GPT Image 2

• 🆕 OpenAI's text-to-image and editing model, released April 2026.
• 👁️ Generates and edits images from text and image inputs.
• 🔧 Supports high input fidelity for image-based editing.
• 📏 Offers flexible output image sizes.
• 🏢 Available through the OpenAI API.
• 🎯 Newest entry in OpenAI's GPT Image family.
• 💬 Pairs with a dedicated edit endpoint variant.

OpenAI

OpenAI is an American artificial intelligence research organization headquartered in San Francisco, structured as both a for-profit public benefit corporation and a nonprofit foundation. The lab developed the GPT family of large language models, the DALL-E…

GPT Image 2 is OpenAI's image generation and editing model, available through the OpenAI API. It produces images from text prompts and accepts image inputs for editing, supporting flexible output sizes and high-fidelity image inputs. A companion editing-focused variant, GPT Image 2 Edit, handles inpainting-style tasks through the API's image edit endpoint.

It is the newest member of OpenAI's GPT Image family, following its same-family predecessor GPT Image 1.5. Both models share the same core text-to-image and image-editing workflow exposed through the OpenAI API, with GPT Image 2 documented as supporting high input fidelity for editing tasks.

GPT Image 2 sits within a broad April 2026 OpenAI lineup that also includes text models such as GPT-5.5 and GPT-5.5 Pro. No independent benchmark figures from top evaluators were available at the time of writing, so the description here reflects OpenAI's own API documentation.