arrow_backBack to all models
DeepSeekactive

R1 Distill Llama 70B

Released at: January 23, 2025

API StatusAvailable for integration
Context Window128,000 tokens
Input Price / MTok$0.80
Output Price / MTok$0.80

Model Overview

DeepSeek · Active Model

  • Long-Context
  • API Available
  • Vetted Benchmarks
  • Production Ready

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...

Developer
DeepSeek
Release Date
January 23, 2025
Context Window
128,000 tokens171 words
API Access
Publicly AvailableIntegrate via official API
Input Cost
$0.80per million tokens
Output Cost
$0.80per million tokens
SHARE MODEL:

Vetted Benchmarks

mmluScore: 85.2% (Ranked top 59%)
humanevalScore: 88.3% (Ranked top 52%)
mathScore: 70% (Ranked top 62%)
mt_benchScore: 9.05% (Ranked top 50%)
gpqaScore: 44.5% (Ranked top 66%)
hellaswagScore: 86% (Ranked top 66%)

How does this model compare?

Evaluate benchmark standing and performance rankings vs all other tracked models.

Compare with another model →