Image model · OpenAI ·
GPT Image 2 is an image model by OpenAI. In Endless it costs from 1 credit per image and is available on every plan.
GPT Image 2 is OpenAI's image model for design work and on-image text, with edits that work across up to 4 images plus reference images.
GPT Image 2 is the model OpenAI launched in April 2026 alongside ChatGPT Images 2.0. It takes a text prompt and images as input and returns images, and it reads the images you give it at high fidelity, so faces, logos and product details carry over into the edit. You can generate from scratch or change an existing image by describing what should be different.
Teams use it for layout-heavy work: banners and slides with real copy, product mockups, packaging variations and quick fixes to existing creative. Because it edits up to 4 images in one request, you can restyle a small set of assets together and keep them consistent. In Endless it runs in chat and on the canvas.
GPT Image 2.5 is the newer OpenAI model in the Endless catalog, with a fast Flare variant and a higher-fidelity Sunburst variant. GPT Image 2 remains a fit when you need multi-image edits around on-image text.
by OpenAI
Fast everyday renders or slower, finer detail from up to 16 refs
From 1 credit per image
by Google
Hard briefs that need fine detail, accurate text and many references
From 20 credits per image
by Google
Design-ready images and edits that keep your subject consistent
From 9 credits per image
Start free, create a project, and bring your brand’s references together. Or book a demo to explore Endless with your team.