DeepSeek R1
deepseek/deepseek-r1- DeepSeek
- Family · DeepSeek R1
- Released 20 Jan 2025
Not on OSMEXO yet
Spec & list price
Context156K
Scores · standing
Intelligence13.1#194/489
Coding24.6#126/196
Usage
Requests / day27.8K
Tool calls / req0.02
Per request · 30 days
Avg input4.7K0.3× median
Avg output1.3K1.9× median
Cache hit48%0.7× median
Reasoning share80%1.4× median
Tool-call failures10%5.4× median
Consumption
Peak 465.5M 29 SepLow 124.9M 19 Oct
News & trends
33 mentions this week ▲ 120%this model · videos, posts, articles · 30 days
Trending · 14 days
- DeepSeek R1 Open Source AI | Malayalam #ai #artificialintelligence #opensource184 views
- Why Did the Early Version of DeepSeek R1 Start Writing "Wait" ? #deepseek #rl #ai1.0K views
- Nexus-CLI – Pure Go Bridge to DeepSeek R1/V3 with Claude Code and Ollama Support1 upvotes
News · latest from DeepSeek
- Tell HN: Mistrap Pro includes DeepSeek v4.1 Flash 1017docs.mistral.ai · 1 Nov
- Show HN: DeepSeek v4.1 Flash-1017 Safety Evaluationtwitter.com · 26 Oct
- DeepSeek V4 Pro 0813 vs Claude Fable 5 on DeepSWE: Cost, Coding, and RoutingTogether AI · 17 Aug
- DeepSeek-V4 Flash 0731 vs GPT-5.6 Luna on DeepSWE: Cost and CodingTogether AI · 6 Aug
Benchmarks
bar = share of the top score · Benchmark data: Artificial AnalysisWhen to use
Best for
- Math and competition-style problem solving
- Scientific and technical Q&A
- Code reasoning and debugging
- Reasoning over long documents
Think twice for
- Tool-calling agents (no native tool calling)
- Image understanding
- Latency-sensitive chat
- Instruction-following pipelines
Research papers
- Linear Probes Transfer from Base to Distilled Language Models despite Rotation26 Oct
- Tracing Hallucinations in LLM Reasoning for UML Class Diagram Generation: An Empirical Taxonomy and Mitigation Study22 Oct
- The Reaction of Financial Markets to the Releases of DeepSeek R1 and Kimi K3: A Critical Analysis22 Oct
- SPARE: Sparsity Allocation via Routing Entropy for Efficient MoEs21 Oct
- Exposing Vulnerability Monoculture Through Systemic Adversarial Robustness19 Oct
- Aerial-R1: Reinforcing Aerial Reasoning and Segmentation in MLLMs19 Oct
- Lingdan-V2: Large language models for clinically grounded reasoning in traditional Chinese medicine10 Oct
- Can Language Models Play the Wikipedia Game?9 Oct
Social
Most watched and discussed · 90 days
- Why Did the Early Version of DeepSeek R1 Start Writing "Wait" ? #deepseek #rl #aiNeuronimation · 1.0K views · 30 Oct
- DeepSeek R1 Open Source AI | Malayalam #ai #artificialintelligence #opensourceAgentic life Malayalam · 184 views · 31 Oct
- 不给示范，只做强化学习：DeepSeek-R1-Zero 从 15.6% 涨到 77.9%技术喵 · 113 views · 27 Oct
- How to Run DeepSeek R1 Free on Your Own ComputerCreative AI ToolZ · 97 views · 28 Oct
- ChatGPT Bhool Jao! DeepSeek R1 Free Offline Setup 🚀🔥 #shortsAgentic Tech · 91 views · 31 Oct
- Which DeepSeek-R1 size fits your computer? #shortsThe NextGen Ai Frontier · 91 views · 27 Oct
- Stop Paying For ChatGPT! Run DeepSeek R1 Locally 🚀💻 #shortsAgentic Tech · 57 views · 1 Nov
- Arsitektur DeepSeek-R1: Mengapa Model MoE 671B Memangkas Biaya AI Hingga 90% #ShortsTata Kreasi Digital · 47 views · 30 Oct
- Running DeepSeek-R1 Locally on an M2 Mac 💻 #shortsTrendLoop · 47 views · 25 Oct
- How DeepSeek-R1 Learned to Reason: 16 Answers, 5 RightAshish Choudhary · 46 views · 25 Oct
- EP9 | How AI Learned to Think: o1, DeepSeek-R1 and the “Aha Moment”AI Signal · 37 views · 31 Oct
- DeepSeek R1: 1-Line Prompt vs 500-Word Prompt #shortsThe AI Method · 27 views · 23 Oct
Alternatives
other vendors · similar capability- 12.9
- 8.5
- 11.6
- 13.1
Want DeepSeek R1 on OSMEXO?
Sign in to request it. Requests are reviewed; a request does not guarantee availability.