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

Model Library
/Deepseek/DeepSeek-V4-Pro
deepseek-ai/deepseek-v4-pro

    DeepSeek-V4-Pro is a flagship open-source Mixture-of-Experts model designed for frontier reasoning, advanced coding, and long-context intelligence at scale (up to 1M tokens). It introduces a hybrid attention architecture that dramatically improves long-context efficiency while reducing KV and compute overhead, along with stability and training enhancements for deep multi-step reasoning. It represents a top-tier open-source system for complex agentic workflows, high-precision reasoning, and demanding production workloads.

    DeepSeek-V4-Pro API Features

    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-V4-Pro using Fireworks' reliable, high-performance system with no rate limits.

    Available Serverless

    Run queries immediately, pay only for usage

    $1.74 / $0.14 / $3.48
    Per 1M Tokens (input/cached input/output)

    Metadata

    State
    Unknown
    Created on
    N/A
    Kind
    Unknown
    Provider
    Deepseek

    Specification

    Calibrated
    No
    Mixture-of-Experts
    No
    Parameters
    N/A

    Supported Functionality

    Fine-tuning
    Not supported
    Serverless
    Supported
    Context Length
    1048.6k tokens
    Function Calling
    Not supported
    Embeddings
    Not supported
    Rerankers
    Not supported
    Support image input
    Not supported