Imagen 4

Text-to-image generation: text only in (up to 480 tokens), 1 to 4 images out. A text-only model — it does not accept image input. A separate upscaling operation raises resolution to 2K, 3K and 4K.

Legacy: точки Imagen 4 в Gemini API выключены 17 августа 2026 с переводом на Gemini 3.1 Flash Image, в Vertex AI помечены как устаревшие с рекомендацией миграции, но модель до сих пор стоит в прайс-листе Vertex AI и остаётся выбираемой в платном плане.

Understands

text

This model cannot see images or video — you can only give it text. That matters if you planned to show it screenshots or documents with pictures.

Produces

images

Contents verified with the vendor: 2026-08-18

Included in subscriptions

No catalogue entry marks this model as part of a plan yet. It will appear here once the plan contents are confirmed with the vendor.