Skip to content

    Zephyr 7B Beta

    Chat

    HuggingFaceH4/zephyr-7b-beta

    Zephyr 7B Beta on FlexAI: HuggingFace LLM, MIT license, available as a dedicated endpoint on FlexAI or your own infrastructure.

    Pricing

    Input

    $0 / M tokens

    Context

    32K tokens

    API endpoint

    /v1/chat/completions

    Compatibility

    OpenAI

    Parameters

    7B

    License

    MIT

    Hardware

    H100

    Quantization

    FP8

    Zephyr 7B Beta runs as a dedicated endpoint, provisioned per customer on FlexAI's infrastructure or your own, not served through the shared Token Factory API.