GPT Image 2.6 Sunburst via the Tokenator API
What the model is for
GPT Image 2.6 Sunburst is OpenAI's image generation and editing model optimized for detail: dense compositions, text-heavy layouts, and edits that keep details consistent from one edit to the next at medium or high quality, generating about 50% faster than GPT Image 2.5. It takes text and image inputs and produces images, with quality tiers from low to max, transparent backgrounds, and custom sizes in multiples of 16 pixels at aspect ratios from 1:3 to 3:1. GPT Image 2.6 introduces a complexity setting for how much the model plans before rendering, markup-guided edits, animated GIF output, and SVG output. Choose Flare instead when speed matters more than fine detail.
Specification
| Full name | GPT Image 2.6 Sunburst |
| API ID | gpt-image-2.6-sunburst |
| Model vendor | OpenAI |
| Type | Image generation |
| Context window | — |
| Max output | — |
| Image input | yes |
| Tokenator usage multiplier | 1× |
| Badge | NEW |
| Input modalities | text, image |
| Supported API formats | /v1/images/generations |
| Current status | currently unavailable |
| Data updated | 2026-11-05 |
Example request
curl https://api.tokenator.top/v1/images/generations \ -H "Authorization: Bearer sk-your-tokenator-key" \ -H "Content-Type: application/json" \ -d '{ "model": "gpt-image-2.6-sunburst", "prompt": "an isometric illustration of a server rack", "n": 1 }'
See also
FAQ about GPT Image 2.6 Sunburst
What is the API ID of GPT Image 2.6 Sunburst?
gpt-image-2.6-sunburst — put this into the model field of your request.
What does a generation request look like?
POST to /v1/images/generations with model, prompt and optionally n and size. The format matches the OpenAI Images API — only the base URL and the key change.
How do I set the image size?
With the size field, for example 1024x1024. The available set depends on the model; 2048x2048 is not supported everywhere, and even there the result sometimes comes back smaller — check the actual image.
What does one image cost?
Generations are taken from the key's image quota: one picture — 1×, and with n images per request it is n × the multiplier. See the documentation for details.
Can I edit an existing image?
No — this model only generates images from a prompt.
What comes back in the response?
A data array where each item holds a link to the finished image in the url field. Download the picture and store it on your side — the link is not meant for permanent hosting.