{
  "slug": "deepseek-v4-pro",
  "order": 61,
  "name": "DeepSeek V4-Pro (1.6T)",
  "baseTitle": "DeepSeek V4-Pro",
  "company": "DeepSeek",
  "country": "China",
  "flag": "🇨🇳",
  "date": "2026-04-24",
  "decoderType": "Sparse MoE",
  "attention": "MLA-style CSA/HCA with mHC",
  "layerMix": "61 CSA/HCA",
  "scale": "1.6T total, 49B active (3.1% active)",
  "totalParams": 1600000000000,
  "activeParams": 49000000000,
  "context": "1,048,576",
  "contextTokens": 1048576,
  "license": "MIT License",
  "kvCacheText": "7.7 KiB",
  "kvCacheKiB": 7.7,
  "kvCacheLevel": "Very low",
  "summary": "DeepSeek's flagship V4 preview scales to 1.6T parameters and introduces compressed sparse attention plus manifold-constrained hyper-connections for million-token contexts.",
  "keyDetail": "Uses 384 experts, 6 routed plus 1 shared expert per token, hash-based routing, compressed attention caches, and the V4 MTP path.",
  "image": {
    "full": "https://sebastianraschka.com/llm-architecture-gallery/images/architectures/deepseek-v4-pro.webp",
    "thumb": "https://sebastianraschka.com/llm-architecture-gallery/images/architectures/thumbnails/deepseek-v4-pro.webp",
    "alt": "Figure 17: DeepSeek V4-Pro",
    "width": 960,
    "height": 774
  },
  "articleUrl": "https://magazine.sebastianraschka.com/p/recent-developments-in-llm-architectures#%C2%A75-csahca-mhc-and-compressed-attention-caches-deepseek-v4",
  "links": [
    {
      "label": "View in article",
      "href": "https://magazine.sebastianraschka.com/p/recent-developments-in-llm-architectures#%C2%A75-csahca-mhc-and-compressed-attention-caches-deepseek-v4",
      "title": null
    },
    {
      "label": "config.json",
      "href": "https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro/blob/main/config.json",
      "title": "deepseek-ai/DeepSeek-V4-Pro"
    },
    {
      "label": "License",
      "href": "https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro/blob/main/LICENSE",
      "title": null
    },
    {
      "label": "Tech report",
      "href": "https://arxiv.org/abs/2606.19348",
      "title": null
    }
  ],
  "concepts": [
    {
      "slug": "csa-hca",
      "label": "CSA/HCA",
      "name": "Compressed Sparse & Heavily Compressed Attention",
      "url": "https://llm-atlas-7or.pages.dev/concepts/csa-hca/"
    },
    {
      "slug": "mhc",
      "label": "mHC",
      "name": "Manifold-constrained Hyper-Connections",
      "url": "https://llm-atlas-7or.pages.dev/concepts/mhc/"
    },
    {
      "slug": "mla",
      "label": "MLA",
      "name": "Multi-Head Latent Attention",
      "url": "https://llm-atlas-7or.pages.dev/concepts/mla/"
    },
    {
      "slug": "deepseek-sparse-attention",
      "label": "DSA",
      "name": "DeepSeek Sparse Attention",
      "url": "https://llm-atlas-7or.pages.dev/concepts/deepseek-sparse-attention/"
    },
    {
      "slug": "moe",
      "label": "MoE",
      "name": "Mixture of Experts",
      "url": "https://llm-atlas-7or.pages.dev/concepts/moe/"
    },
    {
      "slug": "mtp",
      "label": "MTP",
      "name": "Multi-Token Prediction",
      "url": "https://llm-atlas-7or.pages.dev/concepts/mtp/"
    }
  ],
  "aai": {
    "v5": {
      "label": "AA Intelligence Index v5.0",
      "total": 23.1,
      "profile": {
        "Knowledge Work": 36.3,
        "Coding": 15.9,
        "Science": 12.8,
        "General": 27.1
      },
      "url": "https://artificialanalysis.ai/models/deepseek-v4-pro"
    },
    "v4": {
      "label": "AA Intelligence Index v4.3.2",
      "total": 36,
      "profile": {
        "General": 34.4,
        "Scientific": 29.5,
        "Coding": 32.6,
        "Agents": 44.2
      },
      "url": "https://artificialanalysis.ai/models/deepseek-v4-pro"
    }
  },
  "sourceUrl": "https://sebastianraschka.com/llm-architecture-gallery/#card-deepseek-v4-pro",
  "family": "moe",
  "url": "https://llm-atlas-7or.pages.dev/models/deepseek-v4-pro/",
  "markdownUrl": "https://llm-atlas-7or.pages.dev/models/deepseek-v4-pro.md"
}