DeepSeekDeepSeek

DeepSeek R1 Distill 70B

Reasoning capabilities distilled into 70B Llama

DeepSeek R1 Distill 70B transfers the chain-of-thought reasoning abilities of the full R1 model into a 70B Llama architecture via knowledge distillation. It offers strong reasoning performance at a fraction of the full model's cost.

Try DeepSeek R1 Distill 70B

Specifications

Context window128k tokens
Input price$0.230 / 1M tokens
Output price$0.690 / 1M tokens
Credits per query3 cr
Released2025-01
LicenseMIT

Features

Code

Benchmark Scores

What do these mean?

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

PhD-level science & reasoning

Mathematical olympiad problems

Chatbot Arena human preference ranking

Python coding — pass@1 rate

86.7%

Competition-level mathematics

93%

General knowledge across 57 academic domains

86%

Multi-turn instruction following (out of 10)

Real-world GitHub issue resolution rate