DeepSeek R1 Distill Llama 70B

DeepSeek deepseek-r1-distill-llama-70b

Model Information
Slug deepseek-r1-distill-llama-70b
Release Date January 20, 2025
Aliases deepseek-r1-distill-llama-70b
Organization
Name DeepSeek
Description

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 multiple benchmarks, including: - AIME 2024 pass@1: 70.0 - MATH-500 pass@1: 94.5 - CodeForces Rating: 1633 The model leverages fine-tuning from DeepSeek R1's outputs, enabling competitive performance comparable to larger frontier models. Context: 131072

Available at 10 Providers
Provider Input Price ($/1M) Output Price ($/1M) Free
Chutes $0.03 $0.11
Helicone $0.03 $0.13
FastRouter $0.03 $0.14
OpenRouter $0.03 $0.11
Vultr $0.20 $0.20
Alibaba (China) $0.29 $0.86
AIHubMix $0.60 $0.60
OVHcloud AI Endpoints $0.74 $0.74
Scaleway $0.90 $0.90
Fireworks AI $0.90 $0.90