OpenAI's top image quality
OpenAI calls Sunburst its most capable image model, with higher image quality than GPT Image 2.
GPT Image 2.5 Sunburst API: OpenAI's most capable image model, $0.02 per image.
gpt-image-2.5-sunburstfrom openai import OpenAIclient = OpenAI( base_url="https://api.zurelay.com/v1", api_key="YOUR_ZURELAY_KEY",)image = client.images.generate( model="gpt-image-2.5-sunburst", prompt="A red fox sitting in fresh snow at dawn, photo", size="1536x1024", quality="high",)print(image.data[0].url)Base URL https://api.zurelay.com/v1. Works with any OpenAI SDK.
Examples
Every image here is a single API call with the prompt underneath it, not retouched or upscaled. They're shown as compressed WebP; the API returns full-quality PNG.
Pricing
Pay as you go from prepaid credit, with no subscription and no minimum. Requests that fail are never billed.
| Rate | zurelay | OpenAI list | You save |
|---|---|---|---|
1K image 1024 × 1024, any quality | $0.02 | 62%off | |
2K image 2048 × 2048, any quality | $0.02 | ≈ | 91%off |
4K image 3840 × 2160, any quality | $0.02 | ≈ | 95%off |
One price at every size, always high quality. OpenAI bills images by output tokens, which grow with the image's area, so its 2K and 4K prices (≈) are worked out from its 1024 × 1024 price.
Move the sliders to your monthly usage.
$392.40 a year
Overview
GPT Image 2.5 Sunburst is OpenAI's most capable image model, tuned for quality and precision and released on September 8, 2026. The GPT Image 2.5 Sunburst API on zurelay turns a text prompt into detailed images through one OpenAI-compatible endpoint. Every image is made at high quality, at one flat price for any size up to 4K.
GPT Image 2.5 Sunburst is the quality-first of the two image models OpenAI released on September 8, 2026. OpenAI calls it its most capable model for image generation and editing, and describes it as the base model, optimized for quality, with higher image quality than GPT Image 2. It spends longer per image than GPT Image 2.5 Flare, the faster default. The GPT Image 2.5 Sunburst API on zurelay uses the model ID gpt-image-2.5-sunburst.
OpenAI says the GPT Image 2.5 models bring sharper detail, more natural lighting, richer textures and better handling of complex layouts, with Sunburst as the one built for precision. OpenAI points to production-ready campaign creative and polished product imagery as its main uses. OpenAI also built it for precise editing, but zurelay offers Sunburst for text-to-image generation only.
Sunburst takes the same settings as Flare. The recommended sizes are 1024x1024, 1536x1024 and 1024x1536, and custom sizes work when both edges are multiples of 16, the ratio is between 1:3 and 3:1 and no edge passes 3840 pixels. OpenAI treats anything above 2560x1440 as experimental. On zurelay, every image is made at high quality. OpenAI notes that a higher setting does not guarantee a better result for every prompt, and suggests comparing medium and high for small text, dense information or multiple fonts.
OpenAI charges Sunburst and Flare the same token rates, so on OpenAI an image's cost depends on its size and quality. Higher quality and larger sizes add output tokens, and those are the settings Sunburst is chosen for. zurelay makes every image at high quality and charges one flat price at every size, so a 4K image costs the same as a square. Send requests to POST https://api.zurelay.com/v1/images/generations in the OpenAI images format and get a URL back by default, or base64 with response_format set to b64_json.
Strengths
OpenAI calls Sunburst its most capable image model, with higher image quality than GPT Image 2.
Sunburst spends more time per image to hold fine detail. That suits product shots and layouts where small flaws show.
On zurelay, a 3840x2160 image costs the same flat price as a square one, and every image is made at high quality.
Render up to 3840 pixels on the long edge, with sizes above 2560x1440 marked experimental by OpenAI.
Use cases
Ad visuals and key art headed for production, where lighting and texture need to hold up.
Polished product shots and lifestyle scenes for stores, catalogs and launch pages.
Graphics with text in the image, made at high quality. Check spelling before you publish.
Wide banners, website heroes and 4K wallpapers using custom sizes up to 3840 pixels on the long edge.
Get started
No waitlist and no new SDK. If your code already talks to OpenAI, it already talks to zurelay.
Sign up, add credit and create an API key. Set a monthly budget or a rate limit per key if you like.
Change the base URL. Everything else in your code stays the same.
https://api.zurelay.com/v1Send a prompt to /v1/images/generations with a size and aspect ratio, and get back a link to your image.
gpt-image-2.5-sunburstWorks with the tools you already use
Compare
$0.02 per image
Pick Flare for faster results in apps and high-volume jobs; OpenAI makes it the default for most applications.
GPT Image 2.5 Flare APIfrom $0.035 per image
Pick Nano Banana Pro to compare Google's image model, with fixed 1K, 2K and 4K outputs and a focus on legible text.
Nano Banana Pro API$2.50 / $12.50 per 1M tokens
Use GPT-6 Astra to write detailed image prompts or review finished images; it reads images but does not create them.
GPT-6 Astra APIFAQ
Anything else, write to sales@zurelay.com and an engineer will answer.
zurelay charges $0.02 per image for gpt-image-2.5-sunburst at every size, and every image is made at high quality. OpenAI bills by tokens, and its cost for a 1024x1024 image at high quality is about $0.0527, so you save 62%. At larger sizes OpenAI's cost goes up while zurelay's stays the same.
Yes. zurelay serves Sunburst at a flat $0.02 per image, 62% below OpenAI's approximate cost for a 1024x1024 high-quality image. The saving grows at larger sizes, since zurelay's price does not change with size.
Point the OpenAI SDK at https://api.zurelay.com/v1 with your zurelay API key and call images.generate with model set to gpt-image-2.5-sunburst. Pass a prompt and a size, plus background, output_format or n (1 to 4) if you need them. You get image URLs by default, or base64 with response_format set to b64_json.
The recommended sizes are 1024x1024, 1536x1024 and 1024x1536. Custom sizes work when both edges are multiples of 16, the ratio is between 1:3 and 3:1, no edge passes 3840 pixels and the total is between 655,360 and 8,294,400 pixels. OpenAI treats sizes above 2560x1440 as experimental. On zurelay every image is made at high quality, whatever quality you pass, and a 1024x1024 square comes back at 1254x1254.
OpenAI tunes Sunburst for image quality and precision, and Flare for speed. Sunburst takes longer per image, while Flare is OpenAI's default for most applications. Both take the same sizes and cost the same flat $0.02 per image on zurelay.
It can render text in images, and OpenAI suggests medium or high quality for small text, dense information or multiple fonts. Put exact wording in quotes, say where it goes, and spell unusual words letter by letter if needed. OpenAI notes precise text placement can still slip, so check spelling before you publish.
Images are stored for 30 days behind the URL in the response. Download any image you want to keep before then. If you request b64_json, the image data comes back in the response itself.
Yes. zurelay runs the same gpt-image-2.5-sunburst model and accepts requests in the OpenAI images format. Image generation varies from run to run, so the same prompt will not return byte-identical images. zurelay is an independent service and is not affiliated with OpenAI.
No. OpenAI built Sunburst with editing precision in mind, but zurelay offers text-to-image generation only. Image edits, inpainting and reference-image inputs are not available.
Create a key in seconds, point the SDK you already use at zurelay, and every request costs up to 85% less from the first token.