Try the latest GLM-4.6 with extended context, superior coding, and refined intelligence. Now available on-demand

Model Library
/Moonshot AI/Kimi K2 Instruct
fireworks/kimi-k2-instruct

    Kimi K2 is a state-of-the-art mixture-of-experts (MoE) language model with 32 billion activated parameters and 1 trillion total parameters. Trained with the Muon optimizer, Kimi K2 achieves exceptional performance across frontier knowledge, reasoning, and coding tasks while being meticulously optimized for agentic capabilities.

    Fireworks Features

    Fine-tuning

    Docs

    Kimi K2 Instruct can be customized with your data to improve responses. Fireworks uses LoRA to efficiently train and deploy your personalized model

    Serverless

    Docs

    Immediately run model on pre-configured GPUs and pay-per-token

    On-demand Deployment

    Docs

    On-demand deployments give you dedicated GPUs for Kimi K2 Instruct using Fireworks' reliable, high-performance system with no rate limits.

    Available Serverless

    Run queries immediately, pay only for usage

    $0.60 / $2.50
    Per 1M Tokens (input/output)

    Metadata

    State
    Ready
    Created on
    7/11/2025
    Kind
    Base model
    Provider
    Moonshot AI
    Hugging Face
    Kimi-K2-Instruct

    Specification

    Calibrated
    No
    Mixture-of-Experts
    Yes
    Parameters
    1T

    Supported Functionality

    Fine-tuning
    Supported
    Serverless
    Supported
    Serverless LoRA
    Not supported
    Context Length
    131.1k tokens
    Function Calling
    Supported
    Embeddings
    Not supported
    Rerankers
    Not supported
    Support image input
    Not supported