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...
Input
$0.70
per 1M tokens
Output
$0.80
per 1M tokens
Blended
$0.72
per 1M tokens
Cheaper than 46% of models. Median price is $0.56/1M tokens.
Daily
$0.72
Monthly
$21.75
44
tokens/sec
Faster than 15% of models
0.38
seconds
Faster than 92% of models
45.45
seconds
Faster than 11% of models
Market Median
86 tok/s
48% slower
Median TTFT
1.07s
65% faster
Throughput/Dollar
61
tok/s per $/1M
Speed Comparison
Context Window
131K
tokens
Larger than 33% of models
Max Output
16K
tokens
13% of context
Quality Index
16.0
302nd of 507
Top 60%
Coding Index
11.4
300th of 417
Top 72%
Math Index
53.7
133rd of 269
Top 50%
Price/1M
$0.72
346th cheapest
29% above median
Top 54%
Speed
44 tok/s
Top 85%
TTFT
0.38s
Context Window
131K
201st largest
Top 67%