OpenAI: GPT Image 2.6 Sunburst

GPT Image 2.6 Sunburst is the detail-focused model in OpenAI's 2.6 image generation. Use it for detailed compositions and for edits where the result must stay close to the reference image and follow the requested change precisely.

Compare models

gpt-image-2.6-sunburst

AvailableOpenAIImageSync / AsyncCached input 75% less

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

About GPT Image 2.6 Sunburst

GPT Image 2.6 Sunburst is OpenAI's detail-focused image model in the 2.6 generation, listed for detailed visual work. It creates images from text and edits images you supply, and OpenAI suits it to detailed compositions and edits. Use it when the result must stay close to the reference and follow the requested change precisely. For fast drafts and variations, GPT Image 2.6 Flare is the quicker choice.

Where it works well

OpenAI positions it as the 2.6 model for detailed visual work, which fits scenes with many elements and careful composition.
It is suited to edits where the result stays close to the supplied reference image and applies the requested change precisely.
Text-to-image generation and image editing come in one model, so a scene and its revisions stay together.
It is offered through the same image generation and image edit endpoints as Flare.

When to choose another model

OpenAI names Flare, not Sunburst, as the 2.6 model for fast iteration, so start drafts and large batches of variations there.
Complexity control, markup-guided edits, and SVG or GIF output, which OpenAI documents for the 2.6 models, cannot be used here yet.
Images are the only output; descriptions, captions, or copy need a chat model.

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-2.6-sunburst",
  "prompt": "A minimalist product photo of matte black headphones on a soft blue background."
}'

Parameters

Image editing

Parameter	Values and limits	Default	Notes
`async`	Not provided	Not provided	Not provided
`background`	Not provided	Not provided	Not provided
`compression`	Not provided	Not provided	Not provided
`file_id`	Not provided	Not provided	Not provided
`image`	Inputs: ≥ 1, ≤ 16	Not provided	Use at least one and at most 16 source images in total across URL, upload and file references. A mask applies to the first image.
`image_url`	Inputs: ≥ 1, ≤ 1	Not provided	Not provided
`image_urls`	Inputs: ≥ 1, ≤ 16	Not provided	Not provided
`images`	Inputs: ≥ 1, ≤ 16	Not provided	Not provided
`mask`	Not provided	Not provided	Not provided
`moderation`	Not provided	Not provided	Not provided
`n`	Not provided	`1`	Defaults to one output image. The model-specific maximum is not yet verified for this public operation.
`operation`	Not provided	Not provided	Not provided
`output_compression`	Not provided	Not provided	Not provided
`output_format`	png, jpeg, webp	Not provided	Not provided
`prompt`	Not provided	Not provided	Not provided
`quality`	Not provided	Not provided	standard maps to medium and hd maps to high. The complete model-specific quality list and the platform default are not yet verified for this operation.
`response_format`	Not provided	Not provided	The public image response selector accepts url or b64_json. A URL-only supply rejects b64_json before upstream execution. Omit this field to keep the selected supply response representation; no uniform omitted-field default is declared here.
`size`	Not provided	Not provided	Size accepts `auto` or WIDTHxHEIGHT. Custom dimensions must both be multiples of 16, max edge <= 3840px, long/short ratio <= 3:1, and total pixels between 655,360 and 8,294,400.
`user`	Not provided	Not provided	Not provided

GPT Image 2 accepts `background=auto` or `background=opaque`; transparent backgrounds are not supported by the model.

Image edits accept multipart image uploads, JSON image_url, JSON image_urls, or a JSON images array with image_url/file_id references. Create file IDs through TokenLab /v1/files. Up to 16 source images are supported; a supplied mask applies to the first image.

Text to image

Parameter	Values and limits	Default	Notes
`async`	Not provided	Not provided	Not provided
`background`	Not provided	Not provided	Not provided
`compression`	Not provided	Not provided	Not provided
`moderation`	Not provided	Not provided	Not provided
`n`	Not provided	`1`	Defaults to one output image. The model-specific maximum is not yet verified for this public operation.
`operation`	Not provided	Not provided	Not provided
`output_compression`	Not provided	Not provided	Not provided
`output_format`	png, jpeg, webp	Not provided	Not provided
`prompt`	Not provided	Not provided	Not provided
`quality`	Not provided	Not provided	standard maps to medium and hd maps to high. The complete model-specific quality list and the platform default are not yet verified for this operation.
`response_format`	Not provided	Not provided	The public image response selector accepts url or b64_json. A URL-only supply rejects b64_json before upstream execution. Omit this field to keep the selected supply response representation; no uniform omitted-field default is declared here.
`size`	Not provided	Not provided	Size accepts `auto` or WIDTHxHEIGHT. Custom dimensions must both be multiples of 16, max edge <= 3840px, long/short ratio <= 3:1, and total pixels between 655,360 and 8,294,400.
`user`	Not provided	Not provided	Not provided

Use response_format to select URL or base64 image output from TokenLab.

GPT Image 2 accepts `background=auto` or `background=opaque`; transparent backgrounds are not supported by the model.

Size accepts `auto` or WIDTHxHEIGHT. Custom dimensions must both be multiples of 16, max edge <= 3840px, long/short ratio <= 3:1, and total pixels between 655,360 and 8,294,400.

Use response_format to select URL or base64 image output from TokenLab.

Image streaming and partial-image delivery are not supported. TokenLab rejects stream=true, partial_images, and input_fidelity.

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 Nov 5, 2026, 11:26 PM UTC

Metrics appear once privacy and data volume thresholds are met.

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

Open in Console

Open GPT Image 2.6 Sunburst in Console with a prompt ready to edit or send.

Help me create an image with gpt-image-2.6-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

Detailed scene composition
Build an illustration or concept image with many specified elements, such as a crowded market or an interior full of described props.
Reference-faithful edits
Change one element of a supplied image, such as a garment color or a background object, while the rest stays consistent with the original.
Refining a chosen draft
Take a direction picked in a faster pass and rerun it with added detail instructions to get a more finished image.
Multi-change edit requests
Apply several specific changes to one image in a single request, such as a different sky and an added lamp.

Prompt examples

A detailed cutaway illustration of a lighthouse showing every floor, the winding staircase, the lamp room at the top, and the sea at its base.

In the attached photo, replace the red sofa with a green velvet one and leave the room, the lighting, and the people unchanged.

Change the season in this street photo to autumn, with orange leaves on the trees, and keep the buildings, cars, and people exactly as they are.

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 2.6 Sunburst?

OpenAI's model for detailed visual work in the 2.6 image generation. It creates images from text and edits images you supply, and it suits detailed compositions and edits.

When should I choose Sunburst instead of Flare?

Choose Sunburst when a composition has many details, or when an edit must stay close to the reference image and follow your instruction precisely. Choose Flare for quick drafts and variations, where speed of iteration matters more.

Does Sunburst edit existing images?

Yes. Supply an image and describe the change you want through the image edit endpoint, and the model returns the edited result. Without a reference image, use the image generation endpoint with a text prompt.

Can I use SVG output or markup-guided edits?

Not yet. OpenAI documents complexity control, markup-guided edits, and SVG and GIF output for the 2.6 models, but those options are not exposed here. Text-to-image generation and image editing are what you can use today.

What does Sunburst return?

Finished images, delivered through the image generation and image edit endpoints. It does not return text replies, audio, or video, so use a chat model for captions, descriptions, or copy.

How much does GPT Image 2.6 Sunburst cost?

On TokenLab, GPT Image 2.6 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 2.6 Sunburst use?

Use https://api.tokenlab.sh/v1/images/generations for GPT Image 2.6 Sunburst. The request example below shows the matching code shape.

Which operations does GPT Image 2.6 Sunburst support?

GPT Image 2.6 Sunburst supports Image editing, Text to image. Select an operation above to see its endpoint and request example.