ChatGPT Images 2.5 improves visual editing

OpenAI’s ChatGPT Images 2.5 is a newly released update to the image creation platform designed to support faster and more accurate creation and editing of visual content. Introduced on September 8, 2026, the tool includes improvements such as sharper, more natural lighting, richer textures, consistent editing, and new creative controls such as the Sketch feature, templates for popular formats, and the ability to comment directly on images. It is available to all ChatGPT, ChatGPT Work and Codex users on desktop, mobile and web, and comes with new API models – GPT-Image-2.5 Flare and GPT-Image-2.5 Sunburst – for improved performance and accuracy.

Key Features

• Fidelity and recognition of the image: Images 2.5 is improved over earlier versions by better preserving objects (such as people or pets) when converting reference photos, rendering lighting and textures more realistically, and following editing instructions more reliably.

• Editing Accuracy: Users can now make changes that affect only specific parts of an image (background, copy, objects), leave comments on images for clarification, and maintain visual consistency across multiple versions.

• Creative input tools: The new Sketch tool allows users to draw directly into ChatGPT as input to the final images; The templates cover formats such as posters and product photography, making it easy to work with layouts.

• Speed ​​and scalability: Image generation latency has been reduced by nearly 50% compared to Images 2.0, helping you generate and refine ideas faster. Two API models – Flare and Sunburst – offer options that combine speed and maximum detail.

Prices

ChatGPT’s business-oriented pricing includes two seat types: Standard and Premium. Standard seats cost $20 per user per month billed annually ($25 billed monthly), and Premium seats cost $100 per user per month billed annually ($125 billed monthly). Premium seats offer approximately 5 times more usage restrictions and no specific usage restrictions compared to standard seats.

In terms of API usage, the new GPT-Image-2.5 models are now available under the names GPT-Image-2.5 Flare and Sunburst, although OpenAI has not yet published individual pricing for these successors. Users rely on existing prices for GPT-Image-2.0, which are charged on a token basis: text input tokens, image input tokens (when editing), and image output tokens. For GPT-Image-2.0, input requests are priced at $5 per million text tokens, image inputs are priced at $8 per million tokens, and image output tokens are priced at $30 per million tokens. Cached input is slower.

Who is this for?

• Marketing teams you need resources such as social media graphics, product photos, flyers or posters. Improved control over text rendering, layout, and asset consistency makes it suitable for campaign work.

• Content Creators and Small Businesses who want to create or edit images themselves, including changing logos, product images or advertising materials, with minimal interaction with designers.

• Teams of designers or brand managers strives to quickly iterate visuals, especially through reference photographs or sketches, and maintain consistency of style and theme across multiple versions.

• Developers Integrating image creation via APIs—for example, to create creative tools, software that personalizes visual content, or automate workflows that involve creating graphics or editing photos.

When deciding whether to adopt it, decision makers should consider the volume of image usage, quality requirements, and control over the final appearance: companies with frequent visual content requirements will likely benefit most from increased speed and precision editing tools, while casual users may be satisfied with plans with less usage.

Final Thoughts

ChatGPT Images 2.5 represents a significant evolution in AI-powered visual design, offering better speed, sharper visuals, more flexible editing, and more control over the creative process. Its implementation at all levels of users and the introduction of API variants makes it accessible to a variety of business contexts. While API prices for the new 2.5 models have not yet been published, existing token prices within GPT-Image-2.0 provide a useful guide. For organizations with ongoing content production needs, Images 2.5 can reduce design time and costs; for those who use it sporadically, it still provides a powerful experience, although the cost-effectiveness will depend on the scale of use and quality settings.

Visit the official website to find out more.

Follow our stories on LinkedIn, TwitterFacebook and Instagram.