GTWY logo
    Neev Cloud logoNeev Cloud

    llama-3.1-8b-instant

    neev_cloud/llama-3.1-8b-instant

    ChatToolsSystem prompt

    Context

    —

    Max output

    131K

    Input / 1M

    $4.76

    Output / 1M

    $7.62

    Modality

    Chat

    Cutoff

    Dec 2023

    About this model

    Low-latency model suitable for real-time conversational interfaces, content filtering, and general analysis.

    Best suited for

    • Real-time chat applications
    • Low-latency AI assistants
    • Content moderation and filtering
    • General-purpose text analysis
    • Lightweight agent workflows

    Capabilities

    Tools

    Native function calling, so agents can invoke your endpoints.

    System prompt

    Honours a dedicated system role, separate from the user turn.

    Supported parameters

    temperature

    Controls randomness and creativity of responses.

    top_p

    Controls diversity by limiting token probability sampling.

    max_tokensMax Tokens Limit

    Maximum number of tokens generated in the response.

    tools

    Defines external tools available to the model.

    tool_choice

    Determines whether the model can use tools.

    response_type

    Specifies the output response format.

    parallel_tool_calls

    Allows multiple tools to execute simultaneously.

    stream

    Streams the response in real-time.