Gemini logoGemini

    imagen-4.0-fast-generate-001

    Auto-router

    gemini/imagen-4.0-fast-generate-001

    Image

    Context

    Max output

    Input / 1M

    Output / 1M

    Modality

    Image

    Cutoff

    About this model

    This is the Low Latency variant. It is designed for high-speed generation.

    Best suited for

    • This model is optimized for real-time applications and low-latency needs, such as high-speed generation for interactive user experiences or rapid creative exploration. At a lower cost per image, it is ideal for large-scale batch processing, prototyping comic strips or posters, and integration into fast-paced app environments where quick turnaround is more critical than maximum resolution.

    Supported parameters

    number_of_images

    Specifies how many images to generate for a single prompt.

    aspect_ratio

    Defines the width-to-height proportion for generated visual output.