modelbenchmark.io

DeepSeek V3/Chat Cheaper

DeepSeek · deepseek-chat-cheaper

Compare

Chat-tuned GPT model for conversational assistance, writing, and tool workflows

Specification

most-agreed values

Context
128K
Max output
8K
Released
2025-04-15
Knowledge cutoff
Retires
Open weights
yes
Input
text, pdf
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.10
Output
$0.425
Cache read
$0.05

Available from 1 host

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
nano-gpt$0.10$0.425$0.05128K8K

More from DeepSeek

most-hosted first