Introducing our latest image generation model in the API

When we introduced image generation in ChatGPT last month, it quickly became one of our most popular features: over 130 million users around the world created more than 700 million images in just the first week⁠(opens in a new window).

Today, we’re bringing the natively multimodal model that powers this experience in ChatGPT to the API via gpt-image-1, enabling developers and businesses to easily integrate high-quality, professional-grade image generation directly into their own tools and platforms. The model’s versatility allows it to create images across diverse styles, faithfully follow custom guidelines, leverage world knowledge, and accurately render text—unlocking countless practical applications across multiple domains.

Leading enterprises and startups across industries including creative tools, e-commerce, education, enterprise software, gaming, are already using image generation in their products and experiences. We’re excited to share some of these examples below.

We’re also continuing to work with developers and businesses to uncover more ways image generation in the API can serve their use cases, including:

Designing and editing: Canva is exploring ways to integrate OpenAI's gpt-image-1 to push the boundaries of design generation and editing in its Canva AI and Magic Studio tools. Through gpt-image-1 capabilities like transforming rough sketches into stunning graphic elements and enabling high-fidelity visual edits, Canva will further empower its 230 million users to bring their ideas to life in entirely new ways.

Creating and editing logos: GoDaddy is actively experimenting to integrate image generation so customers can easily create logos that are editable, remove backgrounds, and generate professional typography. In addition, as a new experience with GoDaddy Airo^®, the team is working towards customers creating social media posts and marketing assets that reflect their unique brand identities for original product and brand content created from a prompt.