Skip to content

    GPT-OSS 20B

    Chat

    gpt-oss-20b

    Request a dedicated endpoint

    GPT-OSS 20B on FlexAI: OpenAI LLM, Apache 2.0 license, available as a dedicated endpoint on FlexAI or your own infrastructure.

    Pricing

    Input

    $0.03 / M tokens

    Output

    $0.13 / M tokens

    Cached input

    $0.0045 / M tokens

    Context

    128K tokens

    API endpoint

    /v1/chat/completions

    Compatibility

    OpenAI

    Parameters

    20B

    License

    Apache 2.0

    Hardware

    H100

    Quantization

    MXFP4

    GPT-OSS 20B runs as a dedicated endpoint, provisioned per customer on FlexAI's infrastructure or your own, not served through the shared Token Factory API.