Robots Atlas>ROBOTS ATLAS
GPT-Image-2
AI Models

GPT-Image-2

gpt-image-2
OpenAI's GPT Image-series image generation model, released April 2026; the first to add a reasoning model to generation. Autoregressive, integrated into ChatGPT and available via the API.
✓ Active✓ Public accessImage generationReasoning modelMultimodal
🏢OpenAIProducer
Access:APIHostedDeployment:☁ Cloud

Overview

GPT-Image-2 (gpt-image-2) is an image generation model developed by OpenAI, released in April 2026 as a further version of the GPT Image family. Its key novelty was introducing a reasoning model into the image generation process.

Like the other GPT Image models, it is autoregressive (unlike the diffusion-based DALL-E 2 and DALL-E 3), supports image-to-image transformation, photorealism and precise instruction following, and generates images at 1024×1024, 1536×1024 and 1024×1536 pixels.

The model is the successor to the DALL-E line, natively integrated into ChatGPT as “ChatGPT Images” and available through the OpenAI API (as well as in Microsoft Copilot and Apple Intelligence). It was superseded by GPT Image 2.5 in September 2026.

Classification
Image generationReasoning modelMultimodal
Access & deployment
APIHosted
Cloud
Weights: Closed
Key parameters
📥 Input: text, image

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

Technical architecture

Sources and related pages