GPT Image 2.5 Sunburst Text-to-Image
GPT Image 2.5 Sunburst generates images from natural-language prompts with arbitrary resolutions up to 3840x2160, five quality tiers including xhigh and max, and first-class transparent backgrounds.
What it does
GPT Image 2.5 Sunburst Text-to-Image, in practice.
GPT Image 2.5 Sunburst is OpenAI's upgraded GPT Image generation model, reached through the OpenAI Images API. Generation is asynchronous: submit the request, then poll for the final image URL.
- Five quality tiers: `low`, `medium`, `high`, plus `xhigh` and `max`, which are new in gpt-image-2.5.
- Arbitrary resolutions: any `WIDTHxHEIGHT` up to 3840x2160, at any aspect ratio between 1:3 and 3:1.
- Transparent backgrounds: fully supported, not preview, on gpt-image-2.5.
- Long prompts: up to 32000 characters.
Product photo workspace
This page is a model reference. The workspace supports white backgrounds, scene changes, packaging text edits and model try-on using Qwen Image Edit.
Parameters
What you can set.
| Parameter | What it does | Options |
|---|---|---|
prompt | Text description of the desired image. Up to 32000 characters. | |
quality | Rendering quality tier. gpt-image-2.5 adds xhigh and max on top of low/medium/high. Higher tiers cost more per image. | auto low medium high xhigh max |
size | optional string or auto or 1024x1024 or 1536x1024 or 5 moreThe size ofthe generated images.For gpt-image-2.5 is supported as WIDTHxHEIGHT strings,for example 1536x864 . Width and height mustboth be divisible by 16 and the requested aspect r | auto 1024x768 768x1024 1024x1536 1536x1024 2048x2048 2048x1152 1152x2048 2560x1088 1088x2560 2880x2160 2160x2880 |
background | Background of the generated image. When using transparent, set the output format to png or webp. | auto opaque transparent |
output_format | Output image format. | png jpeg webp |
moderation | Content-moderation strictness. low applies less restrictive filtering. | auto low |
n | Number of images to generate, 1 to 10. Each image is billed separately. | default 1 |
Sample prompt
The prompt behind the sample.
Create a cinematic 24-shot storyboard sequence for a Japanese cyberpunk anime feature film. The story follows a young motorcycle rider and his companions through a vast futuristic megacity, escalating from an ordinary night ride into a mysterious supernatural crisis and an explosive confrontation. Maintain strict visual continuity across all 24 shots: same characters, same costumes, same motorcycles, same futuristic city, consistent architecture, lighting, proportions, and color palette. 1980s–1990s Japanese sci-fi animation aesthetic, hand-drawn cel animation feeling, detailed mechanical des
quality: mediumsize: 1024x1024background: autooutput_format: pngmoderation: auton: 1FAQ
Short answers.
How much does GPT Image 2.5 Sunburst Text-to-Image cost?
List price starts at $0.0045 per image at the base resolution; higher resolutions and longer durations cost more. Per-use pricing, no subscription. Model prices are reference prices. The prompt workspace is free during the period shown on the homepage; no automatic charges.
What content policy applies to GPT Image 2.5 Sunburst Text-to-Image?
OpenAI's standard content policy, plus this site's commercial-use rules: product, catalog and marketing work. Uploads are processed for your request only and are not used for training.
What does GPT Image 2.5 Sunburst Text-to-Image take as input?
It is a text-to-image model. GPT Image 2.5 Sunburst generates images from natural-language prompts with arbitrary resolutions up to 3840x2160, five quality tiers including xhigh and max, and first-class transparent backgrounds.
How do I use GPT Image 2.5 Sunburst Text-to-Image?
Prompt for composition first — subject, lens, light — then style. This is also the fastest way to make a first frame you can hand to an image-to-video model. Register or sign in to edit product photos with Qwen Image Edit. Other models on this page are catalog references.
Related