OpenAI GPT Image 2.6 Sunburst Image to Image API: AI Image Editor

Use GPT Image 2.6 Sunburst for image editing via API. 1K/2K/4K output, GIF support, pay per generation, no subscription. Edit or combine up to 16 reference images using GPT-Image-2.6 Sunburst, OpenAI's GPT Image 2.6 model for detailed visual work, with stronger consistency across edits at up to 4K.

Interactive model controls

Edit or combine up to 16 reference images using GPT-Image-2.6 Sunburst, OpenAI's GPT Image 2.6 model for detailed visual work, with stronger consistency across edits at up to 4K.

📝

Overview

About this model

GPT Image 2.6 Sunburst Image to Image is OpenAI's GPT Image 2.6 model for detailed visual work, with higher-quality generation and stronger consistency across edits. Edit or combine up to 16 reference images with a text instruction, keeping what should stay the same and changing only what you ask for. For faster iteration, see GPT Image 2.6 Flare Image to Image.

1Product edits: Swap colors, materials and backgrounds while preserving the product.

2Compositing: Combine up to 16 reference images in one scene.

3Brand work: Update packaging, signage and in-image text consistently.

4Retouching: Make precise, localized edits without regenerating the whole image.

💰

Pricing & Value

Cost analysis

Provider	Cost	Notes
muapiapp	$0.075 (1K) / $0.135 (2K) / $0.225 (4K) per edit with one input image; each extra input image adds $0.015	Priced by output resolution; no subscription required.

muapiapp$0.075 (1K) / $0.135 (2K) / $0.225 (4K) per edit with one input image; each extra input image adds $0.015

Priced by output resolution; no subscription required.

** Competitor pricing is estimated based on similar model architectures and usage tiers.

⚙️

Technical Details

Configuration schema

Parameter	Type	Description	Default
Prompt	string	Text instructions describing the desired transformation. Maximum 20,000 characters.	`Change only the beverage bottle in the center to a matte black can labeled "PEAK", keeping the exact same lighting, shadows, reflective surface, background props, and camera angle. Do not change anything else in the scene.`
Image URLs	array	Upload or provide input images to transform. Up to 16 images supported.	`https://d3adwkbyhxyrtq.cloudfront.net/webassets/videomodels/gpt-image-2-image-to-image-in.jpg`
Aspect Ratio	Enum (16 options)	Output aspect ratio. 'auto' lets the model choose the best frame.	`auto`
Resolution	Enum (3 options)	Output size tier. Higher tiers take longer and cost more.	`1K`
Background	Enum (3 options)	Background handling. Only applies at 1K resolution.	`auto`
Output Format	Enum (4 options)	Output image format. GIF costs the same as a still image.	`png`
Frame Count	Enum (7 options)	Number of GIF frames. Only used when output_format is gif.	`auto`
Frame Duration (ms)	integer	Duration of each GIF frame in ms (20-2000). Only used when output_format is gif.	`-`

Promptstring

Text instructions describing the desired transformation. Maximum 20,000 characters.

Default Value

Change only the beverage bottle in the center to a matte black can labeled "PEAK", keeping the exact same lighting, shadows, reflective surface, background props, and camera angle. Do not change anything else in the scene.

Image URLsarray

Upload or provide input images to transform. Up to 16 images supported.

Default Valuehttps://d3adwkbyhxyrtq.cloudfront.net/webassets/videomodels/gpt-image-2-image-to-image-in.jpg

Aspect RatioEnum (16 options)

Output aspect ratio. 'auto' lets the model choose the best frame.

Default Valueauto

ResolutionEnum (3 options)

Output size tier. Higher tiers take longer and cost more.

Default Value1K

BackgroundEnum (3 options)

Background handling. Only applies at 1K resolution.

Default Valueauto

Output FormatEnum (4 options)

Output image format. GIF costs the same as a still image.

Default Valuepng

Frame CountEnum (7 options)

Number of GIF frames. Only used when output_format is gif.

Default Valueauto

Frame Duration (ms)integer

Duration of each GIF frame in ms (20-2000). Only used when output_format is gif.

Default Value-

📖

Implementation Guide

Developer documentation

How to Use GPT Image 2.6 Sunburst Image to Image

Write your prompt — say what should stay the same and what should change; refer to images by order.
Call the endpoint and poll for the result:

curl -X POST https://api.muapi.ai/api/v1/gpt-image-2.6-sunburst-image-to-image \
  -H "x-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt": "Keep the shelf and lighting unchanged; make every mug matte black", "images_list": ["https://example.com/your-image.png"], "resolution": "2K"}'

Poll for the result using the returned request_id against /api/v1/predictions/{id}/result until status is completed.

❓

Common Questions

Frequently asked

What is GPT Image 2.6 Sunburst?

OpenAI's GPT Image 2.6 model for detailed visual work, with higher-quality generation and stronger consistency across edits.

How is GPT Image 2.6 priced on Muapi?

$0.075 (1K) / $0.135 (2K) / $0.225 (4K) per edit with one input image; each extra input image adds $0.015. PNG, JPEG and WebP add no surcharge.

Does GPT Image 2.6 Sunburst support animated GIFs?

Yes. Set `output_format` to `gif` and optionally `frame_count` and `frame_duration_ms`. GIF costs the same as a still image of that resolution.

Does background transparency work at every resolution?

`background` (transparent, opaque, auto) only applies at 1K; leave it out at 2K and 4K.