News

ChatGPT Images 2.5: two API models, lower latency, steadier multi-turn edits

OpenAI released ChatGPT Images 2.5 on September 8, 2026, for all ChatGPT, ChatGPT Work and Codex users, and as two API models: GPT-Image-2.5 Flare, the faster default, and GPT-Image-2.5 Sunburst for tighter control across edits. OpenAI claims up to 50% lower latency than Images 2.0.

For real pipelines, the change is in editing: per OpenAI, the new models preserve the subjects of reference photos, follow editing instructions more reliably across multiple turns, and make targeted changes without rebuilding the whole asset.

Transparent backgrounds are not new: PNG with a real alpha channel shipped in the API with GPT-Image-2 on August 21, 2026. OpenAI's wording for 2.5 is that the model "can handle more complex layouts including transparent backgrounds".

One API developer measured average latency falling from about 104 seconds on GPT-Image-2 to 35 to 40 seconds on 2.5 (their figure, their workload) and reports better use of reference images. Other commenters note that micro-details still slip: fingers and shadows.

Read OpenAI's announcement
Date

More news

All news

Dekkode at IBC 2026 in Amsterdam

From 11 to 14 September we're at IBC 2026 in Amsterdam — no booth of our own, but you'll find us hanging around the German Pavilion at the RAI most of the time. We're there to network: catching up with partners, customers and friends from the broadcast and media industry. If you're around too, get in touch.

php-mjml is open source: our MJML renderer for PHP

MJML turns a simple markup language into responsive HTML email, usually with a Node toolchain doing the work behind it. We ported it to PHP end to end: php-mjml/php-mjml needs no Node.js, no second runtime in the deployment. It has rendered this website's emails since February; as of this week it's open under the MIT licence for anyone to use.

View the repository on GitHub

Software Development in Hamburg!

Start new project with us or upgrade an existing one to the next level