Skip to content

    Granite 4.0 H Micro

    Chat

    ibm-granite/granite-4.0-h-micro

    Request a dedicated endpoint

    Granite 4.0 H Micro on FlexAI: IBM LLM, Apache 2.0 license, available as a dedicated endpoint on FlexAI or your own infrastructure.

    Pricing

    Input

    $0.017 / M tokens

    Output

    $0.112 / M tokens

    Context

    128K tokens

    API endpoint

    /v1/chat/completions

    Compatibility

    OpenAI

    Parameters

    3.19B dense

    License

    Apache 2.0

    Hardware

    H100

    Quantization

    BF16

    Granite 4.0 H Micro runs as a dedicated endpoint, provisioned per customer on FlexAI's infrastructure or your own, not served through the shared Token Factory API.