Loading...
Loading...
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.
Quality Index
16.0
245th of 444
Top 56%
Coding Index
11.4
243rd of 354
Top 69%
Math Index
53.7
132nd of 268
Top 50%
Price/1M
$0.88
470th cheapest
192% above median
Top 69%
Speed
56 tok/s
Top 43%
TTFT
0.82s
Context Window
131K
145th largest
Top 63%
Input
$0.70
per 1M tokens
Output
$1.05
per 1M tokens
Blended
$0.88
per 1M tokens
Cheaper than 31% of models. Median price is $0.30/1M tokens.
Daily
$0.88
Monthly
$26.25
56
tokens/sec
Faster than 57% of models
0.82
seconds
Faster than 35% of models
36.45
seconds
Faster than 7% of models
Market Median
45 tok/s
24% faster
Median TTFT
0.42s
96% slower
Throughput/Dollar
64
tok/s per $/1M
Speed Comparison
Context Window
131K
tokens
Larger than 37% of models
Max Output
16K
tokens
13% of context