With the launch of ChatGPT Images 2.0, OpenAI now “thinks” before it draws

OpenAI launched ChatGPT Images 2.0, or gpt-image-2, a new image model with built-in reasoning.

It offers Instant and Thinking modes, can use web search in reasoning flows, and improves consistency, dense text rendering, and multilingual support.

The model is available in ChatGPT, the API, and Codex, expanding image generation across OpenAI’s product stack.

The release comes as DALL-E 2 and DALL-E 3 are being retired and competition in AI image generation intensifies.