Excited to announce that Fireworks Training is now in preview. Train and deploy frontier models on one platform. Learn more

Model Library/Deepseek/Deepseek v3.2
Deepseek Logo Mark

Deepseek v3.2

Ready
Try in Playground
Deploy on Demand
Fine-tune
fireworks/deepseek-v3p2

    Model from Deepseek that harmonizes high computational efficiency with superior reasoning and agent performance

    Deepseek v3.2 API Features

    Fine-tuning

    Docs

    Deepseek v3.2 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 Deepseek v3.2 using Fireworks' reliable, high-performance system with no rate limits.

    Available Serverless

    Run queries immediately, pay only for usage

    $0.56 / $0.28 / $1.68
    Per 1M Tokens (input/cached input/output)

    Metadata

    State
    Ready
    Created on
    12/1/2025
    Kind
    Base model
    Provider
    Deepseek
    Hugging Face
    DeepSeek-V3.2

    Specification

    Calibrated
    Yes
    Mixture-of-Experts
    Yes
    Parameters
    675.2B

    Supported Functionality

    Fine-tuning
    Supported
    Serverless
    Supported
    Context Length
    163.8k tokens
    Function Calling
    Supported
    Embeddings
    Not supported
    Rerankers
    Not supported
    Support image input
    Not supported