Google Launches Imagen 4 for Text-to-Image Generation via Gemini API and AI Studio -- Pure AI

Google Launches Imagen 4 for Text-to-Image Generation via Gemini API and AI Studio

By John K. Waters
06/25/2025

Google on Tuesday launched Imagen 4, the latest version of its text-to-image generation technology, making it available via the Gemini API and Google AI Studio. The release includes two model variants—Imagen 4 and Imagen 4 Ultra—aimed at advancing image quality and precision in AI-generated visuals.

The company said the models offer substantial improvements over previous versions, particularly in rendering textual elements within images—a common challenge in generative AI. Imagen 4 is now available in paid preview, with limited free testing enabled through Google AI Studio.

Google is positioning Imagen 4 as the primary model for general use cases, priced at $0.04 per generated image. A higher-tier version, Imagen 4 Ultra, is designed for more precise prompt adherence and detailed outputs. It is priced at $0.06 per image.

Additional billing tiers and options for higher rate limits are expected to be introduced in the coming weeks.

In a demonstration, Google highlighted several examples of Imagen 4 Ultra’s capabilities, including a multi-panel science-fiction comic, a vintage Kyoto travel postcard, and editorial-style fashion photography. These samples are designed to illustrate the model's ability to handle complex prompts, stylistic diversity, and cinematic composition.

As part of its responsible AI initiative, Google said all images generated using Imagen 4 and 4 Ultra will include a non-visible SynthID watermark. The watermarking technology is intended to ensure traceability and transparency in synthetic media.

The release comes amid heightened competition in the AI-generated image space, with OpenAI’s DALL·E and Stability AI’s Stable Diffusion also evolving rapidly. Google’s move to offer Imagen 4 through Gemini API integration positions the model as part of its broader generative AI ecosystem, which includes text, code, and multimedia capabilities.

Imagen 4 and 4 Ultra are available immediately to developers through the Gemini API. Access to Google AI Studio remains limited during the preview phase.

About the Author

John K. Waters is the editor in chief of a number of Converge360.com sites, with a focus on high-end development, AI and future tech. He's been writing about cutting-edge technologies and culture of Silicon Valley for more than two decades, and he's written more than a dozen books. He also co-scripted the documentary film Silicon Valley: A 100 Year Renaissance, which aired on PBS. He can be reached at [email protected].