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...

• Context window: 128,000 tokens
• Input: text
• Output: text
• Pricing: $0.8/M input tokens, $0.8/M output tokens

View on OpenRouter. Model data sourced from OpenRouter.