Back Original

Introducing ChatGPT Images 2.5

8th September 2026 - Link Blog

Introducing ChatGPT Images 2.5. OpenAI's image generation models are apparently used "more than 3 billion images across ChatGPT Images and the GPT‑Image models in the API". This latest release improves their instruction-following ability across multiple turns, responds faster, and "is better at preserving the subjects in your reference photos".

There are two new model IDs in the API: gpt-image-2.5-sunburst and gpt-image-2.5-flare. Based on this I think Sunburst is the stronger option:

Choose Sunburst for workflows where editing precision matters most, and Flare for fast, high-quality everyday image generation.

I upgraded my openai_image.py CLI tool to support passing in one or more reference images, so now this works:

uv run https://tools.simonwillison.net/python/openai_image.py \
  'add a raccoon scientist studying the chart thoughtfully' \
  -i https://static.simonwillison.net/static/2026/openai-agent-usage.webp \
  -m gpt-image-2.5-sunburst

This is the original image, and here's what I got back from that prompt to "add a raccoon scientist studying the chart thoughtfully":

Line chart with cartoon illustration. Title: "Usage of internal coding agents is increasing significantly—Median researcher". Y-axis labeled "Daily $ / researcher" from 0 to 700; x-axis shows Feb 2026, Apr 2026, Jun 2026, Aug 2026. A blue line stays near zero through April, rises gradually to around 150 by June and July, then climbs steeply to about 600 by late August. In the foreground a cartoon raccoon in glasses and a white lab coat, chin in hand, holds a clipboard at a desk with a mug bearing the OpenAI logo, some printed charts, and a stack of three books titled "AI AGENTS", "SOFTWARE ENGINEERING", and "PRODUCTIVITY". An OpenAI logo appears in the top right corner.