{"slug": "deepseek-v4-flash", "title": "DeepSeek V4 Flash", "summary": "DeepSeek released V4 Flash, a 284B-parameter MoE model with 13B active parameters per token, featuring FP4+FP8 hybrid attention and 1M native context. The open-weight model, available under MIT license, can self-host on a 2x H100/H200 node and routes to the deepseek-chat/reasoner API alias as of July 24, 2026.", "body_md": "# DeepSeek V4 Flash\n\nMoE workstation284B total, 13B active per token (MoE). Same FP4+FP8 hybrid-attention family as V4 Pro: Compressed Sparse Attention (CSA) + Heavily Compressed Attention (HCA) across 61 layers, manifold-constrained Hyper-Connections (mHC), Muon optimizer, 32T+ pretraining tokens. 1M native context, 384K max output; three modes (non-think / think-high / think-max). At ~150-170GB for Q4 weights it self-hosts on a 2x H100/H200 node, and at Q2 on a 192GB Mac Studio or 2x RTX 6000 Ada workstation. The model the deepseek-chat/reasoner API aliases now route to (retired 2026-07-24). Open weights under MIT.\n\n- 284.0B\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 | 0.09 | 0.18 | - | - | - | - | 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-flash/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-flash", "canonical_source": "https://tokenstead.ai/models/deepseek-v4-flash", "published_at": "2026-07-09 14:12:02+00:00", "updated_at": "2026-07-09 15:09:01.411232+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-products", "ai-infrastructure"], "entities": ["DeepSeek", "H100", "H200", "Mac Studio", "RTX 6000 Ada", "OpenRouter"], "alternates": {"html": "https://wpnews.pro/news/deepseek-v4-flash", "markdown": "https://wpnews.pro/news/deepseek-v4-flash.md", "text": "https://wpnews.pro/news/deepseek-v4-flash.txt", "jsonld": "https://wpnews.pro/news/deepseek-v4-flash.jsonld"}}