modelbenchmark.io

DeepSeek R1 0528 Qwen3 8B

DeepSeek · deepseek-r1-0528-qwen3-8b

Compare

DeepSeek R1 0528 distilled into Qwen3 8B for mathematics, coding, and reasoning

Specification

most-agreed values

Context
128K
Max output
32K
Released
2025-05-29
Knowledge cutoff
—
Retires
—
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.06
Output
$0.09

Available from 2 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
novita$0.06$0.09——128K32K—
novita-ai$0.06$0.09——128K32K—

More from DeepSeek

most-hosted first