modelbenchmark.io

DeepSeek R1 Fast

DeepSeek · deepseek-r1-sambanova

Compare

Compact GPT model for low-latency assistance and high-volume workloads

Specification

most-agreed values

Context
128K
Max output
4K
Released
2025-02-20
Knowledge cutoff
Retires
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$4.998
Output
$6.987
Cache read
$2.499

Available from 1 host

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
nano-gpt$4.998$6.987$2.499128K4K

More from DeepSeek

most-hosted first