The page describes the model as optimized for multimodal image generation and editing, with a balance of price and performance. It lists a 131,072-token context window and a maximum of 32,768 output tokens.
The documented capabilities include image generation, multi-turn image editing, image generation from video input, interleaved image and text, C2PA Content Credentials, and virtual try-on. The page also marks structured output, function calling, and person generation as unsupported. It links to Agent Studio and Model Garden for trying and viewing the model. This record establishes what Google’s platform documentation lists; it does not substantiate comparative superiority claims or establish availability across other Google products.