modelbenchmark.io

DeepSeek V3 (Turbo)

DeepSeek · deepseek-v3-turbo

Compare

Fast DeepSeek model for efficient chat, coding help, and agent loops

Specification

most-agreed values

Context
64K
Max output
16K
Released
2025-03-05
Knowledge cutoff
Retires
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.40
Output
$1.30

Available from 2 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
novita$0.40$1.3064K16K
novita-ai$0.40$1.3064K16K

More from DeepSeek

most-hosted first