📰 Full Story
OpenAI on April 21, 2026 rolled out ChatGPT Images 2 (also called Images 2.0/gpt-image-2), a major upgrade to its image-generation suite that integrates ‘thinking’ or reasoning capabilities with image synthesis.
The model can generate up to eight consistent images from a single prompt, render dense, legible text (including non‑Latin scripts such as Japanese, Chinese, Hindi and Bengali), and produce varied aspect ratios from 3:1 to 1:3 at up to 2K (with higher-res beta via API). A paid “Thinking” mode can search the web, verify facts, reason through multi-part layouts and incorporate uploaded files; the fuller API offering supports Codex integration and higher-resolution outputs.
OpenAI said it will deprecate GPT-Image-1.5 as the default while retaining legacy access.
The company maintains safety measures including C2PA metadata tagging and content-policy enforcement.
OpenAI positions Images 2.0 for practical, professional tasks — infographics, slides, catalogs, comics and UI mockups — as competition from Google and Anthropic intensifies.
The upgrade is available to free and paid ChatGPT tiers, with advanced features behind subscription and API access.








💬 Commentary