modelbenchmark.io

DeepSeek R1 Llama 70B Abliterated

DeepSeek · deepseek-r1-distill-llama-70b-abliterated

Compare

DeepSeek reasoning model for multi-step analysis, math, coding, and tools

Specification

most-agreed values

Context
16K
Max output
8K
Released
2024-01-01
Knowledge cutoff
Retires
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.70
Output
$0.70
Cache read
$0.35

Available from 1 host

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
nano-gpt · huihui-ai$0.70$0.70$0.3516K8K

More from DeepSeek

most-hosted first