AdaL
    Available now in AdaL CLI and Desktop

    Code with GLM-5.3 Flash
    in AdaL

    Z.ai's native multimodal flash model. Use glm-5.3-flash in AdaL for fast, low-cost coding with 1M context and vision support.

    Get Started

    Run /model and pick GLM-5.3 Flash · $0.15/M input · $0.50/M output

    Why use GLM-5.3 Flash in AdaL

    Key capabilities and pricing

    Native multimodal · flash-cost coding

    Recommended in AdaL for fast coding sessions at flash-tier pricing.

    Vision support

    Understands images alongside code and text in the same session.

    1M context

    1M token context for large codebases and long sessions.

    Flexible effort

    Adjustable reasoning effort levels for speed/quality control.

    Flash-cost pricing

    $0.15/M input · $0.50/M output — a fraction of the GLM-5.3 flagship price.

    Cached input discount

    $0.03/M cached input for repeated context across turns.

    How to pick GLM-5.3 Flash

    Available in AdaL CLI and Desktop through the model selector

    1

    Open AdaL CLI or AdaL Desktop

    Use the coding environment where AdaL already understands your repo, tools, and task context.

    2

    Run /model

    Open the model selector and choose your model from the list.

    3

    Start your task

    Ask AdaL to inspect, plan, edit, test, and review with your chosen model powering the agent loop.

    What to know

    Key details about GLM-5.3 Flash

    "GLM-5.3 Flash is our native multimodal model built for flash-cost coding."

    Z.ai

    "Use GLM-5.3 Flash for fast iteration where vision input and 1M context matter but budget is tight."

    AdaL

    "$0.15/M input · $0.50/M output · $0.03/M cached — flash-tier pricing."

    Pricing

    "Available now in AdaL CLI and Desktop, 50% off launch week."

    Availability

    50% off launch week

    Ready to try GLM-5.3 Flash in AdaL?

    Open AdaL CLI or Desktop, run /model, and choose GLM-5.3 Flash.

    Get Started with AdaL
    AdaL CLIAdaL Desktop