DeepSeek R1 Distill Llama 70B · deepinfra

DeepSeek-R1-Distill-Llama-70B is a highly efficient language model that leverages knowledge distillation to achieve state-of-the-art performance. This model distills the reasoning patterns of larger models into a smaller, more agile architecture, resulting in exceptional results on benchmarks like AIME 2024, MATH-500, and LiveCodeBench. With 70 billion parameters, DeepSeek-R1-Distill-Llama-70B offers a unique balance of accuracy and efficiency, making it an ideal choice for a wide range of natural language processing tasks.

Modelo baseTodos os modelos desta baseTodos os modelos do provedorao provedor

Leia também: Preço da API do DeepSeek: V4 Pro e V4 Flash em cada provedor

Todos os modelos DeepSeek em todos os provedores

Entrada, $/1M $0.70

Saída, $/1M $0.80

Contexto 131 072

Aceita —

Última verificação 04.11.2026 12:00:14 UTC

Fonte —