DeepSeek

⚠️ Heads-up to anyone using the DeepSeek-V3.2-Exp inference demo: earlier versions had a RoPE implementation mismatch in the indexer module that could degrade performance. Indexer RoPE expects non-interleaved input, MLA RoPE expects interleaved. Fixed in github.com/deepseek-ai/De….

🛠 Open Source Release 📦 DeepSeek-V3.2 Model: huggingface.co/deepseek-ai/De… 📦 DeepSeek-V3.2-Speciale Model: huggingface.co/deepseek-ai/De… 📄 Tech report: huggingface.co/deepseek-ai/De… 5/n

💻 API Update 🔹 V3.2: Same usage pattern as V3.2-Exp. 🔹 V3.2-Speciale: Served via a temporary endpoint: base_url="api.deepseek.com/v3.2_speciale_…". Same pricing as V3.2, no tool calls, available until Dec 15th, 2025, 15:59 (UTC Time). 💡 V3.2 now supports Thinking in Tool-Use — details: api-docs.deepseek.com/guides/thinkin… 4/n

🚀 Launching DeepSeek-V3.2 & DeepSeek-V3.2-Speciale — Reasoning-first models built for agents! 🔹 DeepSeek-V3.2: Official successor to V3.2-Exp. Now live on App, Web & API. 🔹 DeepSeek-V3.2-Speciale: Pushing the boundaries of reasoning capabilities. API-only for now. 📄 Tech report: huggingface.co/deepseek-ai/De… 1/n

🛠 Open Source Release 🔗 Model: huggingface.co/deepseek-ai/De… 🔗 Tech report: github.com/deepseek-ai/De… 🔗 Key GPU kernels in TileLang & CUDA (use TileLang for rapid research prototyping!) 4/n

💻 API Update 🎉 Lower costs, same access! 💰 DeepSeek API prices drop 50%+, effective immediately. 🔹 For comparison testing, V3.1-Terminus remains available via a temporary API until Oct 15th, 2025, 15:59 (UTC Time). Details: api-docs.deepseek.com/guides/compari… 🔹 Feedback welcome: feedback.deepseek.com/dsa 3/n

🚀 Introducing DeepSeek-V3.2-Exp — our latest experimental model! ✨ Built on V3.1-Terminus, it debuts DeepSeek Sparse Attention(DSA) for faster, more efficient training & inference on long context. 👉 Now live on App, Web, and API. 💰 API prices cut by 50%+! 1/n

📊 DeepSeek-V3.1-Terminus delivers more stable & reliable outputs across benchmarks compared to the previous version. 👉 Available now on: App / Web / API 🔗 Open-source weights here: huggingface.co/deepseek-ai/De… Thanks to everyone for your feedback. It drives us to keep improving and refining the experience! 🚀 2/2

🚀 DeepSeek-V3.1 → DeepSeek-V3.1-Terminus The latest update builds on V3.1’s strengths while addressing key user feedback. ✨ What’s improved? 🌐 Language consistency: fewer CN/EN mix-ups & no more random chars. 🤖 Agent upgrades: stronger Code Agent & Search Agent performance. 1/2

Pricing Changes 💳 🔹 New pricing starts & off-peak discounts end at Sep 5th, 2025, 16:00 (UTC Time) 🔹 Until then, APIs follow current pricing 📝 Pricing page: api-docs.deepseek.com/quick_start/pr… 5/5

Model Update 🤖 🔹 V3.1 Base: 840B tokens continued pretraining for long context extension on top of V3 🔹 Tokenizer & chat template updated — new tokenizer config: huggingface.co/deepseek-ai/De… 🔗 V3.1 Base Open-source weights: huggingface.co/deepseek-ai/De… 🔗 V3.1 Open-source weights: huggingface.co/deepseek-ai/De… 4/5

Introducing DeepSeek-V3.1: our first step toward the agent era! 🚀 🧠 Hybrid inference: Think & Non-Think — one model, two modes ⚡️ Faster thinking: DeepSeek-V3.1-Think reaches answers in less time vs. DeepSeek-R1-0528 🛠️ Stronger agent skills: Post-training boosts tool use and multi-step agent tasks Try it now — toggle Think/Non-Think via the "DeepThink" button: chat.deepseek.com 1/5

🚀 DeepSeek-R1-0528 is here! 🔹 Improved benchmark performance 🔹 Enhanced front-end capabilities 🔹 Reduced hallucinations 🔹 Supports JSON output & function calling ✅ Try it now: chat.deepseek.com 🔌 No change to API usage — docs here: api-docs.deepseek.com/guides/reasoni… 🔗 Open-source weights: huggingface.co/deepseek-ai/De…

🚀 DeepSeek-V3-0324 is out now! 🔹 Major boost in reasoning performance 🔹 Stronger front-end development skills 🔹 Smarter tool-use capabilities ✅ For non-complex reasoning tasks, we recommend using V3 — just turn off “DeepThink” 🔌 API usage remains unchanged 📜 Models are now released under the MIT License, just like DeepSeek-R1! 🔗 Open-source weights: huggingface.co/deepseek-ai/De…

🚀 Day 6 of #OpenSourceWeek: One More Thing – DeepSeek-V3/R1 Inference System Overview Optimized throughput and latency via: 🔧 Cross-node EP-powered batch scaling 🔄 Computation-communication overlap ⚖️ Load balancing Statistics of DeepSeek's Online Service: ⚡ 73.7k/14.8k input/output tokens per second per H800 node 🚀 Cost profit margin 545% 💡 We hope this week's insights offer value to the community and contribute to our shared AGI goals. 📖 Deep Dive: bit.ly/4ihZUiO