gpt-image-2.6-sunburst:official

Specifications and API

Creation Modes

Text-to-image generation; reference image editing

Output Formats

PNG, JPEG, WebP, GIF

Quality Options

auto, low, medium, high, xhigh, max

Select a Model

Flare focuses on fast generation and editing, while Sunburst focuses on refined composition and editing. Explicitly specify gpt-image-2.6-sunburst:official; do not use gpt-image-2.6 without a variant name.

Text-to-Image Generation

Submit a prompt through the image generation API, describing the subject, scene, lighting, color palette, and aspect ratio. You can first generate one image to check the composition, then adjust the quality and dimensions as needed.

Edit Reference Images

Submit image and prompt through the image editing API. JSON accepts image URLs, while multipart accepts local files; provide up to 16 reference images. Explain the role of each image and what should be preserved and changed.

Billing and Results

Billing is based on actual text input, reference image input, and image output Tokens, with the same rates as 2.5 official. Prices before a request are estimates; the final amount is based on usage records. By default, image links in data are read; when b64_json is selected, only one image is returned. For long-running tasks, pass async or callback_url, and use the original task_id to query the completed result.

Usage Limits

Use auto or WIDTHxHEIGHT for size. Width and height must be multiples of 16, the longest side must not exceed 3840, total pixels must be 655,360–8,294,400, and the aspect ratio must not exceed 3:1. n is 1–10, and b64_json requires n=1. Static PNG/JPEG/WebP supports 4K pixel presets. For native GIF, 512x512, 9 frames, and 200ms per frame are recommended; actual dimensions may be adjusted by the model. GIF cannot directly use the static 4K specifications. SVG is not currently supported. Version 2.6 does not configure cross-model fallback.

Frequently Asked Questions

Advanced Parameters

Supports complexity=low/medium/high and static image markup annotation editing. GIF supports 2–16 frames, each frame 20–655350ms (rounded to 10ms increments), with defaults of 9 frames and 200ms. The annotation image must be a PNG of the same dimensions as the first reference image and contain transparent pixels; it cannot be used together with mask or GIF.