does not make every detail exact. Say which reference controls identity, which one only supplies atmosphere and what may change. For packaging, logos, ingredients, dates and small type, compare the output with approved artwork or a source document. Transparent output is useful for compositing, but preview it against both light and dark backgrounds to find unwanted edges. Keep important facts as editable text in the final layout when the image will be published.

6. Quality, cost and current limits

Image generation uses Credits and the final charge depends on the selected model, quality, dimensions and references. The pricing page is the current source of truth; there is no single flat per-image promise. The 2.6 catalog currently exposes low, medium, high and auto. Do not select older xhigh or max values for these models unless the catalog explicitly adds them. A successful provider request is evidence that the route works, not a guarantee of a particular visual result.

7. A safe first request

Try a small request before a long series:

text
Create one 4:5 image of [subject] for [purpose]. Preserve [identity details] from my reference. Use [model preference: automatic / gpt-image-2.5-sunburst / gpt-image-2.6-sunburst / gpt-image-2.6-flare], medium quality and a transparent background only if the edges will be composited. Keep [exact words] short and legible. Tell me what needs checking before I use the result.

Review the subject, text, edges and composition at full size. Then keep the model fixed while you revise one issue at a time.

Sources and further reading

Try it with the assistant

A starter message is filled in for you to edit and send. Chat is billed by usage; clear image requests generate directly and use Credits.