ThePromptBuddy logoThePromptBuddy

DeepSeek

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...

Specifications
ProviderDeepSeek
Input pricing$0.80/M tokens
Output pricing$0.80/M tokens
Context length8K tokens
Max output8K tokens
Input modalities
text
Output modalities
text
TokenizerLlama3
Knowledge cutoff2024-07-31
Content moderatedNo
HuggingFacedeepseek-ai/DeepSeek-R1-Distill-Llama-70B

Supported Parameters

frequency_penaltyinclude_reasoningmax_tokenspresence_penaltyreasoningrepetition_penaltyseedstoptemperaturetop_ktop_p