OpenAI has introduced ChatGPT Images 2.5, a new state-of-the-art image model that promises sharper details, more natural lighting, and better subject fidelity when editing reference photos. It also reduces latency by up to 50% compared with Images 2.0. In ChatGPT, new product features include Sketch for drawing in-app references and Templates for common formats like posters or merch, as well as improved multi-turn editing that keeps earlier changes consistent.

For developers, the Images API now offers two models: GPT-Image-2.5 Flare, the default suited for high-volume and rapid prototyping, and GPT-Image-2.5 Sunburst, built for premium workflows needing tighter control. Both are rolling out across ChatGPT tiers and the API today. OpenAI continues to apply safety checks, C2PA metadata, and invisible watermarking to help identify AI-generated images.