DeepSeekDeepSeek

DeepSeek R1

Open-weight reasoning model matching o1

DeepSeek R1 is a pure reasoning model trained with reinforcement learning on chain-of-thought traces. It matches OpenAI's o1 on math and coding benchmarks while being open-weight and significantly cheaper to run via API.

Try DeepSeek R1

Specifications

Context window163k tokens
Input price$0.550 / 1M tokens
Output price$2.19 / 1M tokens
Credits per query5 cr
Released2025-01
LicenseMIT

Features

JSON modeCode

Benchmark Scores

What do these mean?

Sourced from official model cards and academic papers. Higher is better.

PhD-level science & reasoning

71.5%

Mathematical olympiad problems

79.8%

Chatbot Arena human preference ranking

1316

Python coding — pass@1 rate

92.8%

Competition-level mathematics

97.3%

General knowledge across 57 academic domains

90.8%

Multi-turn instruction following (out of 10)

Real-world GitHub issue resolution rate

Run locally

Download and run this model on your own hardware — no API key or internet required after setup.

Min VRAM8 GB
Rec. VRAM10 GB
Best VRAM15 GB
Parameters14B
Speed~22 tok/s
Context64K tokens

Ollama

Terminal

Run this command in your terminal. Ollama downloads and manages the model locally.

ollama pull deepseek-r1:14b