DeepSeek: R1 Distill Llama 70B

DeepSeek R1 Distill Llama 70B is a distilled large language model based on Llama-3.3-70B-Instruct, using outputs from 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...

Yes. The pricing shown on this page for R1 Distill Llama 70B is zero, so you are not charged for prompt or completion tokens. Free endpoints are rate limited — see the rate limit docs.

R1 Distill Llama 70B has a 128,000 token context window.

DeepSeek V4 Flash Vision Exp, DeepSeek V4 Pro 0813, DeepSeek V4 Flash 0731 and 9 more are other text models from DeepSeek.

R1 Distill Llama 70B was released on January 23, 2025. Its knowledge cutoff is July 31, 2024.