Google Launches Imagen 4 Family in Gemini API

Aug 19, 2025
Google has announced the general availability of its advanced text-to-image model, Imagen 4, in the Gemini API and Google AI Studio. This release includes the new Imagen 4 Fast model, designed for rapid image generation.

Google has announced the general availability of its advanced text-to-image model, Imagen 4, in the Gemini API and Google AI Studio announced on their website. This release includes the new Imagen 4 Fast model, which is optimized for speed and high-volume tasks, offering images at a cost of $0.02 per output.

The Imagen 4 family consists of three models: Imagen 4 Fast, Imagen 4, and Imagen 4 Ultra. Each model caters to different creative needs, balancing quality, speed, and cost. Imagen 4 Fast is ideal for rapid image generation, while Imagen 4 serves as the flagship model for high-quality image tasks. Imagen 4 Ultra is designed for projects requiring the highest level of detail and prompt adherence.

Both Imagen 4 and Imagen 4 Ultra support image generation up to 2K resolution, enabling the creation of detailed and crisp visuals. This makes them suitable for a range of applications, from marketing assets to intricate artistic compositions.

The release of the Imagen 4 family is part of Google's ongoing efforts to enhance its AI capabilities, as seen in previous updates to the Gemini platform.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Daily AI Brief.

Also, consider following us on social media:

AI Brief AI Brief (X)
Free newsletter

Daily AI Brief

Daily report covering major AI developments and industry news, with both top stories and complete market updates

AI Token Webinar

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more

You may also like

Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.