All Models
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...
Benchmarks
Available Providers (5)
| Provider | Model ID | Input Cost | Output Cost | Context | Max Output | Docs |
|---|---|---|---|---|---|---|
 Helicone | deepseek-r1-distill-llama-70b | $0.03/MTok | $0.13/MTok | 128K | 4.1K | |
 FastRouter | deepseek-ai/deepseek-r1-distill-llama-70b | $0.03/MTok | $0.14/MTok | 131.1K | 131.1K | |
 Alibaba (China) | deepseek-r1-distill-llama-70b | $0.29/MTok | $0.86/MTok | 32.8K | 16.4K | |
 NovitaAI | deepseek/deepseek-r1-distill-llama-70b | $0.80/MTok | $0.80/MTok | 8.2K | 8.2K | |
 DigitalOcean | deepseek-r1-distill-llama-70b | $0.99/MTok | $0.99/MTok | 32.7K | 8.2K |
Capabilities
Reasoning
Tool Calling
Attachments
Open Weights
Structured Output