All AI models · LLM benchmarks · Methodology

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...

Model facts

Context window
8K tokens
Maximum output
7K tokens
Cheapest paid input
$0.8 per 1M tokens
Cheapest paid output
$0.8 per 1M tokens
Open weights
yes
Providers
2

Capabilities and modalities

reasoning, temperature control, open weights, text.

Observed price history

  • 2026-08-24: $0.8 input / $0.8 output per 1M tokens

API providers

  • OpenRouter — model id deepseek/deepseek-r1-distill-llama-70b; $0.8 input / $0.8 output per 1M tokens; provider documentation
  • Kilo Gateway (DeepSeek) — model id deepseek/deepseek-r1-distill-llama-70b; $0.8 input / $0.8 output per 1M tokens; provider documentation