DeepSeek: R1 Distill Llama 70B

Text input Text output Free Option
Author's 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.

Key Specifications
Cost
$$$$
Context
131K
Parameters
70B
Released
Jan 23, 2025
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Seed Max Tokens Presence Penalty Frequency Penalty Include Reasoning Response Format Temperature Top P Stop Min P Reasoning
Features

This model supports the following features:

Response Format Reasoning
Performance Summary

DeepSeek R1 Distill Llama 70B demonstrates strong performance across a range of benchmarks, particularly excelling in specialized areas. While its speed ranks among the slower models (6th percentile across benchmarks), its pricing is competitive (47th percentile). The model showcases exceptional capabilities in General Knowledge and Reasoning, achieving 99.8% and 84.0% accuracy respectively, placing it in the 90th and 84th percentiles for these categories. Its Ethics performance is also robust at 99.0% accuracy. In Code Generation, it achieves a commendable 87.0% accuracy, further supported by impressive external benchmarks like a 1633 CodeForces Rating and 94.5% on MATH-500. The model's ability to achieve 70.0% pass@1 on AIME 2024 highlights its advanced problem-solving skills. A notable weakness is its speed, consistently ranking in the lower percentiles for duration across all benchmarks. Despite this, its competitive pricing and high accuracy in complex domains, especially those requiring deep understanding and logical inference, position DeepSeek R1 Distill Llama 70B as a powerful and cost-effective solution for tasks demanding high-quality output, particularly in technical and knowledge-intensive applications.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $0.05
Completion $0.05

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
DeepInfra
DeepInfra | deepseek/deepseek-r1-distill-llama-70b 131K $0.05 / 1M tokens $0.05 / 1M tokens
InferenceNet
InferenceNet | deepseek/deepseek-r1-distill-llama-70b 128K $0.05 / 1M tokens $0.05 / 1M tokens
Lambda
Lambda | deepseek/deepseek-r1-distill-llama-70b 131K $0.05 / 1M tokens $0.05 / 1M tokens
Phala
Phala | deepseek/deepseek-r1-distill-llama-70b 131K $0.05 / 1M tokens $0.05 / 1M tokens
GMICloud
GMICloud | deepseek/deepseek-r1-distill-llama-70b 131K $0.05 / 1M tokens $0.05 / 1M tokens
Nebius
Nebius | deepseek/deepseek-r1-distill-llama-70b 131K $0.05 / 1M tokens $0.05 / 1M tokens
SambaNova
SambaNova | deepseek/deepseek-r1-distill-llama-70b 131K $0.05 / 1M tokens $0.05 / 1M tokens
Groq
Groq | deepseek/deepseek-r1-distill-llama-70b 131K $0.05 / 1M tokens $0.05 / 1M tokens
Novita
Novita | deepseek/deepseek-r1-distill-llama-70b 32K $0.05 / 1M tokens $0.05 / 1M tokens
Together
Together | deepseek/deepseek-r1-distill-llama-70b 131K $0.05 / 1M tokens $0.05 / 1M tokens
Cerebras
Cerebras | deepseek/deepseek-r1-distill-llama-70b 32K $0.05 / 1M tokens $0.05 / 1M tokens
Chutes
Chutes | deepseek/deepseek-r1-distill-llama-70b 131K $0.05 / 1M tokens $0.05 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Free Executions Accuracy Cost Duration
Other Models by deepseek