DeepSeek V4 Preview Release: 1.6T-param Pro and 284B Flash Models with 1M Context, Open-Sourced
DeepSeek has released DeepSeek-V4 as an open-weights preview, comprising two MoE variants: V4-Pro (1.6T total / 49B active parameters) and V4-Flash (284B total / 13B active parameters). Both models support 1M token context by default, enabled by a novel Token-wise compression and DeepSeek Sparse Attention (DSA) architecture. V4-Pro claims open-source SOTA on agentic coding benchmarks and world-class math/STEM/coding performance rivaling top closed-source models, while V4-Flash offers near-parity reasoning at lower cost and latency. The API is live today with OpenAI and Anthropic compatibility, and legacy model endpoints will be retired in July 2026.
Related guides (4)
Related events (8)
DeepSeek releases DeepSeek-V4-Flash-Base on Hugging Face
DeepSeek has released DeepSeek-V4-Flash-Base, a new open-weights base model, on Hugging Face. The model uses FP8 precision and the deepseek_v4 architecture with safetensors format. Early traction is notable with over 66,000 downloads and 241 likes shortly after release, suggesting significant community interest in a 'Flash' variant of the V4 series.
DeepSeek-V3: 671B MoE Open-Source Model with 3x Speed Improvement
DeepSeek releases V3, a 671B parameter Mixture-of-Experts model with 37B activated parameters, trained on 14.8T tokens. The model runs at 60 tokens/second (3x faster than V2) and is fully open-source with weights and paper released. API pricing is set at $0.27/M input tokens and $1.10/M output tokens starting February 8, positioning it as a low-cost frontier alternative. DeepSeek signals future multimodal capabilities in the ecosystem.
DeepSeek-V3.2 and V3.2-Speciale Released: Reasoning-First Models with Agent Tool-Use Integration
DeepSeek has released two new open-weights models: DeepSeek-V3.2, the official successor to V3.2-Exp with balanced reasoning and tool-use capabilities, and DeepSeek-V3.2-Speciale, a maxed-out reasoning variant claiming gold-medal performance on IMO, CMO, ICPC World Finals, and IOI 2025. V3.2 is the first DeepSeek model to integrate chain-of-thought thinking directly into tool-use workflows, trained on a new agent data synthesis pipeline covering 1,800+ environments and 85k+ complex instructions. V3.2-Speciale is API-only with no tool-call support, available via a temporary endpoint expiring December 15, 2025, while both models are open-sourced on Hugging Face with an accompanying technical report.
DeepSeek releases DeepSeek-V4-Pro-Base on Hugging Face
DeepSeek has released DeepSeek-V4-Pro-Base, a new base model, on Hugging Face with fp8 and safetensors support. The model has accumulated over 20,000 downloads and 291 likes shortly after release. This represents a new generation in DeepSeek's V-series open-weights frontier models.
DeepSeek-V3.1 Release: Hybrid Think/Non-Think Model with Agent-Focused Upgrades
DeepSeek has released V3.1, a hybrid inference model supporting both thinking and non-thinking modes in a single model, positioned as their first step toward the agent era. The model features improved tool use and multi-step agent task performance, with benchmarks showing gains on SWE-bench and Terminal-Bench, and faster thinking efficiency compared to DeepSeek-R1-0528. The base model received 840B tokens of continued pretraining for long-context extension, a new tokenizer, and open-source weights are available on HuggingFace. API updates include 128K context for both modes, Anthropic API format compatibility, and strict function calling support in beta.
DeepSeek Releases V3.2-Exp with Sparse Attention Architecture and 50%+ API Price Cut
DeepSeek has released DeepSeek-V3.2-Exp, an experimental model built on V3.1-Terminus that introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism designed to improve long-context performance and reduce compute costs during training and inference. Benchmarks indicate V3.2-Exp performs on par with V3.1-Terminus while achieving efficiency gains. The release is accompanied by a 50%+ API price reduction effective immediately, open-weights release on Hugging Face, a technical report, and GPU kernel code in TileLang and CUDA.
DeepSeek releases DeepSeek-V4-Pro on Hugging Face
DeepSeek has released DeepSeek-V4-Pro, a new text-generation model published on Hugging Face under the deepseek-ai organization. The model supports FP8 and 8-bit quantization formats and is tagged as endpoints-compatible with eval results included. With over 4.3 million downloads and 4,740 likes, it has attracted significant community uptake.
DeepSeek releases DeepSeek-V4-Flash on Hugging Face
DeepSeek has released DeepSeek-V4-Flash, a new text-generation model published on Hugging Face under the deepseek-ai organization. The model supports FP8 and 8-bit quantization and is tagged as conversational and endpoints-compatible. With over 2.8 million downloads and 1,455 likes, it has seen substantial early uptake.