DeepSeek R1 — DeepSeek

DeepSeek R1 is a reasoning model: it "thinks" step by step before answering, which makes it excellent at math, logic and code. Being open-weight, it offers a depth of reasoning that is rare for free.

Type : Reasoning · Parameters : MoE architecture · Context : 128K tokens

Strengths

• Step-by-step reasoning
• Mathematics and logic
• Problem solving

Best for

• Math problems
• Debugging and algorithms
• Logic questions

DeepSeek R1 is served via OpenRouter, HuggingFace, included in your subscription with dozens of other models — one price, every model.