OpenAI: GPT Image 2.5 Sunburst

GPT Image 2.5 Sunburst puts emphasis on image quality and editing precision. Consider it for detailed revisions where the relationship between the reference image, the requested change, and the final composition needs close attention.

Compare models

gpt-image-2.5-sunburst

AvailableOpenAIImageSync / AsyncCached input 75% less

Input / Output-30%: $5.00 / $30.00$3.50 / $21.00
Modalities: Image

About GPT Image 2.5 Sunburst

GPT Image 2.5 Sunburst is the precision model of OpenAI's GPT Image 2.5 pair, built for premium visual workflows that need tighter control across edits. It generates and edits images from text and reference images, and OpenAI suggests it for campaign creative and polished product imagery. Expect slower renders than Flare in return for closer adherence to the requested change.

Where it works well

Built for tighter control across successive edits, according to OpenAI.
Aimed at production-ready campaign creative and polished product imagery.
Keeps the relationship between reference image, requested change, and final composition in view during revisions.
Shares the 2.5 improvements in lighting, texture, and subject preservation with Flare.

When to choose another model

Renders take longer than Flare's, so it is a poor fit for rapid draft exploration.
It makes images only; no text answers or copy come back.

Getting started

Create API key
Create a key in Console, then use it with every model on the platform.

Send your first request

Copy the example for your language and run it against the endpoint.

Image editingText to imageTokenLab endpoint

POST/v1/images/generations

curl -X POST "https://api.tokenlab.sh/v1/images/generations" \
  -H "Authorization: Bearer sk-xxx" \
  -H "Content-Type: application/json" \
  -d '{
  "operation": "text-to-image",
  "quality": "auto",
  "size": "auto",
  "model": "gpt-image-2.5-sunburst",
  "prompt": "A minimalist product photo of matte black headphones on a soft blue background."
}'

Pricing

The Verified price applies to Verified, which costs less on most models. The Official price is the model maker's published price and applies to the more reliable Official route. Auto bills the route that completes the request.

Text to image / Image editing · Image

per 1M tokens

Official price: Input $5.00 / Output $30.00 / Text Input $5.00 / Text Input · Cache read $1.25 / Image Input $8.00 / Image Input · Cache read $2.00 / Image Output $30.00
Verified price: Input $3.50 / Output $21.00 / Text Input $3.50 / Text Input · Cache read $0.875 / Image Input $5.60 / Image Input · Cache read $1.40 / Image Output $21.00
Discount: -30%

Default spec

per 1M tokens

Official price: Cache read $1.25
Verified price: Cache read $0.875
Discount: -30%

Prompt cache pricing

Cache read

Official price: $1.25
Verified price: $0.875
Discount: -30%

	Official priceper 1M tokens	Verified priceper 1M tokens	Discount
Text to image / Image editing · Image	Input $5.00 / Output $30.00 / Text Input $5.00 / Text Input · Cache read $1.25 / Image Input $8.00 / Image Input · Cache read $2.00 / Image Output $30.00	Input $3.50 / Output $21.00 / Text Input $3.50 / Text Input · Cache read $0.875 / Image Input $5.60 / Image Input · Cache read $1.40 / Image Output $21.00	-30%
Default spec	Cache read $1.25	Cache read $0.875	-30%
Prompt cache pricing
Cache read	$1.25	$0.875	-30%

Usage & activity

Success rate is the share of requests that completed. Latency is how long a full response takes; P95 means 95% of requests finished within that time.

Usage & availability

Last 24 hours

Requests
Success rate
P95 latency
Total tokens

Model performance

Last updated Oct 12, 2026, 09:17 PM UTC

30-day success rate: 98.9%
30-day requests: 100+
Last active: 16 hours ago

Data is based on aggregate user requests, excluding status checks.

Open in Console

Open GPT Image 2.5 Sunburst in Console with a prompt ready to edit or send.

Help me create an image with gpt-image-2.5-sunburst using text-to-image at /v1/images/generations. Show the result, cost, and any limits I should know.

Use cases

Best for

Text to Image

Campaign creative
Produce final hero images for an ad set, with controlled revisions requested by an art director.
Product imagery
Refine packshots and lifestyle scenes where logo, label, and shape must stay accurate.
Detailed revisions
Apply a specific change to an image, such as swapping a garment, without disturbing the rest.
Final renders
Re-run a prompt that worked in Flare to get the version you will publish.

Prompt examples

Change the model's jacket to deep green leather, keep face, pose, and lighting unchanged.

Product shot of a matte black water bottle on wet slate with a soft rim light, label sharp and legible.

Extend the background of this banner to the right and keep the brand text exactly where it is.

This model has conditional pricing. Monthly token totals alone cannot produce a reliable estimate; use the detailed pricing for the request specification, cache, and applicable time window.

FAQ

What is GPT Image 2.5 Sunburst?

It is the precision-oriented model in OpenAI's GPT Image 2.5 pair, meant for premium creative and editing workflows where each revision has to follow the written instruction closely.

When should I use Sunburst instead of Flare?

Use Sunburst for final, production-grade images where each edit must land exactly. Use Flare for exploration, drafts, and everyday work where speed counts more than fine control over revisions.

Does Sunburst edit existing images?

Yes. It generates and edits images from text and reference images, so you can supply an existing image with a written instruction for the change, such as swapping a garment while the rest of the composition stays put.

Is Sunburst slower than Flare?

It is positioned for quality and control rather than speed, and takes longer to generate. OpenAI cites a 50 percent latency cut for Flare against gpt-image-2.

What can Sunburst output?

Images, delivered through the image generation and image edit endpoints. It does not produce text replies, video, or audio, so pair it with a chat model if you need copy.

How much does GPT Image 2.5 Sunburst cost?

On TokenLab, GPT Image 2.5 Sunburst costs Input $3.50 / Output $21.00 per 1M tokens. The pricing table above shows the full breakdown. Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.

Which endpoint should GPT Image 2.5 Sunburst use?

Use https://api.tokenlab.sh/v1/images/generations for GPT Image 2.5 Sunburst. The request example below shows the matching code shape.

Which operations does GPT Image 2.5 Sunburst support?

GPT Image 2.5 Sunburst supports Image editing, Text to image. Select an operation above to see its endpoint and request example.