{"slug": "deepseek-v4-pro", "title": "DeepSeek V4 Pro", "summary": "DeepSeek releases V4 Pro, a 1.6-trillion-parameter Mixture-of-Experts model with 49 billion active parameters per token, achieving a top open-weight score of 80.6% on SWE-bench Verified. The model requires multi-H200/H100 clusters for inference, limiting deployment to cloud providers despite MIT-licensed open weights.", "body_md": "# DeepSeek V4 Pro\n\nMoE premier1.6T total, 49B active per token (MoE). Hybrid attention: Compressed Sparse Attention (CSA, 4x KV compression) + Heavily Compressed Attention (HCA, 128x) across 61 layers, manifold-constrained Hyper-Connections (mHC). FP4 experts + FP8 rest, 32T+ pretraining tokens, Muon optimizer. 1M native context; Think Max mode recommends >=384K. At ~800GB+ for Q4 weights it needs a multi-H200/H100 cluster or DGX-class system - not workstation-fittable, so cloud-only for nearly everyone despite open weights. Top open-weight agentic coding score (SWE-bench Verified 80.6). Open weights under MIT.\n\n- 1600.0B\n- 1000k\n- mit\n- Apr 2026\n\n## Scores\n\n## Or run it in the cloud\n\nLive per-provider pricing, throughput and uptime - refreshed 3 days ago via OpenRouter. Click a column to sort.\n\n| Provider | Type | Input $/M | Output $/M | Cache $/M | Tok/s | Latency | Uptime | Value |\n|---|---|---|---|---|---|---|---|---|\n| API | 0.44 | 0.87 | - | - | - | - | cheapest |\n\nDefault order: throughput among 95%+ uptime providers, then latency; subscriptions last. Sort by any column. Subscription rows show $/mo in the Value column - per-token columns are \"-\". Affiliate links are marked sponsored / nofollow. Confirm current pricing on the provider's site before committing.\n\n[Detailed API pricing page + JSON endpoint →](/models/deepseek-v4-pro/pricing)\n\n## Inference cost over time\n\nData accumulates from the first daily sync - longer ranges populate over time. Prices come from OpenRouter snapshots, not a historical API.", "url": "https://wpnews.pro/news/deepseek-v4-pro", "canonical_source": "https://tokenstead.ai/models/deepseek-v4-pro", "published_at": "2026-07-10 22:28:00+00:00", "updated_at": "2026-07-10 23:07:05.087912+00:00", "lang": "en", "topics": ["large-language-models", "artificial-intelligence", "ai-products", "ai-research", "ai-infrastructure"], "entities": ["DeepSeek", "OpenRouter", "MIT"], "alternates": {"html": "https://wpnews.pro/news/deepseek-v4-pro", "markdown": "https://wpnews.pro/news/deepseek-v4-pro.md", "text": "https://wpnews.pro/news/deepseek-v4-pro.txt", "jsonld": "https://wpnews.pro/news/deepseek-v4-pro.jsonld"}}