Google has announced that its most advanced text-to-image models, Image 4 and Image 4 Ultra, designed to handle a “wide range of image-generating tasks,” are now available in the Gemini API in a paid preview and in Google AI Studio with limited free trials.
The tech company unveiled the Image 4 family of models at its annual developer event last May, designed to deliver richer images with more vivid colors and more detail, paying special attention to light and shadow contrasts.
Now, Google has released this tool for both the Gemini API for its artificial intelligence assistant, in a paid preview, and for its Google AI Studio platform through limited free trials, aiming to meet “a variety of creative needs,” the company explained in a blog post.
Thus, the company has indicated that Image 4 is the best option for handling a “wide range of image generation tasks,” with significant improvements in content quality compared to Image 3. Thus, this model will be priced at $0.04 per output image (about €0.034).
Meanwhile, if users need to create images with a high degree of precision, Google has clarified that Image 4 Ultra is the recommended model, as it is designed to produce results “more aligned” with their text input. This version is priced at $0.06 per image (about €0.052).
Google has also warned that it will introduce additional billing tiers in the coming weeks, and in the meantime, higher rate limits for Image 4 and 4 Ultra are available for request.
