Robots Atlas>ROBOTS ATLAS
GPT-Image-2.5 Sunburst
AI Models›GPT

GPT-Image-2.5 Sunburst

gpt-image-2.5/sunburst · Family: GPT
Sunburst variant of OpenAI's GPT Image 2.5 image generation and editing model, tuned for higher detail at the cost of longer generation time. Available via API as gpt-image-2.5/sunburst.
✓ Active✓ Public accessImage generationReasoning modelMultimodal📁 GPT
Release date
8 September 2026
🏢OpenAIProducer
Access:APIHostedDeployment:☁ Cloud

Overview

GPT-Image-2.5 Sunburst is one of two API variants of GPT Image 2.5, released by OpenAI on September 8, 2026. The Sunburst variant (gpt-image-2.5/sunburst) is tuned for higher image detail at the cost of longer generation time, while the other variant, Flare (gpt-image-2.5/flare), prioritises speed while retaining some quality.

Version 2.5 introduced a Sketch feature that turns hand-drawn sketches into AI-generated images and reduced generation latency by about 50% compared with the previous version. GPT Image models are autoregressive (unlike the diffusion-based DALL-E 2 and DALL-E 3), support image-to-image transformation, photorealism and precise instruction following, and generate images at 1024×1024, 1536×1024 and 1024×1536 pixels.

The model is the successor to the DALL-E line, is natively integrated into ChatGPT as “ChatGPT Images” and is available through the OpenAI API.

Classification
Image generationReasoning modelMultimodal
Family: GPT
Applications
Content generation
Access & deployment
APIHosted
Cloud
Weights: Closed
Key parameters
📥 Input: text, image
Platforms
OpenAI API

Technical specification

License
Proprietary / Commercial
Hardware requirements
Not applicable — available exclusively via the OpenAI API and ChatGPT (closed cloud). Self-hosting and weight downloads are not supported.
Modalities
⬇ Input
textimage
⬆ Output
image

Capabilities and applications

Native model capabilities
Text-to-image generation
A model's ability to create images from a text description (prompt), including control of style, composition, aspect ratio and rendering text within the image.
Category: vision
Image editing
Modifying an existing image based on a text instruction or direct annotations: removing objects, changing style, adding elements, filling in regions (inpainting/outpainting), while preserving the identity of people and scene coherence.
Category: vision
Reasoning-augmented image generation
Multi-step generation: the model first analyses the prompt (planning layout, looking up web context, choosing references) and only then produces the image. This lets it accurately reflect complex, ambiguous instructions.
Category: reasoning
Text rendering in images
Generating images containing legible, correctly spelled text — infographics, posters, menu cards, QR codes, captions in a specific graphic style. A key capability that separates new-generation models from early image generators.
Category: vision
Image understanding
Analysing and interpreting the content of images.
Category: vision
Multi-image blending
Intelligently combining several input images into one coherent composition — e.g. placing a person from one photo into a scene from another, composing characters from different sources, or building collages that preserve style.
Category: vision
Application domains
Content generation

Technical architecture

Deployment and security

☁ Available on platforms
☁OpenAI APIPlatform

Sources and related pages