AI Models
What each model is good at, where it differs from the others, and what it costs to run.
OpenAI's earlier GPT Image model. Text rendering and photoreal pictures, a medium or high quality choice, and edits of up to four pictures.
Credits come with a Generator plan. The exact cost is shown on the Generate button before anything is spent.
GPT Image 1.5 is OpenAI's earlier GPT Image model. Use it when you want its medium or high quality choice, or when an existing workflow already depends on this model.
OpenAI describes GPT Image 1.5 as image generation and editing, including text rendering, photoreal pictures, and edits from reference images. The quality choice is part of that model. Later GPT Image models do not offer it.
Write the picture in the prompt and choose medium or high quality. To edit or combine pictures, attach one to four of them and name them @image1, @image2, @image3, and @image4 in the prompt.
GPT Image 2 is the next model, aimed at layouts and instruction-following. GPT Image 2.5 Flare and GPT Image 2.5 Sunburst are the current pair: fast, or more precise. None of those three have the medium or high switch.
They are this model's quality choice. High asks for the more careful picture. The other GPT Image models on Visxy do not offer the switch.
Yes. One to four pictures, named @image1 onward.
OpenAI's current models are GPT Image 2 and the 2.5 pair. 1.5 remains the one with the quality choice.
OpenAI's own API lists a low setting. On Visxy the choice is medium or high.
