---
id: "deepseek/deepseek-r1-distill-llama-70b"
also: ["deepseek/deepseek-r1-distill-llama-70b", "deepseek-ai/DeepSeek-R1-Distill-Llama-70B", "hf/deepseek-ai/DeepSeek-R1-Distill-Llama-70B", "requesty/deepseek/deepseek-r1-distill-llama-70b"]
cheapest_list_usd_per_m: "0.23 in, 0.69 out, at deepinfra on requesty"
cheapest_effective_usd_per_m: "0.23 in, 0.69 out, at deepinfra on requesty"
context: 8192
max_output: 7372
input: ["text"]
output: ["text"]
released: "2025-01-23"
params: ["frequency_penalty", "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "repetition_penalty", "seed", "stop", "temperature", "top_k", "top_p"]
endpoints: 5
gateways: "hf (2), requesty (2), openrouter (1)"
no_training: 3
trains: 0
retains_prompts: 0
---
# DeepSeek: R1 Distill Llama 70B

DeepSeek R1 Distill Llama 70B is a distilled large language model based on [Llama-3.3-70B-Instruct](/meta-llama/llama-3.3-70b-instruct), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). The model combines advanced distillation techniques to achieve high performance across...