Skip to content

    Kimi K2 Thinking

    Chat

    moonshotai/Kimi-K2-Thinking

    Request a dedicated endpoint

    Kimi K2 Thinking on FlexAI: Moonshot AI LLM (Reasoning), Moonshot K2 License (modified MIT), available as a dedicated endpoint on FlexAI or your own infrastructure.

    Pricing

    Input

    $0.47 / M tokens

    Output

    $2 / M tokens

    Context

    128K tokens

    API endpoint

    /v1/chat/completions

    Compatibility

    OpenAI

    Parameters

    1T MoE (32B active)

    License

    Moonshot K2 License (modified MIT)

    Hardware

    16× H100

    Quantization

    FP8

    Kimi K2 Thinking runs as a dedicated endpoint, provisioned per customer on FlexAI's infrastructure or your own, not served through the shared Token Factory API.