modelbenchmark.io

DeepSeek-V3.1

DeepSeek · v3

Compare

Hybrid-reasoning DeepSeek model with thinking and non-thinking modes

Specification

most-agreed values

Context
164K
Max output
82K
Released
2025-08-21
Knowledge cutoff
Retires
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.58
Output
$1.68

Available from 2 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
amazon-bedrock$0.58$1.68164K82K
bedrock_converse$0.58$1.68164K82K

Other listings of this model

this page is one of them

The corpus files DeepSeek-V3.1 under several keys. This page is the v3 listing. The full record — every host, every price and every benchmark score — is on the main DeepSeek-V3.1 page.

More from DeepSeek

most-hosted first